Attachment 6 - Response rates for the Preproduction Test

JSM 2016 - Government Statistics Section

Response Rates for the Pre-Production Test of
the Occupational Requirements Survey
Alice Yu1, Chester H. Ponikowski1, & Erin McNulty1
1

U.S. Bureau of Labor Statistics,
2 Massachusetts Ave., NE, Room 3160 Washington, DC 20212
Abstract
The Occupational Requirements Survey (ORS) is an establishment survey conducted by
the Bureau of Labor Statistics (BLS) for the Social Security Administration (SSA). The
survey collects information on the vocational preparation and the cognitive and physical
requirements of occupations in the U.S. economy, as well as the environmental conditions
in which those occupations are performed. In fiscal year (FY) 2015, the BLS completed
data collection for the ORS pre-production test. This paper focuses on the process for
computing and analyzing the response rates from the ORS pre-production test, utilizing
Office of Management and Budget (OMB) approved methods and formulas to produce
detail statistics –weighted and unweighted at the establishment, occupation, and item
levels. The results from this process will be used to help identify important auxiliary
variables for use in estimation processes to reduce potential bias due to non-response in
future samples.
Key Words: response rates, efficiency rates, completion rates, non-response bias
1. Introduction
In the summer of 2012, the Social Security Administration (SSA) and the Bureau of Labor
Statistics (BLS) signed an interagency agreement to begin the process of testing the
collection of data on occupations. As a result, the Occupational Requirements Survey
(ORS) [1] was established as a test survey in late 2012. The goal of ORS is to collect and
publish occupational information that will replace outdated data currently used by SSA.
All outputs generated from ORS data will be made public for use by non-profits,
employment agencies, state or federal agencies, the disability community, and other
stakeholders.
The ORS data are collected by field economists. The field economists are required to
collect close to 70 data elements related to the occupational requirements of a job. The
following four groups of data are being collected:





Physical demands of work such as keyboarding and lifting
Environmental conditions such as extreme heat and cold
Vocational preparation including education, prior work experience, and training
Mental and cognitive demands of work including decision making and communication

Response rates are one of the most important indicators of a survey’s quality since they
can be used as a method to gauge the potential for non-response bias. Although most
surveys have procedures to adjust for non-response, a low response rate may have an
impact on accuracy of a survey estimate of the population value. Therefore, it is important
to monitor response rates and keep them as high as possible. The purpose of this paper is

