Executive Summary

The Panel on Research on Future Census Methods was formed to examine alternative designs for the 2010 census and to assist the Census Bureau in planning tests and analyses to help assess and compare the advantages and disadvantages of them. Toward this goal, the panel was asked, in its first interim report, to examine whether the auxiliary information that is planned to be collected (and retained) during the 2000 census could be augmented to help guide the Census Bureau in its assessment of alternative designs for the 2010 census.

MODIFYING THE MASTER TRACE SAMPLE

The planned master trace sample database will collect information from a variety of auxiliary census data systems to provide comprehensive information for a sample of housing units, showing how each was processed through every step of the 2000 census. We believe that the master trace sample database has the potential to be the single most useful source of information for assessing alternative designs for the 2010 census. This is due to its integration, at the individual household level, of information from all key census processes, so that all their interactions can be examined.

The current (preliminary) plans for the master trace sample are limited in two ways: first, by viewing it only as the result of census operations applied to a sample of census addresses although some operations are carried out prior to the assignment of an address; second by not explicitly mentioning some census processes that would be important to represent.



The National Academies | 500 Fifth St. N.W. | Washington, D.C. 20001
Copyright © National Academy of Sciences. All rights reserved.
Terms of Use and Privacy Statement



Below are the first 10 and last 10 pages of uncorrected machine-read text (when available) of this chapter, followed by the top 30 algorithmically extracted key phrases from the chapter as a whole.
Intended to provide our own search engines and external engines with highly rich, chapter-representative searchable text on the opening pages of each chapter. Because it is UNCORRECTED material, please consider the following text as a useful but insufficient proxy for the authoritative book pages.

Do not use for reproduction, copying, pasting, or reading; exclusively for search engines.

OCR for page 1
DESIGNING THE 2010 CENSUS: First Interim Report Executive Summary The Panel on Research on Future Census Methods was formed to examine alternative designs for the 2010 census and to assist the Census Bureau in planning tests and analyses to help assess and compare the advantages and disadvantages of them. Toward this goal, the panel was asked, in its first interim report, to examine whether the auxiliary information that is planned to be collected (and retained) during the 2000 census could be augmented to help guide the Census Bureau in its assessment of alternative designs for the 2010 census. MODIFYING THE MASTER TRACE SAMPLE The planned master trace sample database will collect information from a variety of auxiliary census data systems to provide comprehensive information for a sample of housing units, showing how each was processed through every step of the 2000 census. We believe that the master trace sample database has the potential to be the single most useful source of information for assessing alternative designs for the 2010 census. This is due to its integration, at the individual household level, of information from all key census processes, so that all their interactions can be examined. The current (preliminary) plans for the master trace sample are limited in two ways: first, by viewing it only as the result of census operations applied to a sample of census addresses although some operations are carried out prior to the assignment of an address; second by not explicitly mentioning some census processes that would be important to represent.

OCR for page 1
DESIGNING THE 2010 CENSUS: First Interim Report Relevant processes that may not be currently included in plans for the master trace sample are information on “Be Counted” forms that cannot be geocoded, information on the workings of the primary selection algorithm, and processing information on the Accuracy and Coverage Evaluation (ACE) program. Augmenting current plans to include representation of additional census processes will permit better understanding of the advantages and disadvantages of alternative designs for the 2010 census. Recommendation: The current plans for the master trace sample database should be augmented so that data for all key steps in the process —starting with address assignment and ending with a final disposition for each case—are included in the master trace sample data base. SETTING PRIORITIES FOR EVALUATION STUDIES Many of the evaluation plans described to the panel ended with data collection and provided little detail about how the data would be used. The Census Bureau should develop these plans further to include how the data will be analyzed; how the results obtained will inform decisions about the 2010 census design; and what resources, in terms of data collection costs and staff expertise, are required. Understanding the costs and technical resources required and the potential information value of each proposed evaluation study will help in setting priorities and allocating resources to the studies being proposed. The Census Bureau is planning a large number of evaluation studies, and there may be insufficient staff and expertise to adequately use the data being collected. For setting priorities, the objectives should be both to assess 2000 census operations and to provide information to support 2010 census design decisions. The results of this process will allow the the Census Bureau to make informed decisions about which are the most important and the least resource-intensive evaluation activities following the 2000 census. Recommendation: The Census Bureau should develop a detailed plan for each evaluation study on how to analyze the data collected and how to use the results in decision making concerning 2010 census design. The Census Bureau should then use these plans to identify the benefits and resources required for each evaluation study, set priorities among them, and allocate sufficient resources for the careful completion of all or, at least, the highest priority evaluations.

