Download:
pdf |
pdfC. Attachment Table of Contents
Attachment 1: BJS authorizing statute; Title 42, United States Code, Section 3732…………………………………2
Attachment 2: 2013 School Crime Supplement (SCS) Questionnaire………………………………………………………7
Attachment 3: 2013 SCS Item Description and Rationale………………………………………………………………………20
Attachment 4: Census Bureau introductory letter for new households (NCVS-572(L))…………………………30
Attachment 5: Census Bureau introductory letter for reinterview households (NCVS-573(L))………………33
Attachment 6: SCS informational brochure for parents (in English)………………………………………………………36
Attachment 7: SCS informational brochure for parents (in Spanish)…………………………………………………….39
Attachment 8: SCS informational brochure for students (in English)……………………………………………………42
Attachment 9: SCS informational brochure for students (in Spanish)……………………………………………………45
Attachment 10: 2011 SCS Nonresponse bias analysis report…………………………………………………………………48
Attachment 1
BJS authorizing statute; Title 42, United States Code, Section 3732
-CITE42 USC Sec. 3732
01/26/98
-EXPCITETITLE 42 - THE PUBLIC HEALTH AND WELFARE
CHAPTER 46 - JUSTICE SYSTEM IMPROVEMENT
SUBCHAPTER III - BUREAU OF JUSTICE STATISTICS
-HEADSec. 3732. Bureau of Justice Statistics
-STATUTE(a) Establishment
There is established within the Department of Justice, under the general authority of the Attorney General, a
Bureau of Justice Statistics (hereinafter referred to in this subchapter as ''Bureau'').
(b) Appointment of Director; experience; authority; restrictions
The Bureau shall be headed by a Director appointed by the President, by and with the advice and consent of the
Senate. The Director shall have had experience in statistical programs. The Director shall have final authority for all
grants, cooperative agreements, and contracts awarded by the Bureau. The Director shall report to the Attorney
General through the Assistant Attorney General. The Director shall not engage in any other employment than that of
serving as Director; nor shall the Director hold any office in, or act in any capacity for, any organization, agency, or
institution with which the Bureau makes any contract or other arrangement under this Act.
(c) Duties and functions of Bureau
The Bureau is authorized to (1) make grants to, or enter into cooperative agreements or contracts with public agencies, institutions of higher
education, private organizations, or private individuals for purposes related to this subchapter; grants shall be made
subject to continuing compliance with standards for gathering justice statistics set forth in rules and regulations
promulgated by the Director;
(2) collect and analyze information concerning criminal victimization, including crimes against the elderly, and
civil disputes;
(3) collect and analyze data that will serve as a continuous and comparable national social indication of the
prevalence, incidence, rates, extent, distribution, and attributes of crime, juvenile delinquency, civil disputes, and
other statistical factors related to crime, civil disputes, and juvenile delinquency, in support of national, State, and
local justice policy and decisionmaking;
(4) collect and analyze statistical information, concerning the operations of the criminal justice system at the
Federal, State, and local levels;
(5) collect and analyze statistical information concerning the prevalence, incidence, rates, extent, distribution,
and attributes of crime, and juvenile delinquency, at the Federal, State, and local levels;
(6) analyze the correlates of crime, civil disputes and juvenile delinquency, by the use of statistical information,
about criminal and civil justice systems at the Federal, State, and local levels, and about the extent, distribution and
attributes of crime, and juvenile delinquency, in the Nation and at the Federal, State, and local levels;
(7) compile, collate, analyze, publish, and disseminate uniform national statistics concerning all aspects of
criminal justice and related aspects of civil justice, crime, including crimes against the elderly, juvenile delinquency,
criminal offenders, juvenile delinquents, and civil disputes in the various States;
(8) recommend national standards for justice statistics and for insuring the reliability and validity of justice
statistics supplied pursuant to this chapter;
(9) maintain liaison with the judicial branches of the Federal and State Governments in matters relating to
justice statistics, and cooperate with the judicial branch in assuring as much uniformity as feasible in statistical
systems of the executive and judicial branches;
(10) provide information to the President, the Congress, the judiciary, State and local governments, and the
general public on justice statistics;
(11) establish or assist in the establishment of a system to provide State and local governments with access to
Federal informational resources useful in the planning, implementation, and evaluation of programs under this Act;
(12) conduct or support research relating to methods of gathering or analyzing justice statistics;
(13) provide for the development of justice information systems programs and assistance to the States and units
of local government relating to collection, analysis, or dissemination of justice statistics;
(14) develop and maintain a data processing capability to support the collection, aggregation, analysis and
dissemination of information on the incidence of crime and the operation of the criminal justice system;
(15) collect, analyze and disseminate comprehensive Federal justice transaction statistics (including statistics
on issues of Federal justice interest such as public fraud and high technology crime) and to provide technical
assistance to and work jointly with other Federal agencies to improve the availability and quality of Federal justice
data;
(16) provide for the collection, compilation, analysis, publication and dissemination of information and
statistics about the prevalence, incidence, rates, extent, distribution and attributes of drug offenses, drug related
offenses and drug dependent offenders and further provide for the establishment of a national clearinghouse to
maintain and update a comprehensive and timely data base on all criminal justice aspects of the drug crisis and to
disseminate such information;
(17) provide for the collection, analysis, dissemination and publication of statistics on the condition and
progress of drug control activities at the Federal, State and local levels with particular attention to programs and
intervention efforts demonstrated to be of value in the overall national anti-drug strategy and to provide for the
establishment of a national clearinghouse for the gathering of data generated by Federal, State, and local criminal
justice agencies on their drug enforcement activities;
(18) provide for the development and enhancement of State and local criminal justice information systems, and
the standardization of data reporting relating to the collection, analysis or dissemination of data and statistics about
drug offenses, drug related offenses, or drug dependent offenders;
(19) provide for research and improvements in the accuracy, completeness, and inclusiveness of criminal
history record information, information systems, arrest warrant, and stolen vehicle record information and
information systems and support research concerning the accuracy, completeness, and inclusiveness of other
criminal justice record information;
(20) maintain liaison with State and local governments and governments of other nations concerning justice
statistics;
(21) cooperate in and participate with national and international organizations in the development of uniform
justice statistics;
(22) ensure conformance with security and privacy requirement of section 3789g of this title and identify,
analyze, and participate in the development and implementation of privacy, security and information policies which
impact on Federal and State criminal justice operations and related statistical activities; and
(23) exercise the powers and functions set out in subchapter
VIII of this chapter.
(d) Justice statistical collection, analysis, and dissemination to insure that all justice statistical collection, analysis,
and dissemination is carried out in a coordinated manner, the Director is authorized to (1) utilize, with their consent, the services, equipment, records, personnel, information, and facilities of other
Federal, State, local, and private agencies and instrumentalities with or without reimbursement therefor, and to enter
into agreements with such agencies and instrumentalities for purposes of data collection and analysis;
(2) confer and cooperate with State, municipal, and other local agencies;
(3) request such information, data, and reports from any Federal agency as may be required to carry out the
purposes of this chapter;
(4) seek the cooperation of the judicial branch of the Federal Government in gathering data from criminal
justice records; and
(5) encourage replication, coordination and sharing among justice agencies regarding information systems,
information policy, and data.
(e) Furnishing of information, data, or reports by Federal agencies Federal agencies requested to furnish
information, data, or reports pursuant to subsection (d)(3) of this section shall provide such information to the
Bureau as is required to carry out the purposes of this section.
(f) Consultation with representatives of State and local government and judiciary In recommending standards for
gathering justice statistics under this section, the Director shall consult with representatives of State and local
government, including, where appropriate, representatives of the judiciary.
-SOURCE(Pub. L. 90-351, title I, Sec. 302, as added Pub. L. 96-157, Sec. 2, Dec. 27, 1979, 93 Stat. 1176; amended Pub. L.
98-473, title II, Sec. 605(b), Oct. 12, 1984, 98 Stat. 2079; Pub. L. 100-690, title VI, Sec. 6092(a), Nov. 18, 1988,
102 Stat. 4339; Pub. L. 103-322, title XXXIII, Sec. 330001(h)(2), Sept. 13, 1994, 108 Stat. 2139.)
-REFTEXTREFERENCES IN TEXT
This Act, referred to in subsecs. (b) and (c)(11), is Pub. L. 90-351, June 19, 1968, 82 Stat. 197, as amended,
known as the Omnibus Crime Control and Safe Streets Act of 1968. For complete classification of this Act to the
Code, see Short Title note set out under section 3711 of this title and Tables.
-MISC2PRIOR PROVISIONS
A prior section 3732, Pub. L. 90-351, title I, Sec. 302, June 19, 1968, 82 Stat. 200; Pub. L. 93-83, Sec. 2, Aug. 6,
1973, 87 Stat. 201; Pub. L. 94-503, title I, Sec. 110, Oct. 15, 1976, 90 Stat. 2412, related to establishment of State
planning agencies to develop comprehensive State plans for grants for law enforcement and criminal justice
purposes, prior to the general amendment of this chapter by Pub. L. 96-157.
AMENDMENTS
1994 - Subsec. (c)(19). Pub. L. 103-322 substituted a semicolon for period at end.
1988 - Subsec. (c)(16) to (23). Pub. L. 100-690 added pars. (16) to (19) and redesignated former pars. (16) to
(19) as (20) to (23), respectively.
1984 - Subsec. (b). Pub. L. 98-473, Sec. 605(b)(1), inserted provision requiring Director to report to Attorney
General through Assistant Attorney General.
Subsec. (c)(13). Pub. L. 98-473, Sec. 605(b)(2)(A), (C), added par. (13) and struck out former par. (13) relating
to provision of financial and technical assistance to States and units of local government relating to collection,
analysis, or dissemination of justice statistics.
Subsec. (c)(14), (15). Pub. L. 98-473, Sec. 605(b)(2)(C), added pars. (14) and (15). Former pars. (14) and (15)
redesignated (16) and (17), respectively.
Subsec. (c)(16). Pub. L. 98-473, Sec. 605(b)(2)(A), (B), redesignated par. (14) as (16) and struck out former par.
(16) relating to insuring conformance with security and privacy regulations issued under section 3789g of this title.
Subsec. (c)(17). Pub. L. 98-473, Sec. 605(b)(2)(B), redesignated par. (15) as (17). Former par. (17) redesignated
(19).
Subsec. (c)(18). Pub. L. 98-473, Sec. 605(b)(2)(D), added par. (18).
Subsec. (c)(19). Pub. L. 98-473, Sec. 605(b)(2)(B), redesignated former par. (17) as (19).
Subsec. (d)(1). Pub. L. 98-473, Sec. 605(b)(3)(A), inserted '', and to enter into agreements with such agencies
and instrumentalities for purposes of data collection and analysis''.
Subsec. (d)(5). Pub. L. 98-473, Sec. 605(b)(3)(B)-(D), added par. (5).
EFFECTIVE DATE OF 1984 AMENDMENT
Amendment by Pub. L. 98-473 effective Oct. 12, 1984, see section 609AA(a) of Pub. L. 98-473, set out as an
Effective Date note under section 3711 of this title.
-SECREFSECTION REFERRED TO IN OTHER SECTIONS
This section is referred to in section 5603 of this title.
Attachment 2
2013 School Crime Supplement (SCS) Questionnaire
NOTICE - We are conducting this survey under the authority of Title 13, United States Code, Section 8. Section 9 of this law requires us to keep all information
about you and your household strictly confidential. We may use this information only for statistical purposes. Also, Title 42, Section 3732, United States Code,
authorizes the Bureau of Justice Statistics, Department of Justice, to collect information using this survey. Title 42, Sections 3789g and 3735, United States Code also
requires us to keep all information about you and your household strictly confidential.
ASK OF ALL PEOPLE AGES 12-18
FORM
SCS-1
Economics and Statistics Administration
U.S. Census Bureau
ACTING AS COLLECTING AGENCY FOR THE
BUREAU OF JUSTICE STATISTICS
U.S. DEPARTMENT OF JUSTICE
We estimate that it will take from 5 to 15 minutes to complete this interview with 10 minutes
being the average time. If you have any comments regarding these estimates or any other
aspect of this survey, send them to the Associate Director for Finance and Administration,
Room 2027, U.S. Census Bureau, Washington DC 20233, or to the Office of Information and
Regulatory Affairs, Office of Management and Budget, Washington, DC 20503. According to
the Paperwork Reduction Act of 1995, no such persons are required to respond to a collection
of information unless such collection displays a valid OMB control number.
SCHOOL CRIME SUPPLEMENT
TO THE NATIONAL CRIME
VICTIMIZATION SURVEY
2013
Control number
PSU
Segment/Suffix
Sample Designation/Suffix
A. FR Code
Serial/Suffx
HH No.
Spinoff
Indicator
QUESTIONNAIRE
B. Respondent
Line No.
