Attachments M,N,O

Attachment M
Sample Design

SAMPLE DESIGN
First and Second Stages of Selection: Census Tracts and Segments
The 2013 National Survey on Drug Use and Health (NSDUH) sample design provides for
estimates by state in all 50 states and the District of Columbia. States may therefore be viewed
as the “first level” of stratification as well as a reporting variable. Eight states, labeled as the
“large” states in Table 1, will have a sample designed to yield 3,600 respondents per state. The
remaining 43 (“small”) states1, will have a sample designed to yield 900 respondents per state.
Each state sample will be allocated equally to the three age groups 12 to 17, 18 to 25, and 26 or
older. This national target sample size of 67,500 will consist of 22,500 for each of the three age
groups.
The larger sample sizes obtained at the state level along with small area estimation techniques
refined under previous survey contracts will enable the development of estimates for all states,
for several demographic subgroups within each state (e.g., age group and race/ethnicity group),
for some Core Based Statistical Areas (CBSAs), and for similar small areas.
A coordinated sample for the period 2005-20132 has been selected down to the area segment
level as a means of coordinating the overlap of sample areas from year to year. The “second
level” of stratification within the coordinated design was defined as contiguous geographic areas
within each state. These state sampling (SS) regions are of approximately equal size in terms of
the allocated sample.
The design of the first stage of selection began with the construction of an area sample frame that
contained one record for each census tract in the United States. If necessary, census tracts were
aggregated until each tract had, at a minimum, 150 dwelling units in urban areas and 100
dwelling units in rural areas. After primary sampling units (PSUs; one or more census tracts)
were formed, a sample was selected within each SS region with probabilities proportionate to a
composite size measure and with minimum replacement. Additional implicit stratification was
achieved by sorting the first-stage sampling units by a CBSA/SES (socioeconomic status)
indicator3 and by percent non-Hispanic white prior to selection.
For the second stage of sampling for the coordinated sample, each of the selected Census tracts
was partitioned into clusters of dwelling units by aggregating adjacent Census blocks.
Consistent with the terminology used in previous surveys, these geographic clusters of blocks are
1

For reporting and stratification purposes, the District of Columbia is treated the same as a state and no
distinction is made in the discussion.
2

The coordinated design developed for the 2005-2009 NSDUHs was extended to the 2010, 2011 and 2012
NSDUHs and will also be used for the 2013 NSDUH. A total of 48 segments per SS region were selected for the
2005-2009 NSDUHs. Only 24 segments per region were used for these surveys; the remaining 24 segments
constitute the "reserve" sample. Twelve reserve segments per region were used to support the 2010 through 2012
NSDUHs and the remaining 12 segments per region will be available for use in 2013.
3
Four categories are defined as: (1) CBSA/low SES, (2) CBSA /high SES, (3) Non CBSA /low SES, and
(4) Non CBSA /high SES.

P-1

referred to as segments. Segments were formed so that they contain at least 150 dwelling units in
urban areas or 100 dwelling units in rural areas and were constructed using 2000 Decennial
Census data supplemented with revised population counts obtained from outside sources. A
sample dwelling unit in the survey refers to either a housing unit or a group quarters listing unit
such as a dormitory room or a shelter bed.
One segment was selected within each selected Census tract with probability proportional to a
composite size measure. Segments were formed so that they will contain sufficient numbers of
dwelling units to support one field test and two annual survey samples. This allows half of the
segments used in any given year’s main sample to be used again in the following year as a means
of improving the precision of measures of annual change. This also allows for any special
supplemental sample or field test that SAMHSA may wish to conduct within the same segments.
A sample of 8 segments per SS region will be used for the 2013 survey year. These 8 segments
will be randomly assigned to quarters and to two panels within each quarter. The panels used in
the 2013 survey will be designated as panels 9 and 10. Panel 9 segments have been used for the
2012 survey and will be used for the second time in the 2013 survey. The panel 10 segments
will be used for the 2013 survey only. Dwelling units that were not selected for the 2012 survey
will be eligible for selection in the panel 9 segments in 2013.
Approximately one-fourth of the final sample of respondents will be collected from each
calendar quarter. This design feature will help control the influence of seasonal variation on
drug use prevalence estimates and other important survey outcome measures of interest.
Third Stage of Selection: Listed Lines
Before any sample selection within selected segments can proceed, specially trained field
household listers will list all dwelling units and potential dwelling units within each selected area
segment. A dwelling unit is either a housing unit for a single household or one of the eligible
noninstitutional group quarters listing units that are part of the defined target population. The
listings will be based primarily on observations of the area segment and may include vacant
dwelling units and units that appear to be dwelling units but may actually be used for
nonresidential purposes. The objective of the listing is to attain as complete a listing of eligible
residential addresses as possible; any false positives for residences will be eliminated during the
household screening process after the sample is selected.
The sampling frame for the third stage of sample selection will be the lines of listed dwelling
units and potential dwelling units. After accounting for eligibility, nonresponse, and the fourthstage sample selection procedures, it was determined that roughly 198,370 lines will need to be
selected in order to obtain a sample of 67,500 responding persons distributed by state and agegroup as shown in Table 2.
As in previous years, during the data collection period, if an interviewer encounters any new
dwelling unit in a segment or finds a dwelling unit that was missed during the original counting
and listing activities, then the new/missed dwellings will be selected into the 2013 survey using