1622

JSM 2016 - Government Statistics Section

to document the methods for analyzing response rates in ORS samples. This paper will
describe the results from the pre-production test as an example of the method to be used
for future production analyses. Section 2 of this paper provides additional background
information on the ORS, including description of response status codes used by the survey.
Section 3 describes calculation of response rates at the establishment, occupation, and ORS
element level. Section 4 presents analysis of response rates at the three levels. Section 5
presents our conclusion and suggestions for future work.
2. Background Information on ORS
In addition to providing Social Security benefits to retirees and survivors, the Social
Security Administration (SSA) administers two large disability programs, which provide
benefit payments to millions of beneficiaries each year. Determinations for adult disability
applicants are based on a five-step process that evaluates the capabilities of workers, the
requirements of their past work, and their ability to perform other work in the U.S.
economy. In some cases, if an applicant is denied disability benefits, SSA policy requires
adjudicators to document the decision by citing examples of jobs the claimant can still
perform despite restrictions (such as limited ability to balance, stand, or carry objects) [2].
For over 50 years, the Social Security Administration has turned to the Department of
Labor's Dictionary of Occupational Titles (DOT) [3] as its primary source of occupational
information to process the disability claims [4]. SSA has incorporated many DOT
conventions into their disability regulations. However, the DOT was last updated in its
entirety in the late 1970’s, although a partial update was completed in 1991. Consequently,
the SSA adjudicators who make the disability decisions must continue to refer to an
increasingly outdated resource because it remains the most compatible with their statutory
mandate and is the best source of data at this time.
When an applicant is denied SSA benefits, SSA must sometimes document the decision by
citing examples of jobs that the claimant can still perform, despite their functional
limitations. However, since the DOT has not been updated for so long, there are some jobs
in the American economy that are not even represented in the DOT, and other jobs, in fact
many often-cited jobs, no longer exist in large numbers in the American economy. For
example, a job that is often cited is “envelope addressor,” because it is an example of a
low-skilled job from the DOT with very low physical demands. There are serious doubts
about whether or not this job still exists in the economy.
SSA has investigated numerous alternative data sources for the DOT such as adapting the
Employment and Training Administration’s Occupational Information Network (O*NET)
[5], using the BLS Occupational Employment Statistics program (OES) [6], and
developing their own survey. But SSA was not successful with any of these potential data
sources and turned to the National Compensation Survey program at the Bureau of Labor
Statistics.
In fiscal years 2013 and 2014, several feasibility tests were performed to assess the viability
of collecting data on occupational requirements using the platform currently used by the
NCS. These tests provided evidence that the NCS platform could be adapted to ORS data
collection, which led to the pre-production test in FY 2015.4 Unlike the earlier tests, which
were small-scale and tested a subset of data elements or the viability of different collection
methods, the pre-production test was designed as a relatively large-scale, nationally
representative test of ORS data collection. ORS pre-production data collection began in
October 2014 and continued until May 2015. The sampling, data collection, procedures,
and review were designed to mimic what will occur during ORS production. [7]

1623

JSM 2016 - Government Statistics Section

The ORS sample is based on a complex two-stage stratified design with probability
proportionate to employment size sampling at each stage. The first stage is a probability
sample of establishments and the second stage is a probability sample of jobs (occupations)
from sampled establishments. Stratification of establishments in the sampling frame is by
industry and ownership, and also implicitly by region and establishment employment. The
frame used for sampling is developed from the BLS Quarterly Census of Employment and
Wages (QCEW) Database with railroads added in. Allocation of sample is proportional to
employment size. ORS samples follow a three-year rotation. Nonresponse in ORS can
occur at the establishment level, job level, and data items (elements) level. Adjustment to
sample weights is done at the establishment and job levels. Imputation is used to account
for missing item values. For more details on the ORS sample design, see the Ferguson and
McNulty paper [8]. Under this design, it is possible for a job to be sampled more than once
in a given establishment. When this occurs, the job is “collapsed” so that data for the job
is only collected once. In reports about data collection, collapsed jobs are counted only
once. In this response analysis, collapsed quotes are counted every time they were selected.
2.1 Response Status Codes: Non-response Types and Outcome codes
Like any survey, the ORS does not receive responses from every establishment in its
sample. Ideally, the sample establishment agrees to participate in the survey and gives the
Field Economist (FE) quality data. However, sometimes the FE is unable to make contact
with a sample establishment’s representative that is knowledgeable of the ORS data
elements, or an establishment can simply refuse to participate. Also, sample establishments
may go out of business or be out of the survey’s scope. A list of response status codes for
establishments and occupations are provided below:
Response Status
(Code)

Usable (USE)

Indications
Establishment data: When the establishment is coded with all of
the following:
- description of establishment operations for the purpose of
assigning North American Industry Classification System
(NAICS)
total employment
eligible employment
at least one usable occupational observation
Occupational data: When the occupation in the sample
establishment is coded with all of the following:
occupational employment
worker characteristics (Full-time/Part-time, Union/Nonunion, and Time/Incentive)
occupational work schedule
worker type (Supervisory, Non-supervisory, Lead)
job leveling
job duties to code the eight-digit Standard Occupational
Classification (SOC) code using Training
Administration’s Occupational Information Network
(O*NET)
at least one ORS element data

1624

JSM 2016 - Government Statistics Section

Response Status
(Code)
Refusals (REF)

Out-of-Business
(OOB)