001
Age
002
FIELD REPRESENTATIVE - Complete an SCS-1 form for all
NCVS interviewed people ages 12-18. Do NOT complete an
SCS-1 form for Type Z noninterview people or for people in
Type A noninterview households.
1
2
3
4
5
INTRO 1 -
Name
003
D. Reason for SCS noninterview
005
C. Type of SCS Interview
004
U.S. DEPARTMENT OF COMMERCE
2 Refused
} SKIP to END
3 Not available
} SKIP to END
4 NCVS completed in a
Language other than } SKIP to END
English or Spanish
Personal - Self
Telephone – Self
Personal - Proxy
Telephone - Proxy
Noninterview – SKIP to ITEM D
Now, I would like to ask some questions about your experiences at school. We estimate the survey will
take about 10 minutes. The law authorizes the collection of this data and requires us to keep all
information about you and your household strictly confidential.
E. SCREEN QUESTIONS FOR SUPPLEMENT
1a.
Did you attend school at any time this school year?
_________________________________________
1b.
1 Yes
2 No - SKIP to END
_____________________________________________
006
During that time, were you ever home-schooled?
That is, did you receive ANY of that schooling at
home, rather than in a public or private school?
_________________________________________
092
1c.
Was all of your schooling this school year home
schooling?
007
2a.
During the time you were home-schooled this
school year, what grade would you have been in if
you were in a public or private school?
093
1 Yes
2 No - SKIP to 2b
____________________________________________
1 Yes - SKIP to END
2 No
0 Fifth or under - SKIP to END
1
2
3
4
5
6
7
8
Sixth
Seventh
Eighth
Ninth
Tenth
Eleventh
Twelfth
Other - Specify ______
SKIP to
INTRO 2
9 College/GED/Post-graduate/
Other noneligible – SKIP to END
2b.
What grade are you in?
008
0 Fifth or under - SKIP to END
1 Sixth
2 Seventh
3 Eighth
4 Ninth
SKIP to 3
5 Tenth
6 Eleventh
7 Twelfth
8 Other - Specify ________
9 College/GED/Post-graduate/
Other noneligible - SKIP to END
FIELD REPRESENTATIVE - Read introduction only if any of the boxes 1-8 are marked in item 2a.
INTRO 2 - The following questions pertain only to your attendance at a public or private school and not to being homeschooled.
3.
In what month did your current school year begin?
009
1 August
2 September
3 Other - Specify
________________________
F. ENVIRONMENTAL QUESTIONS
6a.
What is the complete name of your school?
________________________________________
6b.
In what city, county, and state is your school
located?
7a.
Is your school public or private?
012 School Name
013 City
014 County
015 State
____________________________________________
1 Public - ASK 7b
2 Private - SKIP to 7c
______________________________________________
7b.
Is this the regular school that most of the students in
your neighborhood attend?
________________________________________
1 Yes } SKIP to 8
2 No } SKIP to 8
_________________________________________
7c.
Is your school affiliated with a religion?
018
Page 2
016
017
1 Yes
2 No
3 Don’t know
FORM SCS-1 (09/06/2012)
8.
What grades are taught in your school?
Grades:
Pre-K or Kindergarten
9.
00
01
02
03
04
05
06
07
08
09
10
11
12
13
20
30
020
(lowest)
TO
021
(highest)
H.S. Senior
Post-graduate
All ungraded
All Special Education
How do you get to school most of the time this
school year?
022
1
2
3
4
5
6
Walk
School bus
Public bus, subway, train
Car
Bicycle, motorbike, or motorcycle
Some other way - Specify
FIELD REPRESENTATIVE - If multiple modes are used,
code the mode in which the student spends the most
time.
10.
How long does it take you to get from your home to
school most of the time?
023
1
2
3
4
5
Less than 15 minutes
15-29 minutes
30-44 minutes
45-59 minutes
60 minutes or longer
11.
How do you get home from school most of the time
this school year?
024
1
2
3
4
5
6
Walk
School bus
Public bus, subway, train
Car
Bicycle, motorbike, or motorcycle
Some other way - Specify
_____________________________
FIELD REPRESENTATIVE - If multiple modes are used,
code the mode in which the student spends the most
time.
If the student volunteers that he or she does not go
directly home after school, record the mode that the
student uses to get to his or her first destination after
school.
12a.
How often do you leave school grounds at lunch
time?
(READ CATEGORIES)
___________________________________________
12b.
Are students in your grade level allowed to leave
school grounds to eat lunch?
026 1 Never
2 Once or twice a year
3 Once or twice a month
4 Once or twice a week
5 Almost every day
___________________________________________
025 1 Yes
2 No
3 Don’t know
13a.
During this school year, have you participated in any
of the following activities sponsored by your school:
Yes
No
a. Athletic teams at school?
120
1
2
b.
121
1
2
c. Performing arts, for example, Band, Choir,
Orchestra, or Drama?
122
1
2
d. Academic clubs, for example, Debate Team, Honor
Society, Spanish Club, or Math Club?
123
1
2
e. Student government?
124
1
2
f. [IF GRADES 6, 7, or 8 ASK:] Volunteer or community
service clubs sponsored by your school, for
example, Peer Mediators, Ecology Club, or
Recycling Club?
125
1
2
126
1
Spirit groups, for example, Cheerleading, Dance
Team, or Pep Club?
[IF GRADES 9, 10, 11, or 12 ASK:] Volunteer or
community service clubs sponsored by your school,
for example, Peer Mediators, Ecology Club, Key
Club, or Interact? Do not include community
service hours required for graduation.
g. Other school clubs or school activities?
2
Specify _____----------------------------------__
14a. Does your school take any measures to make sure
students are safe?
Yes
No
Don’t know School does not
have lockers
For example, does the school have:
Page 4
a. Security guards or assigned police officers?
028
1
2
3
b. Other school staff or other adults supervising the
hallway?
029
1
2
3
c.
Metal detectors, including wands?
030
1
2
3
d.
Locked entrance or exit doors during the day?
031
1
2
3
e.
A requirement that visitors sign in?
032
1
2
3
f.
Locker checks?
033
1
2
3
g. A requirement that students wear badges or
picture identification?
094
1
2
3
h.
One or more security cameras to monitor the
school?
095
1
2
3
i.
A code of student conduct, that is, a set of
written rules or guidelines that the school
provides you?
096
1
2
3
4
FORM SCS-1 (09/06/2012)
14b.
If you hear about a threat to school or student safety,
do you have a way to report it to someone in authority
without giving your name?
Yes
No
Don’t know
167
1
2
3
156
1
2
3
4
Never
Almost never
Sometimes
Most of the time
157
1
2
3
4
Never
Almost never
Sometimes
Most of the time
FIELD REPRESENTATIVE - The term ‘authority’ includes
the police, teachers, principals, security guards, or other
school staff. It does not include the student’s parents,
guardians, or peers.
15a.
In your classes, how often are you distracted from
doing your schoolwork because other students are
misbehaving, for example, talking or fighting?
(READ CATEGORIES.)
15b.
In general, how often do teachers punish students
during your classes?
(READ CATEGORIES.)
16a.
I am going to read a list of statements that could
describe a school. Thinking about your school,
would you strongly agree, agree, disagree, or
strongly disagree with the following...
Agree
Strongly
Disagree Disagree
a.
Everyone knows what the school rules are.
034
1
2
3
4
b.
The school rules are fair.
035
1
2
3
4
c.
The punishment for breaking school rules is the
same no matter who you are.
036
1
2
3
4
d.
The school rules are strictly enforced.
037
1
2
3
4
038
1
2
3
4
Strongly
Agree
Agree
Strongly
Disagree Disagree
e. If a school rule is broken, students know what
kind of punishment will follow.
16b.
Strongly
Agree
Thinking about the TEACHERS at your school,
would you strongly agree, agree, disagree, or
strongly disagree with the following…
a. Teachers treat students with respect.
127
1
2
3
4
b. Teachers care about students.
128
1
2
3
4
c. Teachers do or say things that make students
feel bad about themselves.
129
1
2
3
4
16c.
Thinking about all of the ADULTS at your school,
including teachers, would you strongly agree, agree,
disagree, or strongly disagree with the following…
Strongly
Agree
Agree
Disagree
Strongly
Disagree
There is an ADULT at school who…
16d.
a.
Really cares about you.
173SCS 1
2
3
4
b.
Notices when you are not there.
174SCS 1
2
3
4
c.
Listens to you when you have something to say.
175SCS 1
2
3
4
d.
Tells you when you do a good job.
176SCS 1
2
3
4
e.
Always wants you to do your best.
177SCS 1
2
3
4
f.
Believes that you will be a success.
178SCS 1
2
3
4
Strongly
Agree
Agree
Disagree
Strongly
Disagree
Thinking about FRIENDS at your school, would you
strongly agree, agree, disagree, or strongly disagree
with the following...
a. At school, you have a FRIEND you can talk to, who
cares about your feelings and what happens to
you.
16e.
16f.
Page 6
Thinking about the neighborhood where you live,
would you strongly agree, agree, disagree, or
strongly disagree with the following…
132
1
Strongly
Agree
2
Agree
3
Disagree
4
Strongly
Disagree
a. There is not a lot of crime in the neighborhood
where you live.
179SCS 1
2
3
4
b. You feel safe in the neighborhood where you live.
180SCS 1
2
3
4
Agree
Disagree
Thinking about the neighborhood where your school
is located, would you strongly agree, agree, disagree,
or strongly disagree with the following...
Strongly
Agree
a. There is not a lot of crime in the neighborhood
where you go to school.
181SCS 1
2
3
b. You feel safe in the neighborhood where you go to
school.
182SCS 1
2
3
Strongly
Disagree
4
4
FORM SCS-1 (09/06/2012)
INTRO 3
17a.
-
Now I have some questions about things that happen at school. For this survey, “at
school” includes the school building, on school property, on a school bus, or going to and from school.
Your answers will not be given to anyone.
The following question refers to the availability of
drugs and alcohol at your school.
Tell me if you don’t know what any of these items
are.
FIELD REPRESENTATIVE - For “Don’t Know”
responses, probe if necessary to determine if respondent
means they do not know if the drug is available or if they
do not know the drug.
FIELD REPRESENTATIVE - For each item ask,
Is it possible to get _______________ at your
school?
Yes
No
Don’t know
Don’t
know
drug
a. Alcoholic beverages
040
1
2
3
4
b. Marijuana
041
1
2
3
4
c. Crack
042
1
2
3
4
d. Other forms of cocaine
043
1
2
3
4
e. Uppers such as ecstasy, crystal meth or other
illegal stimulants
097
1
2
3
4
f. Downers such as GHB or sleeping pills
098
1
2
3
4
g. LSD or acid
045
1
2
3
4
h. PCP or angel dust
046
1
2
3
4
i.
Heroin or smack
047
1
2
3
4
j.
Prescription drugs illegally obtained without a
prescription, such as Oxycontin, Vicodin, or
Xannax
159
1
2
3
4
048
1
2
3
4
k. Other illegal drugs
If “Yes” is marked, ASK - What drugs?
(Exclude tobacco products.)
Specify _________________________________
FIELD REPRESENTATIVE - Refer to Drug Slang Card
(SCS-2). Reclassify the “other illegal drug(s)” to one of
the categories a-i if possible. If able to reclassify the
drug(s) mentioned, mark the “No” box in category k,
otherwise, mark the “Yes” box in category k and enter
the “other illegal drug(s)” mentioned in the Specify space.
17b.
During this school year, did you know for sure that
any students were on drugs or alcohol while they
were at school?
101
1 Yes
2 No
17c.
During this school year, did anyone offer, or try to
sell or give you an illegal drug other than alcohol or
tobacco at your school?
102
1 Yes
2 No
G. FIGHTING, BULLYING AND HATE BEHAVIORS
18a.
During this school year, have you been in one or
more physical fights at school?
18b.
During this school year, how many times have you
been in a physical fight at school?
19a.
103
104
1 Yes
2 No - SKIP to 19a
(Number of times)
Now I have some questions about what students do
at school that make you feel bad or are hurtful to
you. We often refer to this as being bullied. You
may include events you told me about already.
During this school year, has any student bullied
you?
That is, has another student...
(Read each category a-g.)
a. Made fun of you, called you names, or insulted
you, in a hurtful way?
b. Spread rumors about you or tried to make others
dislike you?
Yes
No
134
1
2
135
1
2
136
1
2
137
1
2
138
1
2
139
1
2
140
1
2
c. Threatened you with harm?
d. Pushed you, shoved you, tripped you, or spit on
you?
e. Tried to make you do things you did not want to
do, for example, give them money or other
things?
f.
Excluded you from activities on purpose?
g. Destroyed your property on purpose?
CHECK Item 19a
19b.
1 Yes - SKIP to 20a
2 No - SKIP to 19b
Are all categories a-g marked “No” in Q19a
above?
You just indicated that someone had bullied you
during this school year. Thinking about all of the
ways in which you were bullied, how often did all of
those things happen?