OCR for page 1
DESIGNING THE 2010 CENSUS: First Interim Report MODIFYING THE DESIGN OF AREX 2000 The Administrative Records Census Experiment in 2000 (AREX 2000) will test, in a limited set of sites, the use of administrative records as a supplemental method of data collection. The overall goal of AREX 2000 is to determine whether a merged list of administrative records can achieve sufficient coverage to justify using administrative records in the 2010 census for: (1) whole household nonresponse follow-up, (2) reduction of differential undercoverage, (3) imputation for item nonresponse, (4) address list improvement, and (5) the support of special procedures to target individual groups. However, the current design of AREX 2000 will not sufficiently advance the current state of knowledge as to the feasibility and advantages of the use of a merged list of administrative records for the purposes listed above. The currently planned comparison of aggregate counts could miss information on the kinds of individuals or households that are omitted by either the census or the merged AREX 2000 list. The current plans should be modified to include a match of census households with the merged list. The field follow-up of unresolved matches could be restricted to a sample of cases to control costs. In ACE block clusters, one could also use matching to determine whether individuals that are enumerated by the ACE survey and missed by the census appear on administrative records lists, which would help to assess whether administrative records could be used to reduce census undercoverage. Recommendation: The Census Bureau should modify the plans for AREX 2000 to include a match of the merged administrative records list with the 2000 census households. Costs of this new activity could be controlled through use of field follow-up of unresolved matches on a sample basis. MEASURING THE ACTIVITIES OF LOCAL COMMUNITY GROUPS For the 2000 census, the Census Bureau has increased greatly the participation by various community organizations, which is expected to increase the mail return rate and overall responsiveness to the 2000 census. The result will be lower costs and, possibly, improved data accuracy by reducing the frequency of proxy response and amount of differential undercoverage.

OCR for page 1
DESIGNING THE 2010 CENSUS: First Interim Report Community organizations will vary in their degree of effort and the methods used. Some groups might make greater use of “Be Counted” forms, speeches at public gatherings, or door-to-door interaction, but such variation can complicate evaluation. Therefore, to the extent possible, the Census Bureau should examine ways of collecting information about the activities of these groups. This information could come from activity diaries after the 2000 census is concluded, local census office monitoring of the activities of local groups, or interviews with the staffs of local groups. Without such information, analysis of the 2000 census will be confounded, possibly to an important degree, by the unknown activities of these groups. Recommendation: The Census Bureau should examine various methods for collecting information on the activities of local organizations that are intended to produce a more complete census count. In addition to these four recommendations, the panel proposes a number of other changes for the Census Bureau, which we summarize here: For the master trace sample data base: use a two-stage sample design; oversample ACE blocks, list/enumerate and update/leave households, and households in areas that are hard to enumerate; improve the quality of the information on the number and dates of attempts at enumeration; set priorities for the retention of master trace sample input files; provide for the accessibility and availability of the database; increase the resources for developing the database; and collect sufficient information to support a model of total census error. For AREX 2000: examine whether administrative records could be used as the primary stage of nonresponse follow-up for clearly matched households, leaving field follow-up for the remaining households;

OCR for page 1
DESIGNING THE 2010 CENSUS: First Interim Report obtain approval for acquisition of food stamp and Medicaid files for the AREX 2000 test area; begin legal and legislative processes for greater access to administrative records; increase the resources devoted to carrying out this experiment; examine how to improve race and ethnicity data available in administrative records; and assess the accuracy of the matching and unduplication used in this experiment. With respect to auxiliary census data systems that provide information on census processes: save the census visual images for at least the households in the master trace sample database; and reevaluate the decision to use custom software for the various data systems that monitor and control various aspects of census processes. For the 2000 census: expand the Content Reinterview Survey to measure response bias; evaluate the quality of imputation and editing; collect comprehensive cost data on all components of census processes; collect comprehensive information on the accuracy of ACE matching; and continue systematic observation. Finally, while the 2010 census is well in the future, simple steps taken now could have a very big payoff later (as is the case for many of the above proposals). For the 2010 census and the American Community Survey (ACS) we propose: use the ACS as a census testing platform; conduct a census short form-ACS match study; improve the address list in several ways; determine the feasibility in 2010 of use of a targeted replacement questionnaire;

OCR for page 1
DESIGNING THE 2010 CENSUS: First Interim Report continue work on legislative and legal initiatives concerning use of sampling for nonresponse follow-up, modifications to administrative records systems, and developing greater access to administrative records; form an ACS advisory group; and refine development of a model linking responses to the questions on race and ethnicity used in the 1990 and 2000 censuses. We recognize that implementation of the panel's recommendations and proposals must take place in the brief amount of time available before the 2000 census is in high gear. Although we have indicated some priorities, we understand that it will almost certainly be necessary for the Census Bureau to further set priorities among the recommended and proposed changes.