Out-of-Scope
(OOS)

Indications
Refusals can take several forms:
- The establishment/occupation does not have the
minimum required data to be usable.
- The respondent is unwilling or unable to provide data.
For Establishment data only: When a sample establishment is
no longer in business. Since the sample of establishments is
chosen some months before the actual start of collection, it is
possible that some sample units are no longer in business by the
date scheduled for data collection.
For Establishment data only: A sample establishment can be
out of scope for two reasons:
- Geography
When an establishment is located in or has moved to an
area entirely outside of the United States, defined as the
50 states and the District of Columbia.
- Industry
When an establishment falls into one of the following
industry categories:
▪ Federal Government
▪ Private households
▪ Agriculture
▪ Quasi-Federal
▪ Foreign Government
▪ International Government
(For establishment data: When all occupations…)
(For occupational data: When the occupation…)

( )…in the sample establishment are in one or more of the
following categories:
- contractors
- corporate officers, trustees, and board members who do
not hold a job at the firm
- employees on strike more than a year
- family members earning higher-than-market wages
- federal work-study students
No-Matching-Job
- individuals on long-term disability (LTD) not expected to
(NMJ)
return
- leased employees
- non-working individuals with no guarantee to return
- owners of unincorporated firms
- temporary help employees
- volunteers and unpaid workers
- For occupational data only: employees outside the
assigned area (except for situations where worker lives
outside the area, but all work performed via email and
phone)

1625

JSM 2016 - Government Statistics Section

Even if the sample establishment agrees to participate in the survey and gives the FE data,
it would be ideal to capture all of the data for the survey, but this is not always the case. A
list of response status codes for ORS element data are provided below:
Response Status
(Code)
Known (KN)
Present, but
unknown (PU)
Unknown (UK)

Indications
Respondent provided the ORS element data.
Respondent stated the ORS element is present, but does not
know the duration for which the ORS element is present.
Respondent does not know or did not provide data on the ORS
element.
3. Calculation of Response Rates

The Office of Management and Budget (OMB)-approved methods [9] and formulas [10]
were used to produce detail statistics on response rates and efficiency rates.
The formulas used to compute the two rates are as follows:
Response Rate
Efficiency Rate
(For establishment and occupational data)
= USE / (USE + REF)
(For ORS element data)
= (KN+PU) / (KN + PU + UK)

(For establishment data)
= USE / (USE + REF + OOB + OOS + NMJ)
(For occupational data)
= USE / (USE + REF + NMJ)

3.1 Types of Rates
Two types of rates were calculated: response rates and efficiency rates. Response rates
measure how much of the viable sample yielded usable data for estimation. Viable sample
is the original sample excluding establishments or occupations that are considered out-ofbusiness, out-of-scope, or have no matching jobs. Efficiency rates measure how much of
the original sample yielded results usable for estimation. Efficiency rates are not calculated
for ORS element data since all ORS elements are collected for all occupations, and none
are out-of-scope. Response rates and efficiency rates both include collapsed data.
Collapsed data occur when the same occupation is selected more than once from an
establishment.
3.1.1 Unweighted vs. Weighted Data
Unweighted and weighted data for response rates and efficiency rates are both
needed to fully evaluate survey performance. Unweighted rates provide a useful
description of the operational aspect of the survey and indicate how many of the
raw number of cases were successfully collected. Unweighted rates are
computed using unit counts. Weighted rates provide a better indication of the
potential impact of response on estimates. Weighted rates are computed using
the original sample weights for each unit, rather than final sample weight,
because the final sample weights are only assigned to establishments and
occupations that are usable for estimation.
3.2 Types of Units
Computations for rates are based on in the following inputs:
-

Establishment data: establishments in the sample
Occupational data: selected occupations for each establishment in the sample

1626

JSM 2016 - Government Statistics Section

-

ORS Element data: ORS elements eligible to be collected for each occupation in
each establishment in the sample
3.3 Levels of Details
Rates are calculated at various levels of data aggregation for the three types of units. The
levels of data aggregation are:
-

Aggregate industries, which include 24 private industries and 10 government
industries, as listed below.