142
1 Once or twice this school year
2 Once or twice a month
3 Once or twice a week, or
4 Almost every day
5 Don’t know
143
168
169
173
146
1 In a classroom at school?
2 In a hallway or stairwell at school?
3 In a bathroom or locker room at school?
4 In a cafeteria or lunchroom at school?
5 Somewhere else inside the school
building? – Specify __________________
6 Outside on school grounds?
7 On a school bus?
(READ CATEGORIES 1-4.)
19c.
Still thinking about all of the times that you were
bullied, where did the bullying occur? Did it occur …
(READ CATEGORIES) Mark (X) all that apply
144
145
19d.
Page 8
Was a teacher or some other adult at school
notified about this bullying?
147
1 Yes
2 No
FORM SCS-1 (09/06/2012)
CHECK Item B
19e.
Is Box 4 in Question 19a marked “Yes”?
What were the injuries you suffered as a result of
being pushed, shoved, tripped, or spit on?
Mark (X) all that apply
20a.
160SCS 1 Yes - ASK 19e
2 No - SKIP to 20a
148
149
150
151
152
153
154
155
1 None
2 Bruises or swelling
3 Cuts, scratches, or scrapes
4 Black eye/bloody nose
5 Teeth chipped or knocked out
6 Broken bones/internal injuries
7 Knocked unconscious
8 Other - Specify _______________________
Now I have some questions about what students do
that could occur anywhere and that make you feel
bad or are hurtful to you. You may include events
you told me about already.
During this school year, has another student....
(Read each category a-g.)
a.
b.
Posted hurtful information about you on the
Internet, for example, on a social networking site
like MySpace, Facebook, Formspring, or
Twitter?
Purposely shared your private information,
photos, or videos on the Internet or mobile
phones in a hurtful way?
c.
Threatened or insulted you through email?
d.
Threatened or insulted you through instant
messaging or chat?
e.
Threatened or insulted you through text
messaging?
f.
Threatened or insulted you through online
gaming, for example, while playing XBOX, World
of Warcraft, or similar activities?
g.
Purposefully excluded you from online
communications?
CHECK Item 20a
20b.
161
No
1
2
183SCS 1
1
2
162
1
2
163
1
2
171
1
2
172
1
2
1 Yes - SKIP to 21a
2 No - ASK to 20b
165
1 Once or twice this school year
2 Once or twice a month
3 Once or twice a week, or
4 Almost every day
5 Don’t know
166
1 Yes
2 No
(READ CATEGORIES 1-4)
20c.
Was a teacher or some other adult at school notified
about this bullying online (or through text
messaging)?
2
170
Are all categories a-g marked “No” in Q20a
above?
You just indicated that someone had bullied you
online (or through text messaging) during this
school year. Thinking about all of the ways in which
you were bullied online (or through text
messaging), how often did all of those things
happen?
Yes
21a.
21b.
During this school year, has anyone called you an
insulting or bad name at school having to do with
your race, religion, ethnic background or national
origin, disability, gender, or sexual orientation? We
call these hate-related words.
065
1 Yes
2 No - SKIP to 22
Were any of the hate-related words related to ...
Yes
No
Don’t know
a.
Your race?
107SCS
1
2
3
b.
Your religion?
108SCS
1
2
3
c.
Your ethnic background or national origin (for
example, people of Hispanic origin)?
109SCS
1
2
3
d.
Any disability (by this I mean physical, mental,
or developmental disabilities) you may have?
110SCS
1
2
3
e.
Your gender?
111SCS
1
2
3
f.
Your sexual orientation?
112SCS
1
2
3
If “Yes,” SAY - (by this we mean homosexual,
bisexual, or heterosexual)
22.
During this school year, have you seen any
hate-related words or symbols written in school
classrooms, school bathrooms, school hallways, or
on the outside of your school building?
066
1 Yes
2 No
H. AVOIDANCE
23a.
During this school year, did you ever STAY AWAY
from any of the following places because you
thought someone might attack or harm you there?
(READ CATEGORIES.)
Yes
No
a.
For example, did you ever STAY AWAY from the
shortest route to school because you thought
someone might attack or harm you?
068
1
2
b.
The entrance into the school?
069
1
2
c.
Any hallways or stairs in school?
070
1
2
d.
Parts of the school cafeteria?
071
1
2
e.
Any school restrooms?
072
1
2
f.
Other places inside the school building?
073
1
2
g.
School parking lot?
074
1
2
h.
Other places on school grounds?
075
1
2
23a.1.
Page 10
During this school year, did you STAY AWAY from
any online activities because you thought someone
might be mean to you there?
184SCS 1 Yes
2 No
FORM SCS-1 (09/06/2012)
23b.
Did you AVOID any activities at your school because
you thought someone might attack or harm you?
076
1 Yes
2 No
23c.
Did you AVOID any classes because you thought
someone might attack or harm you?
077
1 Yes
2 No
23d.
Did you stay home from school because you
thought someone might attack or harm you in the
school building, on school property, on a school
bus, or going to or from school?
078
1 Yes
2 No
I. FEAR
24.
How often are you afraid that someone will attack or
harm you in the school building or on school
property?
079
1
2
3
4
Never
Almost never
Sometimes
Most of the time
080
1
2
3
4
Never
Almost never
Sometimes
Most of the time
081
1
2
3
4
Never
Almost never
Sometimes
Most of the time
(READ CATEGORIES.)
25.
How often are you afraid that someone will attack or
harm you on a school bus or on the way to and from
school?
(READ CATEGORIES)
26.
Besides the times you are in the school building, on
school property, on a school bus, or going to or from
school, how often are you afraid that someone will
attack or harm you?
(READ CATEGORIES)
J. WEAPONS
27.
In the next series of questions we are going to ask
you about weapons at your school. All your
responses are strictly confidential and will not be
shared with anyone.
Some people bring guns, knives, or objects that
can be used as weapons to school for protection.
During this school year, did YOU ever bring the
following to school or onto school grounds?
(READ CATEGORIES.)
a. A gun?
082
Yes
1
No
2
b. A knife brought as a weapon?
083
1
2
c. Some other weapon?
084
1
2
085
1 Yes
2 No - SKIP to 29
28a.
Do you know of any other students who have
brought a gun to your school during this school
year?
28b.
Have you actually seen another student with a gun at
school during this school year?
086
1 Yes
2 No
3 Don’t know
29.
During this school year, could you have gotten a
loaded gun without adult permission, either at school
or away from school?
113
1 Yes
2 No
K. GANGS
INTRO 4 -
30.
31.
Now, we'd like to know about gangs at your school. You may know these as street gangs, fighting gangs,
crews, or something else. Gangs may use common names, signs, symbols, or colors. For this survey, we
are interested in all gangs, whether or not they are involved in violent or illegal activity. Your responses
are confidential.
Are there any gangs at your school?
During this school year, how often have gangs been
involved in fights, attacks, or other violence at your
school?
058
1 Yes
2 No - SKIP to 34
3 Don't know
089
1
2
3
4
5
6
090
1 Yes
2 No
3 Don't know
(READ CATEGORIES 1-5)
32.
Have gangs been involved in the sale of drugs at
your school during this school year?
Never
Once or twice this school year
Once or twice a month
Once or twice a week, or
Almost every day
Don't know
L. STUDENT CHARACTERISTICS
34.
During this school year, across all subjects have you
gotten mostly -
116
(READ CATEGORIES 1-5)
33a.
During the last 4 weeks of school, did you skip any
classes? Again, we would like to remind you that all
your responses are strictly confidential and will not be
shared with anyone.
33b.
During the last 4 weeks of school, on how many days
did you skip at least one class?
35.
Thinking about the future, do you think you will ...
114
1
2
3
4
5
6
A's
B's
C's
D's
F's
School does not give grades/no alphabetic
grade equivalent
1 Yes
2 No - SKIP to 35
3 Don't know - SKIP to 35
115
(Number of days)
a. Attend school after high school, such as a
college or technical school? . . . . . . . . . .
117
Yes
1
No
2 -- END
b. Graduate from a 4-year college? . . . . . . . . . . .
118
1
2
Page 12
Don't know
3
3
FORM SCS-1 (09/06/2012)
Attachment 3
2013 SCS Item Description and Rationale
Attachment 3
2013 SCS Item Description and Rationale
2013 SCS ITEM DESCRIPTION AND RATIONALE
Background
The School Crime Supplement (SCS), a supplement to the annual National Crime Victimization Survey
(NCVS), is designed to obtain additional information about school-related victimizations so that
policymakers; academic researchers; practitioners at the federal, state, and local levels; and special
interest groups who are concerned with crime in schools can make informed decisions concerning policies
and programs. The Bureau of Justice Statistics, the National Center for Education Statistics, and the
Census Bureau jointly designed the survey questionnaire. The first SCS was administered in 1989, and
again in 1995, 1999, 2001, 2003, 2005, 2007, 2009, and 2011. To study the relationship between
victimization at school and the school environment, and to monitor changes in student experiences with
victimization, accurate information regarding its incidence must be collected. The SCS asks questions
related to students’ experiences with, and perceptions of crime and safety at school, including preventive
measures employed by schools; students’ participation in after school activities; students’ perception of
school rules and enforcement of these rules; the presence of weapons, drugs, alcohol, and gangs in school;
student bullying; hate-related incidents; and attitudinal questions relating to the fear of victimization at
school. These responses are linked to the NCVS survey instrument responses for a more complete
understanding of the individual student’s circumstances.
2013 School Crime Supplement
The 2013 SCS will be the 10th implementation of an occasional supplement to obtain specific
information about school-related victimization and disorder on a national level. The 2013 questionnaire is
identical to that used in 2011 with one minor change noted below. It consists of eight sections, as follows:
1. Screen questions asked to determine if the respondent is eligible for the SCS.
2. Environmental questions that obtain selected information on the type of school the student
attended in the past year, including whether the school was private or public; the grade levels
taught; student transportation to and from school; student involvement in extracurricular
activities; measures taken by the school to ensure student safety; classroom and school rule
enforcement; measures of student support; and the availability of drugs and alcohol in school.
3. Fighting, Bullying, and Hate Behavior questions related to students’ experiences with
physical fights, bullying, and hate-related words and hate-related graffiti at school.
4. Avoidance questions identify the effect of fear of crime on student behavior. The avoidance
questions were designed to determine if students stay away from school or particular places at
school, or avoid participating in extracurricular activities at their school for fear of being
attacked or harmed.
5. Fear questions pertain to how often a student feared an attack or being harmed.
6. Weapons questions pertain to whether weapons to determine if students brought weapons to
school for protection.
7. Gangs questions relate to the presence of organized gangs at school.
8. Student Characteristics ask questions about the respondent’s attendance, grades, and plans
regarding college (future orientation).
Below is a more detailed justification or rational for each section.
1
1. Screen Questions
Because the SCS survey is administered to a subset of individuals within the households participating in
the NCVS survey, it is necessary to ascertain the eligibility of the individuals being interviewed. The SCS
questionnaire is administered only to individuals ages 12–18 who were in primary or secondary education
programs leading to a high school diploma (elementary through high school) sometime during the 6
months prior to the interview. Those who dropped out of school, who have been expelled or suspended
from school, or who were temporarily absent from school for any other reason, such as illness or vacation,
are eligible as long as they were attending school at any time during the 6 months prior to the month of
the interview. Home-schooled students are not included in the survey past the screening questions since
many of the questions in the SCS are not relevant to their situation.
2. Environmental Questions
This section collects data on the school that the student attends and collects general information about the
student’s awareness and experiences in that environment. These data on programs and experiences can be
analyzed in relation to increases or decreases in incidences of school crime and bullying—information
which is collected elsewhere on the questionnaire. These correlations can be important in helping
educators and policymakers identify factors in their schools which may be precursors to increases in
crime and bullying, and may also help determine which programs and environmental factors can support
efforts to reduce incidences of school crime. Below is a summary of the content foci for each
environmental question and corresponding rational.
Question
number/s
6-12
Content
•
•
•
•
13
•
14a-b
•
Is school public or private,
religiously affiliated
Grade levels in the school
Is the school in the
individual’s neighborhood
or is travel required
Are students required to stay
on school grounds during
lunch
Students’ participation in
school activities
Methods or strategies
schools use to monitor
school environment to
prevent crime
Rationale
School characteristics of interest 1,2,3
Increased involvement may mean more
opportunities to be exposed to crime and bullying
outside the classroom or it may be a factor in
reducing incidents of crime and bullying since high
levels of involvement within a school are correlated
with increased student connectedness to the
academic environment.4
Monitoring strategies may affect crime and bullying
by making students reluctant to engage in
inappropriate activities for fear of being caught.
Conversely, students’ awareness of the strategies
1
Van Dorn, R. A. (2004). Correlates of violent and nonviolent victimization in a sample of public high school students. Violence & Victims,
19(3), 303-320.
2
Lab, S. P., & Whitehead, J. T. (1992). School Environment & School Crime: Causes & Consequences; Summary Report.
