Monroe G. Sirken

Sampling rare and elusive populations.

The sampling of rare and elusive populations is difficult because the costs of locating such populations are substantial and can exceed actual interviewing costs. There are efficient probability methods that have been developed recently that reduce these costs. If the special populations are geographically clustered, efficient sampling involves the rapid location of segments in which no members of the special population are located with the use of Census data, telephone screening, or incomplete lists. Populations that are not geographicaily clustered can be located by network sampling and use of large previously gathered samples. Characteristics of mobile populations such as the homeless can be estimated by capture-recapture methods.

Household Surveys with Multiplicity

Abstract In the household survey with multiplicity, sample households report information about their own residents as well as about other persons who live elsewhere, such as relatives or neighbors, as specified by a multiplicity rule adopted in the survey. Although sampling errors for the multiplicity survey are not necessarily smaller than those for the conventional survey in which sample households report for their own residents only, in most instances it should be feasible to assure a substantial reduction in sampling error by selecting appropriate multiplicity rules. Using alternative statistical models, it is demonstrated that under specified conditions, sampling errors for the multiplicity survey are necessarily smaller than those for the conventional survey, and the results give insight regarding the factors contributing to the efficiency of the multiplicity survey.

Stratified Sample Surveys with Multiplicity

Abstract Sampling variances are compared for the conventional and for two classes of multiplicity estimators based on stratified sample surveys. The conventional estimator uniquely links every individual to a single enumeration source—its index source. The multiplicity estimators link every individual to its index source, and possibly to other sources as well. One multiplicity estimator permits an individual to be linked to sources in one stratum only; the other multiplicity estimator permits an individual to be linked to any sources. None of the three estimators is necessarily more reliable than the others.

Laboratory-based Research on the Cognitive Aspects of Survey Methodology: The Goals and Methods of the National Center for Health Statistics Study

The National Center for Health Statistics is embarked on a major project to combine the respective strengths of cognitive psychologists and survey researchers in a common effort to improve the design of survey questionnaires. This methodological research is conducted within the framework of the National Health Interview Survey, the nations main source of information on the health of civilians. Better quality of such information--from recall to response rates--can aid both scientific inquiry and public policy.

Multiplicity Estimation of Proportions Based on Ratios of Random Variables

Abstract This article applies the counting rule strategy to the problem of estimating the proportion of population elements with a specified characteristic based on a sample of enumeration units. The distribution of population elements among the enumeration units is a function of the counting rule which specifies the conditions for linking population elements to enumeration units. The counting rule strategy involves the selection of the counting rule which minimizes the variance of the estimate for fixed cost. The strategy is illustrated by a problem which involves estimating the proportion of incorrect statistical statements in the text of a report based on a sample of lines of text.

Bias Due to Non-Availability in Sampling Surveys

Abstract A technique is presented for the treatment of errors introduced into sampling surveys due to the non-availability of respondents. The expected cost and variance of the sample survey are expressed as functions of sample size and of the number of call-backs made on the non-availables. A method is then presented which optimizes precision for a given cost by playing sampling error against the bias resulting from non-availables. * Research under the sponsorship of the Office of Naval Research. Presented to the Institute of Mathematical Statistics, November 27, 1948.

Preparing Statisticians for Careers in the Federal Government: Report of the ASA Section on Statistical Education Committee on Training of Statisticians for Government

Abstract A profile of the federal statistician is provided, out-lining the variety of fields and methodologies involved. Office of Personnel Management (OPM) requirements are discussed and recommendations for graduate and undergraduate training are outlined. The report is directed to (a) colleges and universities as they design their statistical curricula, (b) prospective federal statistical employees as a counseling tool, and (c) OPM as that agency undertakes the review and revision of the qualification standards applied to Federal statisticians.

Residence Histories and Exposure Residences for the United States Population

Abstract Residence histories were collected in a supplement to the Current Population Survey. By restricting query to places rather than individual dwellings, complete histories were obtainable for ninety per cent of the sample. The concept of “exposure residence” is suggested as one technique for summarizing residence histories. Exposure residence data for the United States adult population are presented, and are used to support the hypothesis of stage patterning of rural-urban migration.

Design of household sample surveys to test death registration completeness

This paper studies the design effect of counting rules, for linking deaths to housing units where they are enumerated in the survey, on the sampling variance of dual system and single system estimators of death registration completeness. It investigates estimators based on conventional rules that uniquely link each death to a single housing unit as well as estimators based on multiplicity rules which permit deaths to be linked to more than one housing unit. Sampling variance formulas are derived containing parameters that reflect the efficiency of the counting rule. Estimates of these parameters for different counting rules are compared utilizing information that was collected in a mortality survey experiment. Finally, the design of a national death registration test is considered and the sample size implications of different counting rules arc compared.

Establishment Surveys With Population Survey–Generated Sampling Frames†

When stand-alone sampling frames list all establishments and size measures, the Hansen–Hurwitz (HH) pps estimator is generally used to estimate the volume of transactions between establishments and households. The network sampling (NS) version of the HH estimator depends on a population-survey-generated establishment frame, which lists establishments that have transactions with households in a population sample survey and the number of transactions that establishments have with survey households. The NS estimator is a competitor of the HH estimator whenever stand-alone frames of good quality are unavailable and, as this article indicates, the NS estimator may be competitive with the HH estimator when stand-alone and population-survey-generated frames are flawless. Keywords: establishment surveys; sampling frames; network sampling; Hansen–Hurwitz estimator