Private Industry
1) Mining
2) Utilities
3) Construction
4) Manufacturing
5) Aircraft Manufacturing
6) Wholesale Trade
7) Retail Trade
8) Transportation and Warehousing
9) Information
10) Finance (excluding Insurance)
11) Insurance Carriers and Related Activities
12) Real Estate and Rental and Leasing
13) Professional, Scientific, and Technical Services
14) Management of Companies and Enterprises
15) Administrative and Support, Waste Management
16) Education (rest of)
17) Elementary & Secondary Educations
18) Colleges & Universities Educations
19) Health and Social Assistance (rest of)
20) Hospitals
21) Nursing Homes
22) Arts, Entertainment, and Recreation
23) Accommodation and Food Services
24) Other Services (except Public Administration)
-

Government Industry

1) Mining, Construction,
Manufacturing
2) Wholesale and Retail
Trades
3) Elementary & Secondary
Educations
4) Colleges & Universities
Educations
5) Educational Services
6) Hospitals
7) Nursing & Residential
Cares
8) Other Health Care
9) Public Administration
(excluding National
Security Information,
Finance, Food Services,
Professionals)
10) Other service providing

Census Regions and Divisions
There are 4 census regions, each with 2 or 3 census divisions. The regions are West
with Pacific and Mountain divisions; Midwest with West North Central and East
North Central divisions; Northeast with Middle Atlantic and New England
divisions; and South with West South Central, East South Central, and South
Atlantic divisions. [11]

-

Establishment Size Class is assigned based on establishment employment size,
as listed below.
Establishment Size Class
1
2
3
4

Employment Size
Less than 50 employees
Between 50 and 99 employees
Between 100 and 499 employees
More than 499 employees

1627

JSM 2016 - Government Statistics Section

-

Ownership
An establishment can be labelled as private entity, state government, or local
government.

-

Major occupational groups are identified with 2-digit Standard Occupational
Classification (SOC) codes, as listed below.
2-digit SOC Codes
11
13
15
17
19
21
23
25
27
29
31
33
35
37
39
41
43
45
47
49
51
53

Standard Occupational Classification
Management Occupations
Business & Finance Operations Occupations
Computer & Mathematical Occupations
Architecture & Engineering Occupations
Life, Physical, & Social Science Occupations
Community & Social Service Occupations
Legal Occupations
Education, Training, & Library Occupations
Arts, Design, Entertainment, Sports, & Media Occupations
Healthcare Practitioners & Technical Occupations
Healthcare Support Occupations
Protective Service Occupations
Food Preparation & Serving Related Occupations
Building, Grounds Cleaning, & Maintenance Occupations
Personal Care & Service Occupations
Sales & Related Occupations
Office & Administrative Support Occupations
Farming, Fishing, & Forestry Occupations
Construction & Extraction Occupations
Installation, Maintenance, & Repairing Occupations
Production Occupations
Transportation & Material Moving Occupations
4. Analysis of Response Rate

4.1 Establishment Level
Table 1 below shows that there are 2,549 establishments in the Occupational Requirements
Survey pre-production sample. Of the 2,549 establishments, 168 establishments were
either out of business, out of scope, or had no jobs in scope for ORS. Of the remaining
2,381 establishments, 1,851 establishments provided usable data, indicating a usable
establishment unweighted response rate of 78 percent, weighted response rate of 76
percent, unweighted efficiency rate of 73 percent, and weighted efficiency rate of 69
percent.
Table 1. Overall Response and Efficiency Rates for Establishment Level Data
Total Establishments
USE
2,549
1,851
Unweighted Response Rate = 78%
Unweighted Efficiency Rate = 73%