3
Kuck, D., & Popp, A. (2005). Characteristics of students and schools as predictors of being a victim of bullying: An Opportunity Theory
Analysis. Conference Papers -- American Society of Criminology, N.PAG.
4
DeVoe, J. (2009). Social bonding and school victimization: The ties that bind. Conference Papers. American Society of Criminology, 1.
2
Question
number/s
Content
15 a-b
•
16a, 16 e-f
•
16b-d
•
17a
Description of the school
environment, especially the
availability of drugs, alcohol,
and tobacco on school grounds
General level of disruption
in the individual’s classes in
the past year
Awareness of school rules
and enforcement
Relationships within school
Rationale
also can make them feel more secure and therefore
increase school connectedness; as noted above,
increased attachment within the school population
can reduce the overall risk of crime and bullying. 5
Helps define the environment in which crime and
bullying incidents occur.6,7
Helps determine the general level of disruption and
the general level of crime students are exposed to in
their school and home neighborhoods. 8,9
The presence of caring relationships has been found
to be a key protective factor in multiple surveys of
student experiences. Question 16c is taken directly
from the California Healthy Kids Survey—one of
the most widely quoted surveys measuring student
protective factors. The content of Question 16c is
based on the work of social bonding theorists who
suggest that bonding is a potential mediator of
problem behavior. Specifically, when youth are
bonded or positively associated with their school or
other positive institutions, they are more likely to
engage in prosocial behaviors, whereas one would
expect poorly bonded students to be frequent
victims of crime, bullying, and other negative
behaviors. Including these questions on the SCS
allows direct comparison of these factors with a
wide range of potential negative school experiences
such as crime, bullying, and drug availability. 10
The availability of illegal substances is correlated
with both the general level of crime in a school and
the likelihood that students using these substances
may be involved in crimes. 11
5
Blosnich, J., & Bossarte, R. (2011). Low-level violence in schools: Is there an association between school safety measures and peer
victimization? The Journal Of School Health, 81(2), 107-113.
6
Mayer, M. J., & Leone, P. E. (1999). A structural analysis of school violence and disruption: Implications for creating safer schools. Education
& Treatment Of Children, 22(3), 333.
7
Collins, J. J., Messerschmidt, P. P., Ringwalt, C. C., & Research Triangle, I. (1992). Relationship Between School Disruption & School Social
Control Activities: Summary Of Findings,
8
Smith, B. E., & Elstein, S. G. (1993). Effective ways to reduce school victimization: practical and legal concerns. Children's Legal Rights
Journal, 14(1-2), 22-38.
9
Clay-Warner, J., Bunch, J., & James, K. (2009). Procedural Justice and School Crime. Conference Papers -- American Society of Criminology,
1.
10
DeVoe, J. (2009). Pg. 2
11
Elliott, E., & Rayne, K. (2008). Victimization rates and drug use among high school and college students. Conference Papers -- American
Society of Criminology, 1.
3
3. Fighting, Bullying, and Hate Behaviors
This section focuses on the type and extent of crime and bullying students are exposed to in their schools.
Using weighting factors provided by the U.S. Census Bureau, these data can be used to estimate the
extent of fighting, bullying, and hate crime in schools nationally. This information is crucial to educators
and policymakers in prioritizing funding and program development for school systems across the country.
Changes in overall levels of crime in the schools can be used to evaluate the effects of national programs,
and individual school districts can compare their rates to national averages to assess the success of local
initiatives. Although similar crime data are collected from other venues such as crime reports, and surveys
of adults and schools, the SCS gathers direct information on students’ experiences in schools. This can be
used in conjunction with the other data sources to indicate gaps in reporting, to compare school crime to
crime outside the school, and can be used by researchers to explore the differences between the
perceptions of adolescents and adults with regard to crime and security. Below is a summary of the
content foci for questions about fighting, bullying, and hate behaviors and corresponding rationale.
Question
number/s
18a-b
Content
•
Individual’s involvement in fights
19a.a-a.g
•
Types of bullying experienced
19b
•
Frequency of bullying experienced
19c
•
Locations in and around the school in
which bullying occurred
19d
The extent to which bullying was reported
to an adult at school and that there are
secure paths for reporting help deter
bullying
Rationale
Determine exposure to physical violence
as separate from bullying. 12
An array of questions are required as
students’ concepts of what constitutes
‘bullying’ has been found to vary from
technical definitions used by
policymakers and researchers.
Random acts of bullying may occur in
any environment with adolescents, but
more frequent occurrences may indicate
things that schools need to address. 13
Noting where bullying occurs is
important in determining trends and to
develop strategies to monitor or prevent
the incidences of bullying in those
environments. 14
Research indicates that significant
numbers of bullying incidents go
unreported. Collecting this information
in a confidential interview format can
shed light on estimates of bullying in
U.S. schools. 15,16
Additionally, collecting this information
with reports from the same students on
school attachment factors gathered in
section 2 can be used to analyze what
12
Noe, K., & Petras, H. (2009). Peer victimization in middle and high school: An application of latent class analysis. Conference Papers -American Society of Criminology, 1.
13
Elliott, E., & Rayne, K. ,pg. 3
14
Ringwalt, C. C., Messerschmidt, P. P., Graham, L. L., Collins, J. J., & Research Triangle, I. (1992). Youths' Victimization Experiences, Fear of
Attack Or Harm, & School Avoidance Behaviors: Summary Of Findings,
15
Watkins, A. M., & Maume, M. O. (2011). School victims and crime reporting. Youth Violence & Juvenile Justice, 9(4), 333-351.
16
Watkins, A., & Maume, M. (2007). We Don't Need No Notification: The Underreporting of Victimization by Students. Conference Papers -American Society of Criminology, 1.
4
Question
number/s
Content
•
19e
20 a.a-a.g and 20 •
b-c
(Question added
in 2007)
21a-b and 22
•
Types of injuries that resulted from
physical bullying
Types of cyber-bullying experienced
The experience, content, and location
of experiencing hate-related speech
directed at the individual
Rationale
factors may increase the likelihood of
reporting bullying.
May have implications for analyzing
when bullying is or is not reported.
Cyber-bullying is not generally
experienced on school grounds, but
often involves school peers. The
question is asked separately from those
in 19 about in-person bullying. The
format of the question and the follow-up
questions 20b (frequency of cyberbullying) and 20c (notification of an
adult) follow the format and rationale of
the questions on in-person bullying. 17
Hate-related speech is not reported by
adolescents as often as bullying because
students are often embarrassed about the
message conveyed or not sure where it
falls with relation to various categories
of crime/bullying that should be
reported. Collecting specific information
on use of hate-related words in this
anonymous survey will provide school
personnel and policymakers information
about the extent and seriousness of the
crime. 18
4. Avoidance
This section asks about places and activities students avoid because of the likelihood of bullying, cyberbullying, and physical attacks. Avoidance, where warranted, reduces the actual number of such incidents
without reducing the risk that they will occur. Students who avoid going to classes are negatively affected
not only by the experience of crime, but also by the loss of instructional time 19. Below is a summary of
the content foci for questions about avoidance and corresponding rationale.
Question
number/s
23a.a-a.h
Content
•
Areas of the school avoided because of
risk of attack or harm
23a.1
•
Avoidance of online activities because
of mean behavior
Rationale
This information about avoidance can be
used to (a) estimate overall actual crime
in schools in addition to that experienced
by the absence of direct reporting from
the individuals interviewed, and (b)
17
Bagwell, K. (2011). Students use cellphones more than computers to cyberbully. Education Daily, 44(189), 2.
Van Dorn, R. (2002). Unrecognized warning signs. Education Week, 22(11), 41.
19
Barrett, Kimberly L.; Jennings, Wesley G.; Lynch, Michael J. (2012). The relationship between youth fear and avoidance of crime in school
and academic experiences. Journal of School Violence. Vol. 11 (1), 1-20.
18
5
Question
number/s
23b
23c
23d
Content
•
•
•
Avoidance of specific school activities
Avoidance of specific classes
Extent to which students avoid going
to school because of risk of attack or
harm in, around, or traveling to and
from school
Rationale
analyze the impact it has on student
behavior and academic performance. 20,
21,22,23,24,25
5. Fear
This section adds to the information in Section 4, Avoidance, by asking how often students fear attack or
harm. Students may not be able to avoid school activities even though they may fear attending 26. Fear,
like avoidance, harms adolescents beyond the harm attributed to the actual crimes experienced27. Below
is a summary of the content foci for questions about fear and corresponding rationale. 28
Question
number/s
24
Content
•
25
•
26
•
How often students are afraid of attack
or harm in the school building or on
school property
How often students are afraid of attack
or harm on the bus or on the way to
and from school
How often students are afraid of attack
or harm at other times besides in or
going to school
Rationale
Fear results in stress, which negatively
affects academic performance, can lead
to inappropriate psycho-social outcomes
such as acting out, and can impact future
orientation such as plans to complete
school. 29,30
6. Weapons
This section asks about experiences with weapons in school. Bringing weapons to school for personal
protection is another indicator of the extent of the perceived level of violence in the school. Although a
student may not have been directly threatened or harmed by a weapon, knowing that weapons are on
20
Pearson, F. S., Toby, J. J., & Rutgers, U. (1992). Perceived & Actual Risks Or School-Related Victimization: Final Activities Report,
Randa, R. (2007). The impact of incivilities on fear and routine activities in high schools. Conference Papers -- American Society Of
Criminology, 1.
22
Lab, S. P., & Whitehead, J. T. (1994). Avoidance behavior as a response to in-school victimization. Journal of Security Administration, 17(2),
32-45.
23
Ringwalt, C. C., Messerschmidt, P. P., Graham, L. L., Collins, J. J., pg. 5
24
Randa, R., Drayer, A., & Lytle, D. (2008). Routine Activities of School Children: How Fear and Disorder Influence Avoidance of Specific
Places. Conference Papers -- American Society Of Criminology, 1.
25
Hutzell, K. (2009). The Impact of Bullying Behaviors on School Avoidance. Conference Papers -- American Society of Criminology, 1.
26
Jenkins, Patricia H. (1997). School delinquency and the school social bond. Journal of Research in Crime & Delinquency. Vol. 34 (3), 337367.
27
U.S. Department of Education. (2006). Indicators of School Crime & Safety: 2006.
28
Barrett, K. L., Jennings, W. G., & Lynch, M. J., pg1-20.
29
Ades, L. (2007). Horror in the Halls: Examining Adolescent Fear, Avoidance, and Academic Difficulty. Conference Papers -- American
Sociological Association, 1.
30
Randa, R., Drayer, A., & Lytle, D., pg. 6.
21
6
campus can also lead to fear and avoidance of school.31 Below is a summary of the content foci for
questions about weapons and corresponding rationale.
Question
number/s
27a-c
Content
•
28 a-b
•
•
29
If interviewee has brought a gun, knife
or other weapon to school.
If interviewee knows of, or has seen,
another student with a weapon in
school
If interviewee can get a weapon
without adult permission either in
school or outside.
Rationale
Potential for violence escalates when
students carry weapons in school.
Negative academic and psycho-social
outcomes are correlated with fear of
weapons on campus. 32,33,34
7. Gangs
This part of the survey examines the extent of gang activity in schools. Gangs are known to be an
indicator of increased crime in schools and require separate types of interventions to address from specific
incidences of crime and bullying. Below is a summary of the content foci for questions about gangs and
corresponding rationale.
Question
number/s
30
31
Content
•
•
32
•
Gangs in the student’s school
Frequency of gang involvement in
fights, attacks, or other violence in the
school
Extent of gang involvement in drugs in
the school
Rationale
Provides an opportunity to compare
adolescents’ perceptions of gang activity
from the official reports from police, and
from school and adult surveys. 35,36
8. Student Characteristics
These questions focus specifically on student academic characteristics. Information about demographic
characteristics is included in the NCVS survey. Below is a summary of the content foci for questions
about student characteristics and corresponding rationale.
31
Mooij, Ton; Smeets, Ed; de Wit, Wouter. (2011). multi-level aspects of social cohesion of secondary schools and pupils' feelings of safety.
British Journal of Educational Psychology. Vol. 81(3)3.
32
Cao, L., Zhang, Y., & He, N. (2008). Carrying weapons to school for protection: An analysis of the 2001 school crime supplement data.
Journal Of Criminal Justice, 36(2), 154-164.
33
Noonan, M. (2005). Guns in schools: results from the 2003 School Crime Supplement. Conference Papers -- American Society of Criminology.
34
Hong, Jun; Eamon, Mary. (2012). Students' perceptions of unsafe schools: An ecological systems analysis. Journal of Child & Family
Studies. Vol. 21(3), p428-438.
35
Scott, L., & Ruddy, S. (2003). How Students Identify Gangs at School: An Analysis of Multiple Gang Identification Questions in the 1995
SCS/NCVS. Conference Papers -- American Association for Public Opinion Research.