P-2

the half open interval selection technique4. The selection technique eliminates any frame bias
that might be introduced because of errors and/or omissions in the counting and listing activities
and also eliminates any bias that might be associated with using “old” segment listings.
Fourth Stage of Selection: Persons
After dwelling units are selected within each segment, an interviewer will visit each selected
dwelling unit to obtain a roster of all persons residing in the dwelling unit. This roster
information will be used to select 0, 1, or 2 persons for the survey. Sampling rates will be pre-set
by age group and state. Roster information will be entered directly into the electronic screening
instrument which will automatically implement this fourth stage of selection based on the state
and age group sampling parameters.
One exciting consequence of using an electronic screening instrument in the survey is the ability
to efficiently sample from all possible pairs of respondents within a dwelling unit while
preserving the target sampling rates for individuals within 5 age groups (12 to 17, 18 to 25, 26 to
34, 35 to 49, and 50 or older). Using an adaptation of Brewer’s method for samples of size 2, a
sample of 0, 1, or 2 persons will be selected from each dwelling unit. As a consequence, any two
survey-eligible people within a dwelling unit will have a known chance of being selected, that is,
all survey eligible pairs of people will have some nonzero chance of being selected. This feature
of the design is of interest to survey researchers because for example, it will allow analysts to
examine how the drug use propensity of one individual in a family will relate to the drug use
propensity of another family member residing in the same dwelling unit (e.g., the relationship of
drug use between a parent and child).
As illustrated in Table 1, at the fourth stage of selection, roughly 84,375 people will be selected
from within 145,474 screened and eligible dwelling units. Assuming a 80% interview
completion rate and an 89% screening completion rate, these sample sizes are sufficient to obtain
the desired 67,500 person respondents.
Expected Precision of Survey Estimates
The multistage, stratified 2013 survey design has been designed to achieve specified precision
for various person subpopulations of interest. Precision requirements specified by SAMHSA
were that the expected relative standard error on a prevalence of 10% not exceed the following:


3.00% for total population statistics,



5.00% for statistics in three age group domains: 12-17, 18-25, and 26 plus years-old.
4

In summary, this technique states that if a dwelling unit is selected for the 2013 study and an interviewer
observes any new or missed dwelling units between the selected dwelling unit and the dwelling unit appearing right
after the selection on the counting and listing form, then all new/missed dwellings between the selection and the next
one on the listing form will be selected. If a large number of new/missed dwelling units are encountered (generally
greater than 10) then a sample of the missing dwelling units will be selected. If the listing is highly discrepant (50 or
more missed dwelling units following any one selected dwelling unit or 150 or more total missed dwelling units),
then special "bust" sampling procedures will be employed.

P-3

The allocation of 300 persons per each of the major age groups (12-17, 18-25, and 26 or older)
for 43 small sample states and 1,200 persons per each of these age groups for the 8 large sample
states was also taken as a requirement to support small area estimation in the small sample states
and direct estimation in the large sample states.
Tables 1 and 2 reflect the sample allocation at the national and state levels. Table 3 shows the
projected relative standard errors for selected prevalence measures after standardization to reflect
an estimated prevalence of 0.10. All of the initial specifications for precision levels are satisfied
by the proposed allocation.