1628

REF
OOB/OOB/NMJ
530
168
Weighted Response Rate = 76%
Weighted Efficiency Rate = 69%

JSM 2016 - Government Statistics Section

For the section below, refer to the Figures in the attachment provided at the end of the
paper.
Figures 1, 3, 5, and 8 display result for establishment units. In each of the four Figures,
the darker line represents weighted data and the lighter line represents unweighted data
for both response (red) and efficiency (blue) rates. If the darker line is greater than the
lighter line, then more data were collected on establishments that have greater
representation in the population sampled.
Figure 1 displays the weighted and unweighted response rates and efficiency rates for
private aggregate industries. The private aggregate industries are listed in descending
order by (dark red) weighted response rates. The weighted response rates range from
52 percent for ‘Information’ industry to 93 percent for ‘Utilities’ industry.
Figure 3 displays the weighted and unweighted response rates and efficiency rates for
census regions and divisions. Figure 3 is sorted by (dark red) weighted response rates
in descending order for census region and for census division within each census
region. The weighted response rates for census regions range from 73 percent for
‘Midwest’ region to 81 percent for ‘West’ region. The weighted response rates for
census division range from 71 percent for ‘West South Central’ division to 81 percent
for ‘Mountain’ division.
Figure 5 displays the weighted and unweighted response rates and efficiency rates for
employment size. The employment sizes are listed in descending order by (dark red)
weighted response rates. The weighted response rates range from 72 percent for
establishments with ‘More than 499 Employees’ to 81 percent for establishments with
‘Less than 50 Employees.’
Figure 8 displays the weighted and unweighted response rates and efficiency rates for
ownership status. The ownership statuses are listed in descending order by (dark red)
weighted response rates. Government establishments appear to have better response
rates than private establishments.
4.2 Occupation Level
Table 2 below shows within the 1,851 usable establishments, 10,495 occupational
observations or quotes were attempted to be collected. Of the 10,495 quotes, 9,132
provided usable data, 1,232 refused, and 131 are out of scope. Collapsed quotes are counted
once for each time selected. The occupational level response rates are 88 percent for
unweighted data and 89 percent for weighted data. The occupational level efficiency rates
are 87 percent for unweighted data and 88 percent for weighted data.
Table 2. Overall Response and Efficiency Rates for Occupational Level Data
From 1,851 Usable Establishments:
Total Occupations
USE
REF
NMJ
10,495
9,132
1,232
131
Unweighted Response Rate = 88%
Weighted Response Rate = 89%
Unweighted Efficiency Rate = 87% Weighted Efficiency Rate = 88%

1629

JSM 2016 - Government Statistics Section

For the section below, refer to the Figures in the attachment provided at the end of the
paper.
Figures 2, 4, 6, and 9 display results for occupational units. In each of the four Figures,
the darker line represents weighted data and the lighter line represents unweighted data
for both response (red) and efficiency (blue) rates. If the darker line is greater than the
lighter line, more data were collected on occupations that have greater representation
in the population sampled.
Figure 2 displays the weighted and unweighted response rates and efficiency rates for
private aggregate industry. The private aggregate industries are listed in descending
order by (dark red) weighted response rates. The weighted response rates range from
65 percent for ‘Colleges & Universities Educations’ industry to 100 percent for ‘Arts,
Entertainment, and Recreation’ industry.
Figure 4 displays the weighted and unweighted response rates and efficiency rates for
census regions and divisions. The weighted response rates are sorted in descending
order for census region and for census division within each census region. The
weighted response rates for census region range from 88 percent for ‘West’ region to
90 percent for ‘Midwest’ region. The weighted response rates for census division range
from 87 percent for ‘Pacific’ division to 93 percent for ‘East South Central’ division.
Figure 6 displays the weighted and unweighted response rates and efficiency rates for
establishment employment size. The employment sizes are listed in descending order
by (dark red) weighted response rates. The weighted response rates range from 80
percent for establishments with ‘More than 499 Employees’ to 93 percent for
establishments with ‘Less than 50 Employees.’
Figure 9 displays the weighted and unweighted response rates and efficiency rates by
ownership status. The ownership statuses are listed in descending order by (dark red)
weighted response rates. Private establishments appear to have better response rates
than government establishments.
4.3 ORS Element Level
There are up to 70 ORS elements [12] collected for each occupational observation. Table
3 below shows response rate range for ORS elements in 9,132 usable occupations from
1,851 usable establishments. The weighted response rates range from 77 percent to 98
percent. Efficiency rates are not calculated for ORS element data since all elements are
collected for all occupations, and an ORS element can never be out-of-scope.
Table 3. Overall Response Rates for ORS Element Level Data
From 9,132 Usable Occupations in 1,851 Usable Establishments:
Unweighted Response Rate Range: (76%, 98%)
Weighted Response Rate Range: (77%, 98%)
ORS elements data were also analyzed at various level of detail. For example, among the
5 elements with the top weighted response rates, establishments with ’50 to 99 Employees’
provide answers at a higher rate than establishments in the other three size classes. Whereas
within the 5 elements with the bottom response rates, establishments with ‘More than 499