36
Ralph, J. H., Colopy, K. W., McRae, C. C., Daniel, B. B., & National Center for Education, S. (1995). Gangs and victimization at school.
Gangs & Victimization At School.
7
Question
number/s
33
34
Content
•
•
35
•
Frequency of skipping classes
Overall grades the student received
over the past school year
Postsecondary school plans (future
orientation)
Rationale
These are indicators of academic
behavior and planning, which may be
analyzed with regard to the impact of
student experiences with school violence
and bullying. 37,38,39,40
37
Wynne, S. L., & Hee-Jong, J. (2011). Predictors of school victimization: Individual, familial, and school factors. Crime & Delinquency, 57(3),
458-488.
38
Wynne, S., & Joo, H. (2007). Predicting School Victimization: A Multi-level Approach. Conference Papers -- American Society of
Criminology, 1.
39
Kuck, D., & Popp, A., pg. 2
40
DeVoe, J., pg. 2
8
Attachment 4
Census Bureau introductory letter for new households (NCVS-572(L))
Attachment 5
Census Bureau introductory letter for reinterview households (NCVS-573(L))
Attachment 6
SCS informational brochure for parents (in English)
The School Crime Supplement (SCS) is a national survey that asks students in
grades 6 through 12 about experiences they had in school.
What is the purpose of this survey?
The purpose of this survey is to collect
information about school-related victimizations
on a national level. This information will assist
policymakers as well as academic researchers
and practitioners at the federal, state, and local
levels in making informed decisions concerning
crime in schools.
Why is my child being asked to
complete this survey?
Your household was one of more than 40,000
households selected to participate in the National
Crime Victimization Survey (NCVS). We are
asking all students in grades 6 through 12 in
those households to complete the 2011 SCS. We
are collecting data about crime in schools and
how it affects students.
Who sponsors this survey?
The U.S. Census Bureau is conducting the SCS
for the National Center for Education Statistics
(NCES) in partnership with the Bureau of Justice
Statistics (BJS), the sponsor of the NCVS.
How often is this survey conducted?
The SCS is conducted every other year along
with the NCVS. Your child is being asked to
participate in the 2011 SCS.
NCES 2010-359 parents ssocs br.indd 1
What questions are on the survey
for my child?
We will ask your child questions about his or her
school environment, including
•
•
•
•
•
•
Perception of school practices to prevent
school-related crimes;
Perceptions of rules and equality at school;
The availability of drugs, alcohol, and
weapons at school;
The presence of gangs at school;
Whether he/she has been victimized at
school or bullied; and
Participation in extra-curricular activities.
What is the benefit of my child
answering the survey?
Your child’s answers provide valuable
information that contributes towards making
schools safer. This information will be used by
others to make informed decisions about how to
best help prevent and reduce crime in schools.
Will anyone find out what my child’s
answers are?
No, your child’s answers to the survey are
completely confidential. Information about
specific individuals will not be revealed and
the SCS findings are released ONLY in the form
of statistical summaries. Names will never be
associated with answers. All information that
can identify individuals will be held strictly
confidential by the Census Bureau and the BJS
according to the provisions stated in Title 13,
U.S. Code, Section 9 and Title 42, U.S. Code,
Sections 3789g and 3735 (formerly Section
3771). Only Census Bureau employees sworn
to preserve this confidentiality may see the
completed questionnaires. The respondents are
assured confidentiality and informed that their
participation is voluntary in a letter from the
Director of the Census Bureau.
Does my child have to complete
this survey?
This survey is voluntary and there are no
penalties for not participating, but we hope that
your child will respond.
Who uses the information from
this survey?
The BJS and the NCES analyze and use the
statistical data produced from the SCS. The SCS
is an important data source for the Indicators
of School Crime and Safety report released
annually by the NCES. Other SCS data users
include legislators; policymakers; academic
researchers; practitioners at the federal, state,
and local government levels; as well as special
interest groups who are concerned with crimes
committed at school.
7/29/10 11:41 AM
Some findings
Publications
Some findings from the 2007 SCS
include
The NCES publishes a wide variety of special
reports on crime in schools, including the
Crime, Violence, Discipline, and Safety in U.S.
Public Schools and Indicators of School Crime
and Safety. To learn more about these reports
or the SCS, please visit
http://nces.ed.gov/programs/crime.
•
•
•
•
•
•
•
About 31.7 percent of all students
ages 12-18 reported that they were
bullied at school.
Cyber-bullying, which could have
occurred anywhere, on or off
school property, was reported by
3.7 percent of all students ages
12-18.
About 36.1 percent of students
ages 12-18 who were bullied at
school and 30.0 percent of students
who were cyber-bullied anywhere
notified a teacher or other adult at
school about the event.
About 4.3 percent of students ages
12-18 reported that they were
victims of any crime at school.
Three percent of both males and
females ages 12-18 reported being
victims of theft at school.
There was no statistical difference
detected between the percentage
of public and private school
students ages 12-18 who reported
being bullied at school.
Among students ages 12-18 who
had been bullied, 62.6 percent
reported that they were bullied
once or twice in the school year,
20.7 percent reported bullying
once or twice a month, 10.1
percent reported bullying once
or twice a week, and 6.6 percent
reported bullying almost every day.
Useful Information
•
National Center for Victims of Crime
1-800-FYI-CALL (1-800-394-2255)
1-800-211-7996 (TTY)
•
Child Help USA National Child
Abuse Hotline
1-800-4-A-CHILD (1-800-422-4453)
Child’s
Your Child’s
Experiences
at School
The School Crime
Supplement (SCS)
to the National
Crime Victimization
Survey for Students
in Grades 6
Through 12
National Center for Education Statistics
Institute of Education Sciences
1990 K Street NW
Washington, DC 20006-5651
nces.ed.gov
202-502-7300
Coming soon:
Your child will be contacted to complete
the survey between January and June 2011.
NCES 2010-359
U.S. DEPARTMENT OF EDUCATION
NCES 2010-359 parents ssocs br.indd 2
7/29/10 11:41 AM
NCES 2010-359
Attachment 7
SCS informational brochure for parents (in Spanish)
El Suplemento de Delitos en la Escuela (SCS) es una encuesta nacional que les pregunta a
estudiantes de 6º a 12º grados escolares acerca de las experiencias que tuvieron en la escuela.
¿Cuál es el propósito de esta encuesta?
El propósito de esta encuesta es recopilar
información sobre acoso o persecución en las escuelas a
nivel nacional. Esta información asistirá a los diseñadores
de políticas, asi como a los investigadores académicos
y practicantes a nivel federal, estatal y local a tomar
decisiones informadas con respecto a delitos
en las escuelas.
¿Por qué le pidieron a mi hijo(a) que
completara esta encuesta?
Su hogar fue uno de los más de 40,000 hogares
seleccionados para participar en la Encuesta Nacional de
Víctimas de Delitos (NCVS). Les pedimos a todos los
estudiantes de grados 6 a 12 que viven en estos hogares
que completen la SCS del 2011. Estamos recopilando
datos acerca de delitos en las escuelas y como afectan a los
estudiantes.
¿Quién es el patrocinador de esta
encuesta?
La Oficina del Censo de EE.UU. está llevando a cabo
la SCS para el Centro National para Estadísticas de
la Educación (NCES) en conjunto con la Oficina de
Estadísticas Judiciales (BJS), que es el patrocinador de
la NCVS.
¿Con qué frecuencia llevan a cabo esta
encuesta?
La SCS se lleva a cabo cada 2 años, a la par con la NCVS.
Pedimos que su hijo(a) participe en la SCS del 2011.
¿Qué preguntas de la encuesta ha de
contestar mi hijo(a)?
Le preguntaremos a su hijo(a) sobre el ambiente de su
escuela, incluyendo
• Percepción de las prácticas de la escuela para evitar
delitos en la escuela;
• Percepciones de las reglas e igualdad en la escuela;
• La disponibilidad de drogas, alcohol y armas en la
escuela;
• La presencia de pandillas (gangs) en la escuela;
• Si él o ella ha sufrido intimidación o ha sido
perseguido(a) (bullied) en la escuela; y
• Participación en actividades extracurriculares.
¿Cuál es el beneficio para mi hijo(a) si
contesta a la encuesta?
Las respuestas de su hijo(a) proporcionarán información
muy valiosa que contribuirá a una mayor seguridad en la
escuela. Esta información la usarán otras personas para
tomar decisiones informadas para asistir a prevenir y
reducir los delitos en las escuelas.
¿Alguien se enterará de las respuestas
de mi hijo(a)?
No, las respuestas de su hijo(a) en esta encuesta son
completamente confidenciales. Información específica
sobre individuos no será divulgada y los resultados de
la SCS serán publicados SOLO en forma de resúmenes
estadísticos. Los nombres nunca serán asociados con las
respuestas. Toda la información que pudiera identificar
a un individuo se mantendrá estrictamente confidencial
por la Oficina del Censo de EE.UU. y BJS, de acuerdo
a las provisiones fijadas en el Título 13, Código de los
Estados Unidos, Sección 9 y en el Título 42, Código de
los Estados Unidos, secciones 3789g y 3735 (previamente
sección 3771). Solamente los empleados de la Oficina
del Censo de EE.UU., quienes están bajo juramento
de conservar la confidencialidad, pueden ver los
cuestionarios completos. El Director de la Oficina del
Censo de EE.UU., por medio de una carta, asegura a los
respondientes la confidencialidad y les informa que su
participación en la encuesta es voluntaria.
¿Tiene que completar la encuesta mi
hijo(a)?
Esta encuesta es voluntaria y no hay ninguna sanción por
no participar, pero esperamos que su hijo(a) responda a las
preguntas.
¿Quién usa la información obtenida por
medio de esta encuesta?
BJS y NCES analizan y usan los datos estadísticos
producidos por el SCS. El SCS es una fuente importante
de datos para el informe Indicadores de Delitos y Seguridad
en las Escuelas que se publica anualmente por NCES.
Otros usuarios de la información del SCS son legisladores;
diseñadores de políticas; investigadores académicos;
practicantes a nivel del gobierno federal, estatal y local; asi
como grupos de intereses especiales que están preocupados
por los delitos cometidos en las escuelas.
Algunos resultados
Algunos resultados de la SCS del 2007
incluyen
• Alrededor del 31.7 por ciento de todos
los estudiantes de 12 a 18 años de edad
reportaron que fueron intimidados
(bullied) en la escuela.
• La ciber-intimidación, que pudo haber
ocurrido en cualquier lugar, sobre la
propiedad de la escuela o fuera de ella,
fue reportada por un 3.7 por ciento de
todos los estudiantes de 12 a 18 años de
edad.
• Alrededor del 36.1 por ciento de
estudiantes de 12 a 18 años de edad que
fueron intimidados en la escuela y 30.0
por ciento de estudiantes que fueron
víctimas de la ciber-intimidación en
cualquier lugar reportaron el caso a un
maestro o a otro adulto de la escuela.
• Alrededor del 4.3 por ciento de
estudiantes de 12 a 18 años de edad
reportaron que fueron víctimas de algún
delito en la escuela.
• Tres por ciento de tanto niños como
niñas de 12 a 18 años de edad reportaron
haber sido víctimas de robo en la escuela.
• Estadísticamente, no se detectó ninguna
diferencia en el porcentaje de estudiantes
de 12 a 18 años de edad de escuelas
públicas o privadas que reportaron ser
víctimas de intimidación en la escuela.
• Entre estudiantes de 12 a 18 años de
edad que habían sido intimidados, el
62.6 por ciento reportaron que estas
intimidaciones habían ocurrido una o dos
veces en el curso escolar, 20.7 por ciento
reportaron que habían ocurrido una o dos
veces al mes, 10.1 por ciento reportaron
que habían ocurrido una o dos veces por
semana, y el 6.6 por ciento reportaron
que habían ocurrido casi diario.
Publicaciones
NCES publica una amplia variedad de informes
especiales sobre delitos en las escuelas, incluyendo
Delitos, Violencia, Disciplina y Seguridad en las Escuelas
Públicas en los Estados Unidos y Indicadores de Delitos y
Seguridad en las Escuelas. Para conocer más acerca de
estos informes o sobre el SCS, sírvase visitar:
http://nces.ed.gov/programs/crime.
Información Útil
•
National Center for Victims of Crime
(Centro Nacional para Víctimas de Delitos)
1-800-FYI-CALL (1-800-394-2255)
1-800-211-7996 (TTY)
Child’s
Las Experiencias
de su Hijo(a)
en la Escuela
Suplemento de
Delitos en la Escuela
(SCS) de la Encuesta
Nacional de
Víctimas de Delitos
para estudiantes
de 6º a 12º grados
escolares
National Center for Education Statistics
(Centro Nacional para Estadísticas de la Educación)
Institute of Education Sciences
(Instituto de Ciencias de Educación)
1990 K Street NW
Washington, DC 20006-5651
nces.ed.gov
202-502-7300
Próximamente:
Nos comunicaremos con su hijo(a) entre
enero y junio del 2011 para completar la
encuesta.
