Supporting Statement B__3206-0036

Supporting Statement Part B
DD 1918 Establishment Information Form, DD 1919 Wage Data Collection Form, and DD
1919C Wage Data Collection Continuation Form
OMB Control Number: 3206-0036
Justification – Part B a statistical survey
Part B must be completed for any information collection that is a statistical survey, that is, a
collection in which one of the sponsoring agency’s purposes is to use the information for the
description, estimation, or analysis of the characteristics of groups, segments, activities, or
geographic areas. Surveys include both censuses (that is, all members of the group of interest are
asked to submit information) and sample surveys (that is, only a subset of all members are asked
to submit information but the intention is to describe, estimate, or analyze the characteristics of
larger groups, segments, activities, or geographic areas). For more information, see OMB’s
Standards and Guidelines for Statistical Surveys.
1. Development of Concepts, Methods, and Design:
The potential respondent universe is all retail, service, recreational, manufacturing,
transportation, communication, electric, gas, sanitary services, and wholesale trades
establishments. As a result, statistical sampling is used. These surveys have been conducted
since 1973 and yield a response of 21,760 establishments per year.
2. Collection of Data:
In 1988, OPM approved DOD’s assumption of those statistical support functions for FWS wage
surveys previously performed under contract by BLS. DOD establishes lists of private sector
establishments for FWS wage surveys in the 130 appropriated fund and 118 nonappropriated
fund local wage areas. In areas having a relatively small number of establishments within the
scope of the survey (usually 100 or fewer), a universe listing of all area firms is provided. Where
there is a large number of firms, DOD draws a statistical sample, stratifies companies by size and
major industrial category, creates cells of companies, and assigns statistical weights. After the
collection period, DOD reweights establishments, as necessary, to ensure statistical validity.
3. Processing and Editing of Data:
DOD selects the establishments to be surveyed. The respondents work directly with data
collectors knowledgeable in the occupational areas of the survey, and questions are readily
answered regarding any part of the survey. This ensures a maximized response rate from
participants.
4. Production of Estimates and Projections:
The sampling design used in the wage surveys is sampling proportionate to establishment
employment. The universe is divided into groups based on the industry in which the
establishment is engaged. These groups are in turn divided into subgroups based on the

establishment employment. These subgroups are called strata. Within each stratum, a sample
of establishments is selected independently from the other strata. The number of selected
establishments is allocated over the strata based on total stratum employment. The basic steps
for the selection of sample establishments are:
Definition of certainty units, if any
Definition of additional industries to be in the scope of the universe for the wage survey,
such as General Medical and Surgical Hospitals, NAICS 622110
Determination of sample size
Stratification of the universe by industry and employment size
Allocation of the sample over the strata based on the number of employees
Computation of the measure of size for each establishment to determine its probability of
selection
Selection of establishments within each stratum
Computation of the weight for each selected unit
Listing of the selected establishments
As applicable, the methodology to measure sampling error and estimation error.
Agencies under the Federal Wage System are required by title 5, Code of Federal
Regulations (CFR), Part 532 to design and conduct probability surveys according to
accepted statistical principles. These principles provide the framework for calculating
estimates of sampling error. Estimates from nonprobability surveys are difficult to
evaluate because there is no accepted method for measuring the error associated with
estimates from these surveys. This severely limits the use of the estimates. Statistical
principles are also used to determine and select a sample which is consistent with survey
goals and resources.
Ideally, designing a probability sample is an iterative process which starts with
determining the resources available to the survey and identifying goals for the survey.
The next step is to determine the sample size required to meet the survey goals using
accepted statistical principles. In many cases the sample size may be too large for the
survey resources. The survey planners must either find more resources or re-evaluate
survey goals. Goals and resources for the survey must be managed so there is
compatibility with the goals and resources of the agency.
In stratified sampling the population of N units is first divided into subpopulations of N1,
N2, . . . , NL units, respectively. These subpopulations do not overlap and together they
comprise the whole of the population, so that
N1 + N2 + . . . + NL = N
The subpopulations are called strata. To obtain the full benefit from stratification, the
value of the Nh, or total number of units, must be known. When the strata have been
determined, a sample is drawn from each, the drawings being made independently in
different strata. The sample sizes within the strata are denoted by n1, n2, . . ., nL,
respectively.