1630

JSM 2016 - Government Statistics Section

Employees’ provide answers at a lower rate than establishments in the other three size
classes.
4.4 Comparison Across the Types of Units
Further analyses were performed on a combination of establishment data, occupational
data, and ORS element data. Figure 7 displays combined effect of establishment and
occupational response on the overall response and efficiency rates. For example, the
combined weighted response rate for the entire sample of occupations within
establishments with ‘More than 499 employees’ is 58 percent. The 58 percent is the result
of 72 percent response at the establishment level and 88 percent at the occupational level.
The overall response rates for the entire sample of occupations within establishments range
from 58 percent with ‘More than 499 Employees’ to 75 percent with ‘Less than 50
Employees’.
5. Conclusion and Future Work
Considering the amount of data requested by ORS, the response and efficiency rates for
pre-production sample are fairly high. The collected data show that the rates vary by
industry, occupational group, establishment size, and ownership. This indicates that
industry, occupational group, establishment size, and ownership are important auxiliary
variables; and they should be used in adjustment for nonresponse process to reduce
potential bias due to nonresponse.
We plan to continue to monitor, calculate, and analyze response rates by available auxiliary
variables from the ongoing ORS production sample each year. The results from further
analysis may lead to additional improvements in the nonresponse adjustment process for
ORS. We also plan to carefully analyze the potential for non-response bias in key subsets
of the data collected.

Any opinions expressed in this paper are those of the authors and do not constitute policy
of the Bureau of Labor Statistics or the Social Security Administration.

1631

JSM 2016 - Government Statistics Section

References
[1]
[2]
[3]
[4]
[5]
[6]
[7]
[8]
[9]
[10]
[11]
[12]

Bureau of Labor Statistics, Occupational Requirements Survey, http://www.bls.
gov/ors/.
Social Security Administration, Occupational Information System Project, http://
www.ssa.gov/disabilityresearch/occupational_info_systems.html.
U.S. Department of Labor, Employment and Training Administration (1991),
“Dictionary of Occupational Titles, Fourth Edition, Revised 1991”.
Occupational Information Development Advisory Panel, 2010, http://www.social
security.gov/oidap/index.htm.
U.S. Department of Labor, O*Net Online, http://www.onetonline.org/.
Bureau of Labor Statistics, Occupational Employment Statistics Program, http://
www.bls.gov/oes/.
Bureau of Labor Statistics, Occupational Requirements Survey Pre-Production
Report September 28, 2015. Occupational Requirements Survey, http://www.bls.
gov/ncs/ors/pre-prod-report.htm.
Ferguson, Gwyn R., McNulty, Erin. 2015. Occupational Requirements Survey
Sample Design. In JSM proceedings, Government Statistics Section. Alexandria,
VA: American Statistical Association.
OMB Statistical Standards and Guidelines, page 8, https://www.whitehouse.gov/
sites/default/files/omb/assets/omb/inforeg/statpolicy/standards_stat_surveys.pdf.
“Questions and Answers When Designing Surveys for Information Collections”,
pages 56-71, https://www.whitehouse.gov/sites/default/files/omb/inforeg/pmc_
survey_guidance_2006.pdf.
“Census Regions and Divisions of the United States”, https://www2.census.gov/
geo/pdfs/maps-data/maps/reference/us_regdiv.pdf.
Bureau of Labor Statistics, Occupational Requirements Survey Pre-Production
Estimation and Validation Report September 10, 2015. Occupational
Requirements Survey, http://www.bls.gov/ncs/ors/pre-prod-estval.htm.

