2015 Overview of CPS Sample Design and Methodology

Attachment B

OVERVIEW OF CPS SAMPLE DESIGN AND METHODOLOGY
(For the Sample Design Based on Census 2000)
1.

CPS Sample Design and Selection
The Current Population Survey (CPS) is a monthly survey conducted in approximately
72,000 assigned housing units throughout the United States, including approximately
12,000 housing units from the monthly supplementary sample to improve state-level
estimates of health insurance coverage for low-income children, also known as the State
Children’s Health Insurance Program (SCHIP) expansion. This supplementary sample
has been part of the official CPS since July 2001. Twenty-six states plus the District of
Columbia contain this supplementary sample each month.
The CPS is a probability sample based on a multistage stratified sampling scheme. In
general, the CPS sample is selected from lists of addresses obtained from the most recent
decennial census and updated for new construction. The SCHIP sample selection
methodology is generally similar to that used for the CPS.
a.

State-Based Design
In the first stage of sampling, primary sampling units (PSUs) are selected. These
PSUs consist of counties or groups of contiguous counties in the United States,
and are grouped into strata. The CPS is a state-based design. Therefore, all PSUs
and strata are defined within state boundaries and the sample is allocated among
the states to produce state and national estimates with the required reliability,
while keeping total sample size to a minimum. The national reliability
requirement is a coefficient of variation (CV) of 1.9 percent or less on the monthly
unemployment level, assuming an unemployment rate of 6 percent. The state
reliability requirement is a CV of 8 percent or less on the annual average
unemployment level, assuming an unemployment rate of 6 percent. For New York
and California, the state reliability requirement applies to the following substate
areas: New York City (the five boroughs only), the balance of New York state,
Los Angeles County, and the balance of California.
Each stratum consists of one or more PSUs. Within each stratum, a single PSU is
chosen for the sample, with probability proportional to its population as of the
most recent decennial census (in this case, Census 2000). This PSU represents the
entire stratum from which it was selected. In the case of strata consisting of only
one PSU, the PSU is termed “self-representing.” Sample PSUs from strata with
more than one PSU are called “non self-representing.” The sample PSUs are
selected from each stratum using a statistical method which increases the
probability of keeping the same areas in the sample from one sample redesign to
the next.

2
In total, 824 PSUs from a total of 2,025 in the United States are in sample for
either the basic CPS, the SCHIP expansion, or for both the basic CPS and the
SCHIP expansion; four of these PSUs contain sample for the SCHIP expansion
only.
A sample of addresses within the sample PSUs is obtained in a second step. Most
of the sample addresses are selected from census lists in a single stage of
sampling within the selected PSU; for a relatively small proportion, an additional
stage of selection within the PSU is necessary.1
b.

PSU Stratification
The variables chosen for grouping the non self-representing PSUs in each state
into strata reflect the primary interest of the CPS in maximizing the reliability of
estimates of labor force characteristics. Basically, the same set of stratification
variables (from the Census 2000) were used for each state: unemployment
statistics by male, female; number of families with a female head; and the ratio of
occupied housing units with three or more people, all ages, to total occupied
housing units. In addition, the number of persons employed in selected industries
and the average monthly wage for selected industries were used as stratification
variables in some states. The industry-specific data are averages over the period
1990 through 1998 and were obtained from the Bureau of Labor Statistics.
In states with SCHIP sample, the self-representing PSUs are the same for both
CPS and SCHIP. In all but three SCHIIP states, the same non self-representing
sample PSUs are in sample for both surveys. In the three remaining states, in
order to improve the reliability of the SCHIP estimates in those states, the SCHIP
non self-representing PSUs were selected independently from the CPS sample
PSUs, with replacement.

c.

Rotation System
Each sample is divided into eight approximately equal rotation groups. A rotation
group is interviewed for four consecutive months, temporarily leaves the sample
for eight months and then returns for four more consecutive months before
retiring from the CPS (after a total of eight interviews). This rotation scheme has
been in use since July 1953. The end result of this rotation pattern is an
improvement in the estimates of change on both a month-to-month and year-toyear basis.

2.

CPS Estimation Procedure
The CPS estimation procedure involves an unbiased weight for each person in the
sample. The unbiased weight, which is the inverse of the probability of the person being

1

Additional selection of the sample is done through a sampling of the Building Permit Survey.

3
in the sample, is a rough measure of the number of actual persons that the sample person
represents. Almost all sample persons within the same state have the same unbiased
weight. The unbiased weights are then adjusted for nonresponse, and then other ratio
adjustment procedures are applied.
a.

Noninterview Adjustment
The weights for all interviewed households are adjusted to account for occupied
sample housing units for which no information was obtained. Reasons for a
noninterviewed household include absence of the occupants, impassable roads,
refusal of the occupant to participate in the survey, or unavailability of the
occupant for other reasons. The noninterview adjustment is performed by
noninterview cluster. Noninterview clusters are classified as either metropolitan
or non-metropolitan. PSUs classified as metropolitan are assigned to metropolitan
clusters. PSUs representing metropolitan areas of the same or similar size (based
on Census 2000 population) are grouped in the same noninterview cluster. Each
metropolitan cluster is further divided into two cells: central city and balance of
the metropolitan area. Likewise, non-metropolitan PSUs are assigned to nonmetropolitan clusters. All non-metropolitan areas in a state are placed within the
same noninterview cluster. Due to small sample sizes, a few non-metropolitan
noninterview clusters contain PSUs from more than one state.

b.