P-4

Table 1. Summary of 2013 Main Study Design
Statistic
Total Sample
State Sampling (SS) Regions
Segments
Selected Lines
Eligible dwelling units
Completed screening interviews
Selected persons
Completed Interviews

Small States

Large States

Total

516
4,128
113,732
93,714
83,405
48,375
38,700

384
3,072
84,638
69,740
62,069
36,000
28,800

Total Per State
SS Regions
Segments
Selected Lines
Completed Interviews
Interviews Per Segment

12
96
2,645
900
9.38

48
384
10,580
3,600
9.38

Total Per SS Region/Segment by
Quarter
Segments Per SS Region
Interviews Per SS Region
Interviews Per Segment

2
18.75
9.38

2
18.75
9.38

43

8

Total States

900
7,200
198,370
163,454
145,474
84,375
67,500

51

Note:
"Small” states refer to states where the design is expected to yield roughly 900 respondents in the
2013 survey and “Large” states refer to states where the design is expected to yield roughly
3,600 respondents.

P-5

Table 2. Sample Sizes and Projected Respondents by State and Age Group

State

SS
Regions

Total
Segments

Total
Selected
Dwelling
Units

Total Respondents
Total
Selected
People

12 to
17

18 to 25

26 to 34

35 to 49

50+

Total

900

7,200

198,370

84,375

22,500

22,500

6,000

9,000

7,500

67,500

Northeast
Connecticut
Maine
Massachusetts
New Hampshire
New Jersey
New York
Pennsylvania
Rhode Island
Vermont

12
12
12
12
12
48
48
12
12

96
96
96
96
96
384
384
96
96

2,645
2,645
2,645
2,645
2,645
10,580
10,580
2,645
2,645

1,125
1,125
1,125
1,125
1,125
4,500
4,500
1,125
1,125

300
300
300
300
300
1,200
1,200
300
300

300
300
300
300
300
1,200
1,200
300
300

70
65
77
67
73
312
283
74
68

127
121
124
129
128
491
479
122
120

103
114
99
104
99
397
438
104
112

900
900
900
900
900
3,600
3,600
900
900

Midwest
Illinois
Indiana
Iowa
Kansas
Michigan
Minnesota
Missouri
Nebraska
North Dakota
Ohio
South Dakota
Wisconsin

48
12
12
12
48
12
12
12
12
48
12
12

384
96
96
96
384
96
96
96
96
384
96
96

10,580
2,645
2,645
2,645
10,580
2,645
2,645
2,645
2,645
10,580
2,645
2,645

4,500
1,125
1,125
1,125
4,500
1,125
1,125
1,125
1,125
4,500
1,125
1,125

1,200
300
300
300
1,200
300
300
300
300
1,200
300
300

1,200
300
300
300
1,200
300
300
300
300
1,200
300
300

332
82
76
81
297
81
81
82
79
307
79
77

489
120
117
118
487
122
118
117
112
478
113
121

379
98
107
101
416
97
101
101
109
415
108
102

3,600
900
900
900
3,600
900
900
900
900
3,600
900
900

South
Alabama
Arkansas
Delaware
Dist of Columbia
Florida
Georgia
Kentucky
Louisiana
Maryland
Mississippi
North Carolina
Oklahoma
South Carolina
Tennessee
Texas
Virginia
West Virginia

12
12
12
12
48
12
12
12
12
12
12
12
12
12
48
12
12

96
96
96
96
384
96
96
96
96
96
96
96
96
96
384
96
96

2,645
2,645
2,645
2,645
10,580
2,645
2,645
2,645
2,645
2,645
2,645
2,645
2,645
2,645
10,580
2,645
2,645

1,125
1,125
1,125
1,125
4,500
1,125
1,125
1,125
1,125
1,125
1,125
1,125
1,125
1,125
4,500
1,125
1,125

300
300
300
300
1,200
300
300
300
300
300
300
300
300
300
1,200
300
300

300
300
300
300
1,200
300
300
300
300
300
300
300
300
300
1,200
300
300

79
81
75
106
294
85
81
84
78
81
78
84
76
80
359
80
75

118
116
121
110
463
128
119
117
126
118
125
114
120
120
496
124
113

103
103
104
84
443
87
100
99
96
101
97
102
104
100
345
96
112

900
900
900
900
3,600
900
900
900
900
900
900
900
900
900
3,600
900
900

West
Alaska
Arizona
California
Colorado
Hawaii
Idaho
Montana
Nevada
New Mexico
Oregon
Utah
Washington
Wyoming