1632

JSM 2016 - Government Statistics Section

Aggregate Industry: Rates (in Occupational Units)
Figure 2

Figure 1

Aggregate Industry: Rates (in Establishment Units)

Response Rates for Establishment (Figure 1) and Occupational (Figure 2) Units by
Aggregate Industry

1633

JSM 2016 - Government Statistics Section

Response Rates for Establishment (Figure 3) and (Figure 4) Occupational Units by
Census Regions and Divisions

Census Regions and Divisions: Rates
(in Establishment Units)

Figure 3

Weighted Efficiency Rate

Unweighted Efficiency Rate

Weighted Response Rate

Unweighted Response Rate

95%
90%
85%
80%
75%
70%
65%
60%
Mountain

Pacific

West
Figure 4

Middle
Atlantic

New
England

South
Atlantic

Northeast

West East South West East North
South
Central
North
Central
Central
Central

South

Midwest

Census Regions and Divisions: Rates
(in Occupational Units)
Weighted Efficiency Rate

Unweighted Efficiency Rate

Weighted Response Rate

Unweighted Response Rate

95%
90%
85%
80%
75%

70%
65%
60%
West East North East South South
North
Central Central Atlantic
Central

Midwest

West
South
Central

South

Middle
Atlantic

New Mountain
England

Northeast

1634

Pacific

West

JSM 2016 - Government Statistics Section

Response Rates for Establishment (Figure 5) and Occupational (Figure 6 & 7) Units
by Employment Size
Figure 5

Employment Size: Rates (in Establishment Units)
95%
90%
85%
80%
75%
70%
65%
60%

Less than 50
Employees

50 to 99
Employees

100 to 499
Employees

More than 499
Employees

Weighted Efficiency Rate

0.67

0.71

0.69

0.71

Unweighted Efficiency Rate

0.72

0.74

0.71

0.74

Weighted Response Rate

0.81

0.76

0.72

0.72

Unweighted Response Rate

0.83

0.77

0.73

0.75

Figure 6

Employment Size: Rates (in Occupational Units)
95%
90%
85%
80%
75%
70%
65%
60%

Less than 50
Employees

50 to 99
Employees

100 to 499
Employees

More than 499
Employees

Weighted Efficiency Rate

0.92

0.91

0.87

0.78

Unweighted Efficiency Rate

0.93

0.91

0.87

0.80

Weighted Response Rate

0.93

0.92

0.88

0.80

Unweighted Response Rate

0.93

0.92

0.88

0.81

1635

JSM 2016 - Government Statistics Section

Figure 7

Occupational Rates out of the Entire Sample of Occupations
(Including Establishment’s Non-usable Occupations)

Response Rates for Establishment (Figure 8) and Occupational (Figure 9) Units by
Ownership Status
Figure 8

Ownership Status: Rates
(in Establishment Units)

Figure 9

95%

95%

90%

90%

85%

85%

80%

80%

75%

75%

70%

70%

65%

65%

60%

Ownership Status: Rates
(in Occupational Units)

60%
State
Local
Private
Government Government Establishment

State
Local
Private
Government Government Establishment

1636