Adjusting Estimates to Population Controls
The distribution of the population selected in the sample in any month will differ
somewhat from that of the population as a whole for characteristics such as age,
rate, Hispanic origin, and sex. Since these characteristics are correlated closely
with labor force status and other characteristics estimated from the sample, the
latter estimates can be improved substantially when weighted appropriately by the
known distribution of these population characteristics. This is accomplished
through four adjustments as follows:
1)

First-stage ratio adjustment
In the CPS, some of the sample areas are chosen to represent both
themselves and other areas in the same state, but not in the sample; the
remainder of the sample areas represent only themselves. The first-stage
ratio estimation procedure is designed to reduce that portion of the
variance resulting from requiring sample areas to represent areas not in
sample (i.e., non self-representing PSUs). Therefore, this adjustment
procedure is applied only to sample data for the non self-representing
PSUs and is done by Black alone/non-Black alone cells at the state level.
Each race cell is further divided into two age cells: age 0-15, and age 16
and older.

4
2)

National and state coverage adjustments
The national and state coverage adjustments were introduced in January
2003 in an effort to improve the national and state estimates by race,
Hispanic origin, sex, and age. The national coverage adjustment is done
by Black alone, White alone, Asian alone, and All Other Race for nonHispanics and by White alone, and non-White alone for Hispanics. The
All-Other-Race category includes respondents who indicate they belong to
more than one race. These race/ethnicity categories are further divided
into cells representing various combinations of age and sex.
The national adjustment is performed by month-in-sample pair (1,5; 2,6;
3,7; and 4,8).
The cells used in the state coverage adjustment are defined by race
category (Black alone, non-Black alone), age, and sex. The adjustment is
performed either for each month-in-sample pair or for all eight month-insample groups combined. The actual cells used vary by state/District of
Columbia and race category.

3)

Second-stage ratio adjustment
The second-stage ratio adjustment modifies sample estimates in a number
of age-sex-race-Hispanic origin groups to independently derived censusbased estimates of the civilian noninstitutional population (CNP) in each
of these groups. This adjustment reduces variance of sample estimates
and bias due to differential coverage of the sampling frame. The
adjustment is carried out in three steps and each set of three steps is
referred to as a “rake.” There are 10 cycles (or iterations) of raking. Each
step in each rake is done by month-in-sample pair.
In the first step, the sample estimates are adjusted for each state and the
District of Columbia to independent controls for the CNP by age and sex.
There are three age cells by sex (0-15, 16-44, 45 and over). The second
step of the adjustment is done at the national level by Hispanic origin
status. Hispanic and non-Hispanic each have 13 age/sex cells, which are
adjusted to nationwide independent controls. The third and final step of
the second-stage adjustment is performed by race (Black alone, White
alone, All Other Race). Each of these cells is adjusted to national
independent population controls as in the previous step.
The entire second-stage adjustment procedure is iterated through 10 rakes.
This iteration ensures that the sample estimates of state and national
population by the various age-sex-race-Hispanic origin categories will be
virtually consistent with the independent population controls.

5
3.

Specialized Sampling
An unusual problem occurs in the CPS sample that requires specialized sampling
procedures. This problem occurs in rural areas in the state of Alaska because of their
sparse population. Special methods of defining the ultimate sampling units are used in
these areas.

4.

Periodic Data Collection Cycle
Collection of CPS data on a monthly basis is mandated in Section 2 of Title 29, United
States Code. Less frequent collection would place the Bureau of Labor Statistics, which
is the co-sponsor of the CPS, in violation of this code.

5.

Nonresponse in the CPS
If a respondent is reluctant to participate in the CPS, the interviewer immediately informs
the regional office staff. The regional office sends a follow-up letter to the household
explaining CPS in greater detail and urging cooperation. The interviewer then recontacts
the household and attempts the interview again. If this procedure fails, a Supervisory
Field Representative then contacts the household in an attempt to convert the reluctant
respondent. Methods used to interview reluctant households include conducting
telephone or personal interviews with the household, if so requested, and interviewing a
designated individual within the household. The CPS estimation procedure adjusts for
household nonresponse in its noninterview adjustment procedure, detailed in Paragraph
2.a. above. Individual item nonresponse is allocated using a procedure in which the
missing data are assigned from individuals whose data are complete and have similar
characteristics. The CPS household noninterview rate ranges between 7.0 and 8.5 percent
monthly. Accuracy of the CPS data is maintained through interviewer training and
monthly home studies, monitoring of error and noninterview rates, and systematic
reinterviewing of CPS households. Each month about 2 percent of all CPS enumerators
have their assignments reinterviewed for quality control purposes. Errors uncovered
during the reinterview are discussed with the original interviewer and remedial action is
taken. An additional 1 percent of CPS enumerators have their assignments reinterviewed
monthly to measure response error.

6.

Methodological Testing
The basic CPS program is not used as a vehicle for testing procedures or methods. There
was, however, an extensive program of testing conducted on CPS methods, procedures,
and content. This program, the Methods Development Survey (MDS), and its
predecessor, the Methods Test Panel (MTP), was conducted between May 1978 and
December 1993.
The result of this testing is the new CPS Labor Force Instrument that is collected in a
completely automated CATI/CAPI environment. For further information on the testing

6
procedures and results, see the February 1994 Employment and Earnings article titled,
“Revisions to the Current Population Survey Effective January 1994.”
7.

CPS Statistical Contacts
Individuals consulted on the statistical aspects of the CPS are Ruth Ann Killion
(301/763-2048), and Yang Cheng (301/763-3287) of the Demographic Statistical
Methods Division, U.S. Census Bureau. and Christopher J. Laskey (301/763-5312), of
the Demographic Surveys Division, U.S. Census Bureau, have responsibility for data
collection and processing.