12
12
48
12
12
12
12
12
12
12
12
12
12

96
96
384
96
96
96
96
96
96
96
96
96
96

2,645
2,645
10,580
2,645
2,645
2,645
2,645
2,645
2,645
2,645
2,645
2,645
2,645

1,125
1,125
4,500
1,125
1,125
1,125
1,125
1,125
1,125
1,125
1,125
1,125
1,125

300
300
1,200
300
300
300
300
300
300
300
300
300
300

300
300
1,200
300
300
300
300
300
300
300
300
300
300

90
87
343
88
80
87
76
87
85
83
108
83
84

123
117
500
123
115
115
111
122
114
114
113
120
112

87
96
357
89
105
98
113
91
101
103
79
97
104

900
900
3,600
900
900
900
900
900
900
900
900
900
900

Total Population

P-6

Table 3. Expected Relative Standard Errors by Age Group Standardized for an Estimated
Prevalence of 10 Percent
Outcome Measure
Past Month Cigarette Use
Past Month Alcohol Use
Past Month Use of Any Illicit Drug
Past Month Use of Any Illicit Drug But Marijuana
Past Month Cocaine Use
Past Year, Dependent on Illicit Drugs
Past Year, Dependent on Alcohol
Past Year Received Treatment for Illicit Drugs
Past Year Received Treatment For Alcohol Use

Estimate
22.97
51.79
8.92
3.56
0.58
1.90
2.81
0.86
0.61

Total
R.S.E.
1.34
0.75
2.16
3.32
7.34
4.23
4.07
6.37
8.93

Past Month Cigarette Use
Past Month Alcohol Use
Past Month Use of Any Illicit Drug
Past Month Use of Any Illicit Drug But Marijuana
Past Month Cocaine Use
Past Year, Dependent on Illicit Drugs
Past Year, Dependent on Alcohol
Past Year Received Treatment for Illicit Drugs
Past Year Received Treatment For Alcohol Use

2.20
2.34
2.02
1.91
1.68
1.77
2.08
1.78
2.10

Estimate
8.34
13.59
10.13
4.50
0.25
2.53
1.10
0.84
0.14

12-17
R.S.E.
3.09
2.43
2.85
4.31
18.52
5.46
9.25
9.91
23.86

1.99
3.00

Average Relative Standard Error
Target Relative Standard Error
Outcome Measure

S.R.S.E.

Estimate
34.24
61.53
21.51
7.95
1.46
5.37
5.11
1.65
0.87

18-25
R.S.E.
1.37
0.81
1.85
3.09
7.79
4.13
4.09
6.98
10.02

S.R.S.E.
2.97
3.07
2.90
2.73
2.84
2.95
2.84
2.72
2.82
2.87
5.00

Average Relative Standard Error
Target Relative Standard Error

P-7

S.R.S.E.
2.79
2.89
2.87
2.81
2.77
2.64
2.92
2.74
2.70
2.79
5.00

Estimate
22.83
54.85
6.57
2.67
0.47
1.22
2.63
0.73
0.62

26+
R.S.E.
1.68
0.88
3.44
5.33
10.86
7.70
5.50
9.19
11.10

S.R.S.E.
2.74
2.92
2.74
2.65
2.23
2.56
2.71
2.36
2.64
2.62
5.00

Projected relative standard errors for direct state estimates by age group are shown in Table 4.
The precision of direct estimates for the small sample states is not considered adequate. Small
area estimation procedures should be used to develop state estimates for the small sample states.
Table 4. Expected Relative Standard Errors by Age Group Standardized for an Estimated
Prevalence of 10 Percent for Large Sample and Small Sample States
Outcome Measure
Expected Relative Standard Errors
Past Year Dependence on Alcohol
Past Month Alcohol Use
Past Month Cigarette Use
Past Month Cocaine Use
Past Year Received Treatment for Illicit Drug Use
Past Year Received Treatment for Alcohol Use
Past Month Use of Any Illicit Drug But Marijuana
Past Year Dependence on Illicit Drugs
Past Month Illicit Drug Use
Average Relative Standard Error

12-17

Outcome Measure
Expected Relative Standard Errors
Past Year Dependence on Alcohol
Past Month Alcohol Use
Past Month Cigarette Use
Past Month Cocaine Use
Past Year Received Treatment for Illicit Drug Use
Past Year Received Treatment for Alcohol Use
Past Month Use of Any Illicit Drug But Marijuana
Past Year Dependence on Illicit Drugs
Past Month Illicit Drug Use
Average Relative Standard Error