If a simple random sample is taken in each stratum, the procedure is described as
stratified random sampling.
Stratification is a common technique. There are many reasons for using this technique;
the principal ones are:
1. If data of known precision are wanted for certain subdivisions of the population, it
is advisable to treat each subdivision as a “population” in its own right.
2. Administrative convenience may dictate the use of stratification; for example, the
agency conducting the survey may have field offices, each of which can supervise the
survey for a part of the population.
3. Sampling problems may differ markedly in different parts of the population. With
human populations, people living in institutions (e.g., hotels, hospitals, prisons) are often
placed in a different stratum from people living in ordinary homes because of a different
approach to the sampling is appropriate for the two situations. In sampling businesses we
may possess a list of the large firms, which are placed in a separate stratum. Some type
of area sampling may have to be used for the smaller firms.
4. Stratification may produce a gain in precision in the estimates of characteristics of
the whole population. It may be possible to divide a heterogeneous population in
subpopulations, each of which is internally homogeneous. This is suggested by the name
strata, with its implication of a division into layers. If each stratum is homogeneous, in
that the measurements vary little from one unit to another, a precise estimate of any
stratum mean can be obtained from a small sample in that stratum. These estimates can
then be combined into a precise estimate for the whole population.
The theory of stratified sampling deals with the properties of the estimates from a
stratified sample and with the best choice of the sample sizes nh to obtain maximum
precision. In this development it is taken for granted that the strata have already been
constructed.
The Wage and Salary Division use the following sampling error formula to measure the
inaccuracy of the sample’s statistical characteristics from that of the population since the
sample does not include all members of the population. Data on sampling error is for
internally use only.
Sampling Error = Z * √(p * (1 – p) / n] * [1 – √(n / N))
The weights applied to the survey data to calculate target population estimates; or if an
alternative method of sample design is utilized (for example, ratio estimation), any evaluations to
ensure the method results in population estimates of high quality.
Each establishment selected has a weight assigned. The weight is a whole number and
indicates the number of establishments in the same stratum that the selected establishment
represents. For example, if there are three companies in the universe in a particular stratum

and one is selected for the survey, it will be given a weight of 3 because it represents itself
and two other companies. All companies in a universe survey have a weight of one since
each represents only itself. The sum of the weights for selected establishments in a stratum
must equal the number of establishments in the stratum.
The computation of the weight is as follows:
N
N
r
is calculated:
= W where N is the number of
n
n
n
establishments in the stratum; n is the number of selected establishments in the stratum; W
is the integer, whole number part of the quotient; r is the remainder part of the quotient.
b. Since the sum of the weights must equal the number of establishments in the stratum, r
establishments are given a weight of W + 1 and n – r establishments are given a weight of
W. The weights are assigned randomly among the selected establishments

a. The quantity

After data collection is complete, the appropriate Wage and Salary regional office enters
the data into the survey database. This data includes the total employment and the
collection status (DAC, REF, OOB, etc.) for each establishment on the establishment
survey list. This data is then used to adjust the weights.
Other activities (for example, use of auxiliary data) that will be utilized in conjunction with the
survey data to improve the quality of the estimates.
Not applicable. No other activities will be used at this time.
If the survey data are collected with an intention of developing model-based estimates of target
population characteristics or projections of future values, explain the methods/models that will
be applied to the survey data.
Not applicable. The data collected will not be used to create model-based estimates.
5. Data Analysis: Describe the plans for analyzing the data including methods to be used
for statistical tests to address the needs and uses of the information as described in Part
A, section 2.
The lead agency reviews all material and wage survey data forwarded by the local wage
survey committee or other local survey organization. The review includes: (1) General
review of all survey materials to: (a) Assure that the survey was conducted within the
prescribed procedures and specifications. (b) Consider matters included in the narrative
report and recommendations of the local wage survey committee or other local survey
organization. (c) Note reasons for nonparticipation of establishments in the sample. (d)
Exclude discriminatory rates, whether for an individual or for a group of employees, which
apparently are set in consideration of religious or political affiliations, marital status, race,
color, national origin, age, or sex, or of a physical handicap if the duties of the position
involved may be performed efficiently by a person with the physical handicap. If, after
review of the local wage survey committee recommendation, it is found that a firm does
have discriminatory hiring or other discriminatory rate-setting practices, the lead agency
shall exclude all data obtained from that firm. (e) Resolve questions of comparability of