NCES 2011-308
U.S. DEPARTMENT OF EDUCATION
NCES 2010-359
Attachment 8
SCS informational brochure for students (in English)
Publications
The NCES publishes a wide variety of special
reports on crime in schools, including the Crime,
Violence, Discipline, and Safety in U.S. Public
Schools and Indicators of School Crime and Safety.
To learn more about these reports or the SCS,
please visit http://nces.ed.gov/programs/crime.
Useful Information
•
•
National Center for Victims of Crime
1-800-FYI-CALL (1-800-394-2255)
1-800-211-7996 (TTY)
Child Help USA
National Child Abuse Hotline 1-800-4-A-CHILD
(1-800-422-4453)
The School Crime Supplement
(SCS) to the National Crime
Victimization Survey for
Students in Grades 6
Through 12
NCES 2010-344
U.S. DEPARTMENT OF EDUCATION
NCES 2010-344 ssocs br.indd 1
7/29/10 11:09 AM
The School Crime Supplement (SCS) is a national survey that asks
students in grades 6 through 12 about experiences they had in school.
Why are my
answers to the
survey important?
Do I have to
take the survey?
The survey is voluntary and
there are no penalties for not
participating, but we hope
that you respond.
The survey helps school administrators
and others interested in school crime
make decisions about school safety.
What will the
survey ask me?
We will ask
you about
fighting,
bullying,
cyber-bullying,
weapons, and
drugs and
gangs at your
school,
among other
things.
Will anyone find out
what my answers are?
No, your answers
to the survey are
completely
confidential.
Your name will
never be
associated with
your answers.
Why am I being asked to
complete this survey?
Your household was one of more than 40,000
households selected to participate in the
National Crime Victimization Survey. We're
asking all students in grades 6 through 12 in
those households to complete the School Crime
Supplement. We are collecting data about crime
in schools and how it affects students.
Stay tuned!
You will be contacted to complete the survey between January and June 2011.
NCES 2010-344 ssocs br.indd 2
7/29/10 11:09 AM
Attachment 9
SCS informational brochure for students (in Spanish)
Publicaciones
NCES publica una amplia variedad de informes
especiales sobre delitos en las escuelas,
incluyendo Delitos, Violencia, Disciplina y
Seguridad en las Escuelas Públicas en los
Estados Unidos y Indicadores de Delitos y
Seguridad en las Escuelas. Para conocer más
acerca de estos informes o sobre el SCS, sírvase
visitar: http://nces.ed.gov/programs/crime.
Información Útil
• National Center for Victims of Crime
(Centro Nacional para Víctimas de Delitos)
1-800-FYI-CALL (1-800-394-2255)
1-800-211-7996 (TTY)
Cuéntenos
Acerca
sus
Experiencias
en la Escuela
de
Suplemento de Delitos en la Escuela
(SCS) de la Encuesta Nacional de
Víctimas de Delitos para estudiantes
de 6º a 12º grados escolares
National Center for Education Statistics
(Centro Nacional para Estadísticas de la Educación)
Institute of Education Sciences
(Instituto de Ciencias de Educación)
NCES 2011-309
U.S. DEPARTMENT OF EDUCATION
El Suplemento de Delitos en la Escuela (SCS) es una encuesta nacional
que les pregunta a estudiantes de 6° a 12° grados escolares acerca
de las experiencias que tuvieron en la escuela.
¿Por qué son
importantes mis
respuestas para la
encuesta?
¿Tengo que
participar en
esta encuesta?
La encuesta ayuda a los administradores de
las escuelas y otras personas interesadas en
el delito escolar a tomar decisiones acerca de
la seguridad en las escuelas.
La encuesta es voluntaria y no
hay ninguna sanción por no
participar, pero esperamos que
usted responda.
¿Qué preguntas
me harán en esta
encuesta?
Le vamos a
preguntar sobre
las peleas, la
intimidación
(bullying),
la ciberintimidación,
las armas, y
las drogas y
las pandillas
(gangs) en su
escuela, entre
otras cosas.
¿Alguien se enterará
de mis respuestas?
No, sus
respuestas a la
encuesta son
completmente
confidenciales.
Su nombre nunca
se asociará a sus
respuestas.
¿Por qué me pidieron que
complete esta encuesta?
Su hogar fue uno de los más de 40,000 hogares
seleccionados para participar en la Encuesta
Nacional de Víctimas de Delitos (NCVS). Les
pedimos a todos los estudiantes de grados 6º a
12º que viven en estos hogares que completen
el Suplemento de Delitos en la Escuela (SCS).
Estamos recopilando datos sobre los delitos en las
escuelas y como afectan a los estudiantes.
¡Manténganse en contacto!
Nos comunicaremos con usted entre enero y junio del 2011 para completar la encuesta.
Attachment 10
2011 SCS Nonresponse bias analysis report
April 25, 2012
MEMORANDUM FOR
Kathryn A. Chandler
Director, Sample Surveys Studies Program
National Center for Education Statistics
Through:
Enrique Lamas
Acting Chief, Demographic Surveys Division
U.S. Census Bureau
From:
Ruth Ann Killion
Chief, Demographic Statistical Methods Division
U.S. Census Bureau
Subject:
National Crime Victimization Survey: Evaluating Nonresponse
Bias in the 2011 School Crime Supplement
Attached is a copy of the report “Evaluating Nonresponse Bias in the 2011 School Crime
Supplement to the National Crime Victimization Survey”.
cc:
W. Sabol
M. Planty
J. Truman
L. Bynum
M. Wilson
D. Watt
C. Seamands
S. Bittner
(BJS)
(DSD)
P. Flanagan
S. Ash
L. Longsine
J. Burcham
(DSMD)
National Crime Victimization Survey
Demographic Statistical Methods Division
U.S. Census Bureau
Evaluating Nonresponse Bias in the 2011
School Crime Supplement to the
National Crime Victimization Survey
Joseph Burcham
April 12, 2012
Evaluating Nonresponse Bias in the 2011 School Crime Supplement
Table of Contents
1.
Executive Summary ............................................................................................................. 3
2.
Introduction .......................................................................................................................... 3
3.
Overview of 2011 SCS ........................................................................................................ 4
4.
Methods................................................................................................................................ 5
5.
Overall Response Rates ....................................................................................................... 8
6.
Obtaining Values of Variables for Person Non-respondents ............................................... 9
7.
Person Nonresponse Estimates .......................................................................................... 10
8.
Item Nonresponse Estimates .............................................................................................. 20
9.
Recommendations .............................................................................................................. 21
10.
Limitations ......................................................................................................................... 21
11.
Who to Contact with Questions ......................................................................................... 21
12.
Miscellaneous .................................................................................................................... 22
13.
References .......................................................................................................................... 22
Tables
Table 1: Overall Unit Response Rates ............................................................................................ 8
Table 2: Sample Counts for January – June 2011........................................................................... 9
Table 3: Obtaining Values of Variables for SCS Person Non-interviews ...................................... 9
Table 4: Obtaining Values of Variables for NCVS Person (Age 12-18) Non-interviews .............. 9
Table 5: Person Response Rates for NCVS Persons .................................................................... 11
Table 6: Person Response Rates for SCS Persons ........................................................................ 12
Table 7: Person Respondent and Non-respondent Distributions for NCVS Persons ................... 14
Table 8: Person Respondent and Non-respondent Distributions for SCS Persons ....................... 15
Table 9: Nonresponse Bias Estimates for NCVS Persons ............................................................ 17
Table 10: Nonresponse Bias Estimates for SCS Persons.............................................................. 18
Table 11: Item Response Rates ..................................................................................................... 20
2
1.
Executive Summary
This report presents results of our analysis of various nonresponse estimates computed for the
2011 School Crime Supplement (SCS) which was a supplement to the National Crime
Victimization Survey (NCVS). In addition to overall nonresponse rates, we computed response
rates, respondent and non-respondent distribution estimates, and nonresponse bias estimates for
various subgroups. Persons age 12-18 made up the universe for most of the estimates presented
here.
2.
•
The overall person response rate for the SCS was 55.0 percent. The NCVS household
response rate in January to June 2011 was 90.8 percent. The NCVS person response rate
for persons age 12-18 was 70.5 percent and the SCS person response rate was 85.9
percent.
•
Person-Level Nonresponse - High nonresponse bias estimates were observed for several
subgroups. However, due to the small SCS sample size and, therefore, small subgroup
sizes, the high numbers may be due to fluctuations among the subgroups instead of a real
nonresponse problem. The most concerning results are for the Hispanic subgroup, which
displayed a large amount of nonresponse bias.
•
Item Nonresponse - Important questions have 100 percent or nearly 100 percent
response so item nonresponse is not a problem for this survey.
•
Because of the strong indicators of nonresponse bias for Hispanic origin, we recommend
that Hispanic origin be considered as one of the nonresponse adjustment cells in the
future.
Introduction
This document presents results from our evaluation of nonresponse bias in the 2011 SCS. We
conducted this study because we expected the overall response rate for 2011 SCS to be below 80
percent. The Office of Management and Budget (OMB) provides guidelines for conducting a
nonresponse bias study when the expected unit response rate of a survey is below 80 percent.
See the guidelines in [1].
The purpose of this study is to compute overall response rates, identify the different
subgroups where nonresponse is occurring, and also to get an indication of the magnitude
of nonresponse bias that exists in the 2011 SCS. See [2] for more background on the
nonresponse bias plan.
3
3.
Overview of 2011 SCS
The 2011 SCS was co-designed by the National Center for Education Statistics (NCES) and the
Bureau of Justice Statistics (BJS). Its purpose is to produce national level estimates of schoolrelated victimization. The supplement took place in January-June 2011 and was administered to
the same sample units that were in sample for NCVS during that time period. All students who
met the following criteria were in scope:
1.
2.
3.
4.
5.
Age 12-18
Attended school any time during the previous six months
Were enrolled in grades 6-12
Were not home schooled
Already completed their NCVS interview for the same time period [3]
All NCVS and SCS interviews were conducted in a computer-assisted personal interviewing
(CAPI) environment. Interviews could be conducted by telephone or by personal visit.
There are three ways that a person can be a non-respondent to the SCS:
•
•
•
The household did not respond to NCVS.
The household responded to NCVS, but a student within the household (that would be in
scope for SCS) did not respond to the NCVS interview.
A person responded to NCVS, but did not respond to SCS.
Nonresponse bias is reduced by applying weight adjustments to respondents within the same
demographic groups during our estimation. The following bullets explain how the demographic
groups are formed for each of the three noninterview adjustments:
•
NCVS household noninterview adjustment – groups are formed by urbanicity, race, and
whether or not the household is inside a Core Based Statistical Area (CBSA). A CBSA is
a geographic entity that has an urban core of at least 10,000 population and surrounding
counties with a high degree of social and economic integration with the urban core.
•
NCVS person noninterview adjustment – groups are formed by region, age, race, and
sex.
•
SCS noninterview adjustment – groups are formed by age, race, and sex.
In the noninterview adjustments, we create the demographic groups so that the cases within one
group share a lot of similar characteristics. Although it is not guaranteed for any one group, as a
rule, “similar characteristics” means that members of the group have similar exposure to school
crime and are similar in their likelihood to respond to the survey. The groups were initially
established by choosing variables which were thought to be related to nonresponse and
nonresponse bias.
4
Nonresponse bias could still be present in the estimates after the nonresponse adjustments. This
is true for two reasons:
•
•
4.
There could be nonresponse bias associated with demographic characteristics that are not
included in the nonresponse adjustment groups.
We do not have any descriptive information about non-respondents, therefore we are
unable to adjust for them.
Methods
An ideal way of examining nonresponse bias is to measure the estimate of interest for
respondents as well as non-respondents and relate the difference to the magnitude of
nonresponse that exists. We cannot examine nonresponse in this way because we do not have an
estimate of school crime for the non-respondents. An alternative is to compare the
characteristics of the respondents and the non-respondents to see if they are similar, which is
what we have done in this report.
The study involved the calculation of response rates, respondent and non-respondent
distributions, and nonresponse bias estimates for several different subgroups of SCS and NCVS
data. The response rates tell us the percentage of a particular subgroup that responds to the SCS
or the NCVS. It is useful to compare response rates for different subgroups. Respondent and
non-respondent distributions show us the relative number of respondents or non-respondents
within the different levels of a subgroup variable. The nonresponse bias estimates give us
information about the impact of nonresponse that exists. We generally computed estimates
related to person response and item response. We examined estimates related to household
nonresponse in previous nonresponse bias studies, but could not include household estimates
here because:
•
•
No reliable data are available for nonresponding households.
The household results would lose a degree of accuracy because we cannot limit
households to those that contain students between 12 and 18 years of age.
We produced estimates for different subgroups (such as male/female, black/non-black, different
regions, etc.) in order to try to pinpoint certain groups that are more prone to nonresponse. The
characteristics must be available for both respondents and non-respondents.