12-17

9.88
10.72
10.73
11.16
10.40
10.70
10.34
9.89
10.48
10.48

19.76
21.44
21.45
22.31
20.81
21.41
20.68
19.77
20.95
20.95

P-8

Large Sample States
18-25
26+
9.93
9.41
11.97
10.76
11.16
10.63
10.56
8.96
11.01
9.55
10.00
9.57
10.99
9.87
9.94
8.75
11.02
9.49
10.73
9.67
Small Sample States
18-25
26+
19.87
23.94
22.31
21.12
22.02
19.99
21.97
19.88
22.04
21.46

18.83
21.52
21.25
17.93
19.09
19.14
19.74
17.50
18.98
19.33

Total
7.22
10.29
9.22
6.68
7.18
7.44
6.79
5.90
7.14
7.54
Total
14.44
20.58
18.45
13.36
14.36
14.87
13.58
11.81
14.28
15.08

Attachment N
2013 Interview Incentive Receipt

Interview Incentive Receipt
United States Public Health Service
and
Research Triangle Institute
thank you for participating in the 2013 National Survey on Drug Use and Health.
In appreciation of your participation in this important study, you are eligible to receive a $30 in cash.
Since maintaining the confidentiality of your information is important to us, your name will not be entered on this
form. However, the interviewer must sign and date this form to certify you received (or declined) the cash incentive.

___________________________________
Interviewer

□

_________
Date

__ __ __ __ __ __ __ __ __ __ - __
Case ID

□

Accepted Cash Incentive

Declined Cash Incentive

If you ever feel that you need to talk to someone about mental health issues, you can call the National Lifeline
Network. Counselors are available to talk at any time of the day or night and they can give you information about
services in your area.
1-800-273-TALK or 1-800-273-8255
1-888-628-9454 (Spanish)
http://suicidepreventionlifeline.org/
If you ever feel that you need to talk to someone about drug use issues, you can call the Substance Abuse and Mental
Health Services Administration’s Treatment Referral Helpline. This is a 24-hour service that will help you locate
treatment options near you.
1-800-662-HELP or 1-800-662-4357
1-800-487-4889 (TDD)
http://findtreatment.samhsa.gov
Disposition: Top copy to Respondent, yellow to Field Supervisor, pink to Field Interviewer.

Interview Incentive Receipt
United States Public Health Service
and
Research Triangle Institute
thank you for participating in the 2013 National Survey on Drug Use and Health.
In appreciation of your participation in this important study, you are eligible to receive a $30 in cash.
Since maintaining the confidentiality of your information is important to us, your name will not be entered on this
form. However, the interviewer must sign and date this form to certify you received (or declined) the cash incentive.

___________________________________
Interviewer

□

Accepted Cash Incentive

_________
Date

__ __ __ __ __ __ __ __ __ __ - __
Case ID

□

Declined Cash Incentive

If you ever feel that you need to talk to someone about mental health issues, you can call the National Lifeline
Network. Counselors are available to talk at any time of the day or night and they can give you information about
services in your area.
1-800-273-TALK or 1-800-273-8255
1-888-628-9454 (Spanish)
http://suicidepreventionlifeline.org/
If you ever feel that you need to talk to someone about drug use issues, you can call the Substance Abuse and Mental
Health Services Administration’s Treatment Referral Helpline. This is a 24-hour service that will help you locate
treatment options near you.
1-800-662-HELP or 1-800-662-4357
1-800-4874889 (TDD)
http://findtreatment.samhsa.gov
Disposition: Top copy to Respondent, yellow to Field Supervisor, pink to Field Interviewer.

Attachment O
Certificate of Participation

Unitedd Staates 
U
Pu
ublicc Heaalth S
Serviice

Certificate of Participation
The United States Public Health Service and Research Triangle Institute would like to thank

[Participant’s Signature]

for participating in the National Survey on Drug Use and Health
on
_____________________________
[Date of Interview]

Field Interviewer
Field Interviewer

Ilona S Johnson
Ilona S. Johnson, 

FI ID #

National Field Director 
Research Triangle Institute 
3040 Cornwallis Road 
Research Triangle Park, NC 27709

This document certifies that the above named individual participated in NSDUH, a voluntary survey for the United States Public Health Service.  
Across the country, some participants approach their school teachers or other group leaders to ask about possible special community service credit 
as they completed this important national survey.  The time commitment for participation in this survey is between 1 and 2 hours.  A copy of the 
NSDUH brochure, which explains the study in more detail, should accompany this certificate.  If you need further information, contact the 
National Field Director, Ilona Johnson, at (800) 848‐4079.