establishment jobs with survey jobs arising from recommendations of the local wage survey
committee or other local survey organization. (f) Question and verify comparability of job
matches when rate data show marked deviations from those for other jobs in the same
establishment or from other establishments in the survey. Such a deviation raises a question
of comparability and should be cause for further investigation of the job match. (g) Exclude
data that were reported for trainees and apprentices. (h) Resolve questions involving the use
of data from unacceptable sources, e.g., from an industry not in the survey specifications for
the area, or from establishments which do not meet the minimum-size-of-establishment
criterion in S5-6b(3)(a). (i) Verify all computations reported on wage data collection forms.
The lead agency computes a weighted average rate for each appropriated fund survey job
having at least 10 unweighed matches and for each nonappropriated fund job having at least
5 unweighed matches. The weighted average rates shall be computed using the survey job
data collected in accordance with 5 CFR §§532.235 and 532.247 and the establishment
weight. The lead agency computes the unit and frequency paylines using the straight-line,
least squares regression formula: Y = a + bx, where Y is the hourly rate, x is grade, a is the
intercept of the payline with the Y-axis, and b is the slope of the payline. The unit payline is
computed using a weight of one for each of the usable survey jobs and the weighted average
rates identified and computed. The frequency payline is computed using a weight equal to
the number of weighted matches for each of the usable survey jobs and the weighted
average rates identified and computed. The lead agency may compute midpoint paylines
using the following formula: Y = (au + af)/2 + ((bu + bf)/2)x, where Y is the hourly rate, x
is the grade, au is the intercept of the unit payline, af is the intercept of the frequency
payline, bu is the slope of the unit payline, and bf is the slope of the frequency payline. A
midpoint line may be computed using the paylines based on all of the usable survey job
data, and a second midpoint line may be computed using the paylines based on limited
survey job data authorized in 5 CFR §532.241 paragraph (b)(2).
The lead agency selects a payline and construct wage schedules for issuance as the regular
wage schedules for the wage area, after considering all of the information, analysis, and
recommendations made available to it pursuant to 5 CFR §532.245.
6. Review and Evaluation Procedures: The statistical design is prescribed by law. OPM
implemented the law with the advice of the Federal Prevailing Rate Advisory
Committee. Survey methodology is updated as necessary.
7. Data Dissemination:
Procedures for releasing and disseminating statistics and microdata (that is, detailed
responses for individual respondents) to the public. As applicable, also describe the
disclosure limitation methods to be used to achieve the confidentiality discussed in Part
A, section 10.
The lead agency develops and issues wage schedules based on its survey and pay
determinations. Each area wage schedule consists of: Name of wage area; Nonsupervisory
wage rates; Leader wage rates; Supervisory wage rates; Effective date; and Signature
of authorizing official. The lead agency distributes copies of area wage schedules to the
headquarters of each Federal agency having wage employees within the wage area as earlier

reported to the lead agency host installation by the agencies’ activities within the wage area,
and to the headquarters of labor organizations having exclusive recognition in the wage area
and to the headquarters of other labor organizations upon request. One copy of each area
wage schedule is forwarded directly to the central office and to each OPM regional office.
The lead agency also provides copies of wage schedules to other agencies whenever
requested to cover newly established local installations. Wage schedules established
under the FWS are public information. A lead agency may make available to news media and
to any other interested party such information as it considers pertinent concerning new or
revised wage schedules for which it is responsible. Upon receipt of an authorized wage
schedule from a lead agency, each employing agency takes immediate steps to place the
schedule into effect. An employing agency: • Authorizes application of the pay schedule to
its covered wage employees within the wage area; • Places schedules into effect in individual
installations on the date specified on the area wage schedule by the lead agency.
After the publication of wage schedules, the Wage and Salary Division produces a survey
summary that summarizes the results of the wage survey. The survey summary includes data
on the number of observations, means, medians, and other data by survey job and industry
group. To maintain confidentiality of participating establishments, company names are
excluded from the survey summary, and data must be obtained from a minimum of three
establishments to be included in the calculations. Survey summaries are only sent to
participating establishments.
Documentation that will be released to the public to improve understanding of how to
properly interpret, analyze, and evaluate information from the survey.
The survey summary that the Wage and Salary Division produces contains information on
the geographic coverage, industry coverage, occupational coverage, wage area definition, and
survey jobs. There is also a detailed section on how to interpret the survey data.

The following point of contact at DOD designates FWS wage survey data collectors:
Mr. Karl H. Fendt
Chief, Salary and Wage Branch
DOD Defense Civilian Personnel Advisory Service
4800 Mark Center Drive
Alexandria, VA 22350-1100
Email: [email protected]
Telephone: (571) 372-1618