5
Obtaining Descriptive Variables for Non-respondents
For SCS non-interviews, we first tried to get values for the descriptive variables from the
corresponding NCVS interviews in the first half of 2011. If values could not be found there,
they went to NCVS data from the past to try to get the values. Similarly, for NCVS person
noninterviews in the first half of 2011, we tried to get values from NCVS data from the past.
In NCVS production, some variables that are still blank after looking at past data are given
values through allocation in program edits (i.e., the values were imputed). However, we are not
using values that are allocated in the edits in this study.
Obtaining and Using County-Level Statistics
We computed the county Uniform Crime Reporting (UCR) crimes per person using 2009 1 UCR
data from the FBI and 2009 population estimates from Population Division (POP). We
identified the counties that had SCS sample and grouped the counties into three categories of
UCR crime level (low, medium, high). We made use of the unweighted SCS cases to make the
categories as equal as possible.
We also obtained county level median income from 2005 to 2009 ACS data and formed three
categories in the same way described in the paragraph above.
Weights
In the detailed weighting process for NCVS, baseweights were adjusted with several different
factors, which are: weighting control factor, new permit factor, weighting factor cap, withinhousehold noninterview factor, household noninterview factor, first-stage ratio-estimate factor,
and second-stage ratio estimate factor.
Since the noninterview adjustment components of the final NCVS weights are created so that
respondents represent the non-respondents, non-respondents do not have final person weights.
Therefore, baseweights were used in this study when computing weighted data. The
baseweight is the inverse of the probability of selection of a unit or person.
Universes for the Estimates
Many of the estimates shown in this report were computed for two different universes:
•
•
1
All persons in scope for SCS (numbers 1-5 from section 3).
All persons age 12-18 in scope for NCVS (number 1 from section 3) excluding NCVS
interviews screened out for SCS.
The one exception is for Illinois. Data from 2009 was not available, so we used 2008 UCR data for that state.
6
The point of the 12-18 universe was to approximate the persons in the original NCVS sample
that would be in scope for SCS. This universe includes persons in the SCS workload as well as
NCVS non-interviews.
For tables based on the NCVS universe, we examined NCVS nonresponse. For the tables based
on the SCS universe, we examined SCS nonresponse. We include both sets of estimates because
not responding to NCVS is one reason why a person does not respond to SCS. People that did
not respond to NCVS were not in the SCS workload, so these people did not respond to SCS
either.
Estimates
The response rates reported in this document are simply the percentage of a certain group that
responds. For example, the percentage of males that respond. For respondent distributions, the
estimate for males is the percentage of respondents that are male. Similarly, the non-respondent
distribution estimate for males is the percentage of non-respondents that are male. To examine
the association between nonresponse and available demographic variables, we computed chisquare tests.
The formula that we used to examine nonresponse bias is:
∑W kY k
k ∈Sr
−
Bias(y r ) = (y r − y t ) × 100 =
∑W k
k ∈Sr
∑W Y
∑W
k k
k ∈St
k
k ∈St
where
y t = the mean based on all sample cases
y r = the mean based only on respondent cases
Sr
St
Yk
Wk
=
=
=
=
total respondents in sample
total persons in sample
one person with characteristic of interest
weight of a person
7
× 100
For example, we compute the nonresponse bias for males as
𝑡𝑜𝑡𝑎𝑙 𝑟𝑒𝑠𝑝𝑜𝑛𝑑𝑒𝑛𝑡 𝑚𝑎𝑙𝑒𝑠
𝑡𝑜𝑡𝑎𝑙 𝑚𝑎𝑙𝑒𝑠
�
−
� × 100
𝑡𝑜𝑡𝑎𝑙 𝑟𝑒𝑠𝑝𝑜𝑛𝑑𝑒𝑛𝑡𝑠
𝑡𝑜𝑡𝑎𝑙 𝑝𝑒𝑟𝑠𝑜𝑛𝑠 𝑖𝑛 𝑠𝑎𝑚𝑝𝑙𝑒
Ideally, nonresponse bias estimates should be based on rates of school crime. We cannot
compute our nonresponse bias estimates based on school crime because we do not know the
crime rates for the non-respondents.
5.
Overall Response Rates
Table 1 shows the overall response rates for NCVS households, NCVS persons age 12-18, and
SCS persons, as well as a combined response rate. We estimate that only 56.5 percent of people
in the SCS universe completed the SCS interview. Note that the household response rate is
based on all households because we do not know which nonresponding households contain
persons in the SCS universe. The NCVS person response rate uses person non-interviews for
age 12-18, so this is an approximation of the persons that would have been in the SCS universe.
See “Universes of the Estimates” in section 4 for more information.
Table 1: Overall Unit Response Rates
Type of Rate
Response Rate
NCVS Household
Person
Overall
90.8%
60.6%*
NCVS
(12-18)
70.5%
SCS
85.9%
55.0%
* Combined NCVS and SCS person response rate
Table 2 shows the unweighted total sample counts, total eligible units, and total completed
interviews for the different types of sample units in the first half of 2011. The person universe
only includes persons that are age 12-18.
8
Table 2: Sample Counts for January – June 2011
Sample Unit
Original Sample
(Eligible & Ineligible)
Eligible Units
Completed
Interviews
62,965
52,238
47,404
NCVS
Persons 12-18
N/A
10,341
7,492
SCS Persons
N/A
6,802
5,860
NCVS
Households
6.
Unweighted
Obtaining Values of Variables for Person Non-respondents
The following tables display the number of non-interviews that received values for subgroup
variables from post-interviewing sources as well as the counts by source.
Table 3: Obtaining Values of Variables for SCS Person Non-interviews
Variable
Total Non-interviews
Obtained from Current or
Past NCVS Data
Still Blank
Age
945
887
58
Sex
945
944
1
Race
945
924
21
Hispanic
945
936
9
Tenure
945
945
0
Table 4: Obtaining Values of Variables for NCVS Person (Age 12-18) Non-interviews
Variable
Total Non-interviews
Obtained from Current or
Past NCVS Data
Still Blank
Age
2,849
2,595
254
Sex
2,849
2,844
5
Race
2,849
2,810
39
Hispanic
2,849
2,829
20
Tenure
2,849
2,849
0
As shown in the above tables, we were able to obtain values of the subgroup variables from
current or past NCVS data for the large majority of person noninterviews. Therefore, we expect
the subgroup estimates presented in this document to be reliable in terms of the characteristics of
interviews versus noninterviews.
9
7.
Person Nonresponse Estimates
This section shows response rates, respondent and non-respondent distributions, and
nonresponse bias estimates for persons, and includes a discussion of person nonresponse
estimates. We present two tables for each type of estimate. One of the tables is for SCS persons
and the other table is for NCVS persons. Due to the small number of blank values for the
subgroup variables (as shown in section 6), we generally do not provide the “blank” categories
in the following tables. The exception is for the tables of distributions, where it is useful to see
the percentage accounted for by blanks.
10
Response Rates
Table 5 shows response rates for all NCVS persons, age 12-18, by subgroup variable.
Table 5: Person Response Rates for NCVS Persons
Characteristic
Age
12
13
14
15
16
17
18
Sex
Male
Female
Race
White Only
Black Only
Asian Only
All Others
Hispanic Origin
Hispanic
Non-Hispanic
Urbanicity
Urban
Suburban
Rural
Region
Northeast
Midwest
South
West
Tenure of Household
Owner
Renter
County UCR Crimes
Low
Medium
High
County Median Income
Low
Medium
High
Overall
% of Total
Response Rate (%)
13.9%
14.3%
13.8%
14.5%
14.8%
14.5%
10.3%
75.9%
78.3%
73.0%
72.4%
69.6%
71.7%
60.5%
50.8%
49.1%
69.8%
71.3%
77.5%
13.5%
3.8%
4.8%
71.3%
65.1%
70.9%
74.8%
20.0%
79.7%
77.8%
68.8%
27.0%
49.9%
23.1%
73.5%
68.6%
71.1%
16.8%
24.9%
35.2%
23.1%
62.8%
69.4%
72.3%
74.5%
70.9%
29.1%
69.4%
73.3%
33.7%
33.1%
33.2%
67.9%
71.3%
72.3%
33.4%
33.6%
33.0%
100%
72.4%
69.5%
69.7%
70.5%
11
Table 6 shows response rates for SCS persons, by subgroup variable.
Table 6: Person Response Rates for SCS Persons
Characteristic
Age
12
13
14
15
16
17
18
Sex
Male
Female
Race
White Only
Black Only
Asian Only
All Others
Hispanic Origin
Hispanic
Non-Hispanic
Urbanicity
Urban
Suburban
Rural
Region
Northeast
Midwest
South
West
Tenure of Household
Owner
Renter
County UCR Crimes
Low
Medium
High
County Median Income
Low
Medium
High
Overall
% of Total
Response Rate (%)
13.8%
14.8%
14.6%
15.2%
14.8%
14.8%
10.1%
85.1%
85.8%
90.3%
89.9%
90.4%
87.6%
71.5%
51.3%
48.6%
85.9%
85.8%
75.8%
15.1%
4.0%
4.9%
86.2%
84.6%
83.8%
88.0%
21.4%
78.4%
87.0%
85.7%
29.2%
48.7%
22.2%
84.6%
85.8%
87.6%
17.2%
24.0%
35.3%
23.5%
82.9%
83.0%
87.3%
88.8%
68.9%
31.1%
86.0%
85.5%
32.8%
33.3%
33.9%
86.1%
86.0%
85.5%
33.5%
33.1%
33.4%
100%
85.8%
85.7%
86.1%
85.9%
Comparing table 5 and table 6, we see that the response rate for persons age 18 is lower than
that of other ages for both NCVS persons and SCS persons. Among NCVS persons, females
have a slightly higher response rate than males. For SCS persons, male and female response
rates are about the same. In both tables, “All other races” shows the highest response rate,
followed by “White Only.” Hispanic persons had a response rate that was nine percent higher
than non-hispanics in the NCVS interview but Hispanics had only a slightly higher response rate
in the SCS interview. Response rates do not vary much for urban, suburban, and rural areas. For
both tables, the west region shows the highest response rate, followed by the south. Renter
12
households had a higher response rate than owner households in the NCVS interview, but for
the SCS interview they are about the same. NCVS results display a higher response rate in high
crime areas, but for SCS results, the rates do not vary much among the low, medium, and high
categories. Areas with low median income show a higher response rates than other areas in the
NCVS interview, but the rates do not vary much among the three categories for the SCS
interview.
Respondent and Non-respondent Distributions
Tables 7 and 8 show comparisons of respondent and non-respondent distributions for persons in
the different subgroups.
13
Table 7: Person Respondent and Non-respondent Distributions for NCVS Persons
Characteristic
Age
12
13
14
15
16
17
18
Blank
Sex
Male
Female
Blank
Race
White Only
Black Only
Asian Only
All Others
Blank
Hispanic Origin
Hispanic
Non-Hispanic
Blank
Urbanicity
Urban
Suburban
Rural
Region
Northeast
Midwest
South
West
Tenure of
Household
Owner
Renter
Blank
County UCR
Crimes
Low
Medium
High
County Median
Income
Low
Medium
High
Overall
Person Respondent
%
Person Nonrespondent %
Chi-Square Statistic
(df)
P-value
14.9%
15.9%
14.3%
14.9%
14.6%
14.8%
8.8%
1.8%
11.3%
10.5%
12.7%
13.6%
15.3%
14.0%
13.8%
8.9%
1286.09 (7)
< 0.0001
50.3%
49.7%
0.02%
52.1%
47.8%
0.2%
39.62 (2)
<0.0001
78.4%
12.5%
3.9%
5.1%
0.2%
75.5%
16.0%
3.8%
4.1%
0.7%
101.38 (4)
< 0.0001
22.1%
77.8%
0.1%
15.1%
84.3%
0.7%
168.47 (2)
< 0.0001
28.2%
48.6%
23.3%
24.3%
53.1%
22.6%
27.17 (2)
<0.0001
14.9%
24.6%
36.1%
24.5%
21.2%
25.8%
33.1%
20.0%
113.70 (3)
< 0.0001
69.8%
30.2%
0.0%
73.7%
26.3%
0.0%
39.03 (2)
< 0.0001
32.5%
33.5%
34.0%
36.6%
32.2%
31.2%
24.72 (2)
<0.0001
34.3%
33.1%
32.6%
100%
31.2%
34.8%
33.9%
100%
11.07 (2)
0.004
14
Table 8: Person Respondent and Non-respondent Distributions for SCS Persons
Characteristic
Person Respondent
%
Person Nonrespondent %
Chi-Square Statistic
(df)
P-value
Age
12
13.7%
14.6%
13
14.8%
14.9%
14
15.4%
10.1%
1012.08 (7)
< 0.0001
15
15.9%
10.9%
16
15.6%
10.0%
17
15.1%
13.0%
18
8.4%
20.4%
Blank
1.1%
6.2%
*Sex
Male
51.4%
51.1%
0.06 (2)
0.81
Female
48.6%
48.8%
Blank
0.0%
0.1%
Race
White Only
76.1%
73.8%
Black Only
14.9%
16.4%
124.86 (4)
< 0.0001
Asian Only
3.9%
4.5%
All Others
5.1%
4.2%
Blank
0.1%
1.1%
Hispanic Origin
Hispanic
21.7%
19.7%
145.79 (2)
< 0.0001
Non-Hispanic
78.3%
79.3%
Blank
0.0001%
1.0%
Urbanicity
Urban
28.7%
31.8%
9.90 (2)
0.0071
Suburban
48.7%
48.7%
Rural
22.6%
19.5%
Region
Northeast
16.6%
20.8%
60.42 (3)
< 0.0001
Midwest
23.2%
28.8%
South
35.9%
31.7%
West
24.3%
18.6%
Tenure of
Household
Owner
69.1%
68.1%
17.23 (2)
0.0002
Renter
30.9%
31.9%
County UCR
Crimes
Low
32.9%
32.2%
0.41 (2)
0.81
Medium
33.4%
33.1%
High
33.8%
34.6%
County Median
Income
Low
33.5%
33.7%
0.37 (2)
0.83
Medium
33.0%
33.5%
High
33.5%
32.8%
100%
100%
Overall
*Sex is never blank for respondents. The chi-square test cannot use empty cells, so the chi-square test for sex does not include
blank values. All other chi-square tests include blank values.
15
The chi-square tests for NCVS persons showed significant differences (at the alpha=0.05 level)
for the distributions of all of the variables. All of them except the test for county median income
were highly significant. For SCS persons, the distributions for age, race, Hispanic origin, region,
and tenure were highly significant. Urbanicity was significant at the alpha=0.05 level. Sex,
county UCR crimes, and county median income were not significant. For the distributions that
were shown to be significantly different, we need to determine if the difference is of practical
importance. This was done using the nonresponse bias measure below.
16
Nonresponse Bias Estimates
Our estimates of nonresponse are not based on school crime estimates. The estimates of
nonresponse bias shown in Tables 9 and 10 are computed by subtracting the third column
(percentage of total persons with the characteristic of interest) from the second column
(percentage of respondents with the characteristic of interest).
Table 9: Nonresponse Bias Estimates for NCVS Persons
Characteristic
Age
12
13
14
15
16
17
18
Sex
Male
Female
Race
White Only
Black Only
Asian Only
All Others
Hispanic Origin
Hispanic
Non-Hispanic
Urbanicity
Urban
Suburban
Rural
Region
Northeast
Midwest
South
West
Tenure of
Household
Owner
Renter
County UCR
Crimes
Low
Medium
High
County Median
Income
Low
Medium
High
% of Respondents
% of Total
Nonresponse Bias
Bias As Percent of
“%of Total”
14.9%
15.9%
14.3%
14.9%
14.6%
14.8%
8.8%
13.9%
14.3%
13.8%
14.5%
14.8%
14.5%
10.3%
1.0
1.6
0.5
0.4
-0.2
0.3
-1.5
7.2%
11.2%
3.6%
2.8%
1.4%
2.1%
14.6%
50.3%
49.7%
50.8%
49.1%
-0.5
0.6
1.0%
1.2%
78.4%
12.5%
3.9%
5.1%
77.5%
13.5%
3.8%
4.8%
0.9
-1.0
0.1
0.3
1.2%
7.4%
2.6%
6.2%
22.1%
77.8%
20.0%
79.7%
2.1
-1.9
10.5%
2.4%
28.2%
48.6%
23.3%
27.0%
49.9%
23.1%
1.2
-1.3
0.2
4.4%
2.6%
0.9%
14.9%
24.6%
36.15
24.5%
16.8%
24.9%
35.2%
23.1%
-1.9
-0.3
0.95
1.4
11.3%
1.2%
2.7%
6.1%
69.8%
30.2%
70.9%
29.1%
-1.1
1.1
1.6%
3.8%
32.5%
33.5%
34.0%
33.7%
33.1%
33.2%
-1.2
0.4
0.8
3.6%
1.2%
2.4%
34.3%
33.1%
32.6%
33.4%
33.6%
33.0%
0.9
-0.5
-0.4
2.7%
1.5%
1.2%
17
Table 10: Nonresponse Bias Estimates for SCS Persons
Characteristic
Age
12
13
14
15
16
17
18
Sex
Male
Female
Race
White Only
Black Only
Asian Only
All Others
Hispanic Origin
Hispanic
Non-Hispanic
Urbanicity
Urban
Suburban
Rural
Region
Northeast
Midwest
South
West
Tenure of
Household
Owner
Renter
County UCR
Crimes
Low
Medium
High
County Median
Income
Low
Medium
High
% of Respondents
% of Total
Nonresponse Bias
Bias As Percent of
“%of Total”
13.7%
14.8%
15.4%
15.9%
15.6%
15.1%
8.4%
13.8%
14.8%
14.6%
15.2%
14.8%
14.8%
10.1%
-0.119
-0.009
0.755
0.715
0.792
0.295
-1.696
0.9%
0.1%
5.1%
4.7%
5.4%
2.0%
16.8%
51.4%
48.6%
51.3%
48.6%
0.039
-0.026
0.1%
0.1%
76.1%
14.9%
3.9%
5.1%
75.8%
15.1%
4.0%
4.9%
0.332
-0.214
-0.094
0.122
0.4%
1.4%
2.4%
2.5%
21.7%
78.3%
21.4%
78.4%
0.283
-0.142
1.3%
0.2%
28.7%
48.7%
22.6%
29.2%
48.7%
22.2%
-0.431
-0.011
0.442
1.5%
0.02%
2.0%
16.6%
23.2%
35.9%
24.3%
17.2%
24.0%
35.3%
23.5%
-0.6
-0.8
0.6
0.8
3.5%
3.3%
1.7%
3.4%
69.1%
30.9%
68.9%
31.1%
0.133
-0.133
0.2%
0.4%
32.9%
33.4%
33.8%
32.8%
33.3%
33.9%
0.1
0.1
-0.1
0.3%
0.3%
0.3%
33.5%
33.0%
33.5%
33.5%
33.1%
33.4%
0
-0.1
0.1
0.0%
0.3%
0.3%
For the NCVS interview, most of the subgroups showed nonresponse bias estimates of about
one percent or less. The exceptions are the age 13 and age 18 age groups, Hispanic and nonHispanic groups, and the northeast region. The Hispanic category shows the most bias at 2.1
percent. While the non-Hispanic subgroup shows a high nonresponse bias estimate, the estimate
is only 2.4 percent of the total percentage, so there is not a big impact of nonresponse bias for
that subgroup. The age 13 and Hispanic categories showed positive bias, meaning that the
response was very good and bias is an issue because of other corresponding categories. For
example, response is good in the Hispanic category, but nonresponse among non-Hispanics
18
causes a large impact of bias in the Hispanic category.
For the SCS interview, most of the subgroups had nonresponse bias estimates that:
• Were less than 0.3 percent, and
• Were less than five percent of the total percentage
The exception was the age 18 category, which had a nonresponse bias estimate of 1.7
percent, which was 16.8 percent of the total percentage.
Person Nonresponse Conclusions
In the weighting process, the person-noninterview adjustments are applied to cells that are
created by region, age, race, and sex. We expect the weighting adjustments to reduce the effect
of nonresponse for these categories. However, some of these subgroups showed the most
nonresponse bias. The age 18 subgroups showed a lot of bias in the NCVS interview as well as
the SCS interview. The age 13 subgroup and the northeast region showed a lot of bias in the
NCVS interview but not in the SCS interview.
Given that the SCS has a relatively small sample and some of the subgroups represent a small
percentage of the total sample, we can expect some fluctuations. This is one reason why we can
observe high nonresponse bias percentages for small subgroups.
Perhaps the most perplexing results concern the northeast region. For the NCVS interviews, the
northeast region represents about 17 percent of the total sample and the nonresponse bias
estimate for this region is about 11 percent of the total percentage. These results are surprising
because all areas of the nation are becoming more and more diverse and census regions
represent large geographic areas. We do not understand how there could be enough differences
among the regions to cause differences in the response of school crime. We suggest more
research into school crime response by region as validation of the results reported here.
The impact of nonresponse is most concerning for the Hispanic category. Because Hispanic
origin showed some of the largest bias among the categories in the NCVS interview and it is not
used in any of the weight adjustments, we recommend that it be considered as an additional
variable for use in the cells of the NCVS person adjustment factor.
19
8.
Item Nonresponse Estimates
We computed nonresponse statistics for the following items from the SCS:
•
•
•
Question #17a – Is it possible to get alcoholic beverages or drugs at your school?
Question #19a – During this school year, has any student bullied you?
Question #19b – Thinking about all the ways in which you were bullied, how often did
all those things happen?
Question #19c – Where did the bullying occur?
Question #19e – What were the injuries you suffered as a result of being pushed, shoved,
tripped, or spit on?
Question #20a – During this school year has another student cyberbullied you?
Question #21b – Were any of the hate-related words related to your race, religion, etc.?
Question #23a – During this school year, did you ever stay away from any of the
following places because you thought someone might attack or harm you there?
Question #24 – How often are you afraid that someone will attack or harm you on a
school bus on the way to and from school?
•
•
•
•
•
•
Table 11: Item Response Rates
Item
Total Persons in Universe
Response Rate
Question #17a
5,857
99.1%
Question #19a
5,857
98.9%
Question #19b
1,634
100.0%
Question #19c
1,634
98.2%
Question #19e
462
99.7%
Question #20a
5,857
98.7%
Question #21b
510
100.0%
Question #23a
5,857
98.8%
Question #24
5,857
98.6%
Due to the skip pattern on the SCS questionnaire, the different items apply to different
subgroups of the sample persons. For example, when respondents were asked question 19a (has
any student bullied you), and the answer was “yes,” they also had to answer question 19b (how
often?). If the answer for 19a was “no,” they got to skip 19b.
Item Nonresponse Conclusions
As shown in Table 11, the response rate for all of the items are either 100 percent or nearly 100
percent. We do not have evidence that there is a nonresponse problem for items.
20
9.
Recommendations
We make the following recommendations for the future:
10.
•
Based on the nonresponse differences between the Hispanic and non-Hispanic
subgroups, we recommend that we consider using Hispanic origin as one of the
noninterview adjustment cells when producing NCVS estimates.
•
We recommend more research to determine whether or not school crime actually varies
by census region.
Limitations
1.
Using past data to assign subgroup variables to non-respondents - Due to
inmovers and outmovers, it is possible for subgroup variables that we get from past data
to be out of date. However, we do not believe our results need to be 100% accurate in
order to show major differences between respondents and non-respondents. We assume
that the demographics of neighborhoods do not change very much in three years, and
therefore, our estimates should be pretty good overall.
2.
Determining the universe – By defining the overall universe as all persons age
12-18, we only approximate the persons in the original NCVS sample that would be in
scope for SCS. The information that determines whether or not an NCVS interview is in
scope for SCS (shown in section 3) is collected at the beginning of the SCS interview.
Therefore, we did not know exactly how many of the NCVS non-interviews would have
been in scope for SCS. We did have age available from NCVS data, so we used that
variable (when filled) to approximate NCVS non-interviews that were in scope for SCS.
3.
Variances - In some nonresponse bias studies, variances are computed for the
nonresponse bias estimates. We did not compute variances in this study.
4.
Dependence in the Data - Housing units are sampled for NCVS, and then
persons within the sample housing units are interviewed for NCVS and SCS. This
means that the sample persons are clustered within housing units, so the persons are not
completely independent. The chi-square test assumes independence, so this clustering
should be considered when examining the chi-square test results.
11.
Who to Contact with Questions
Direct any questions about this document to:
•
Joseph Burcham at 763-4278, or
21
•
12.
Stephen Ash at 763-4294
Miscellaneous
This memorandum is stored in the directory “M:\ADC-LEDSP\VEB\NCVS\_Final Memos”
with the name “2012-xx NCVS 2011 SCS NR Bias Report v1.0.doc”.
13.
References
[1] Guideline 3.2.9, Standards and Guidelines for Statistical Surveys (2006), Office of
Management and Budget.
[2] Memorandum for Cheryl R. Landman from Ruth Ann Killion, Subject: Nonresponse Bias
Plan for the 2011 School Crime Supplement (SCS) to the National Crime Victimization Survey
(NCVS), November 24, 2010.
[3] National Center for Education Statistics., “Indicators of School Crime and Safety: 2007,”
December 2007.
[3] Memorandum for Cheryl R. Landman from Ruth Ann Killion, Subject: Data Request for the
School Crime Supplement (SCS) Nonresponse Bias Study, August 22, 2011.
22
| File Type | application/pdf |
| Author | trumanj |
| File Modified | 2012-09-27 |
| File Created | 2012-09-17 |