Measurement Errors in Surveys (Wiley Series in Probability and Statistics) - Hardcover

Über die Autorin bzw. den Autor

About the editors PAUL P. BIEMER has been Principal Scientist at Research Triangle Institute since 1991. His prior experience includes: Head of the Department of Experimental Statistics and Director of the University Statistics Center at New Mexico State University (1986?91) and administrator/researcher at the U.S. Bureau of the Census (1978?86).

ROBERT M. GROVES is presently Associate Director for Statistical Design, Methodology, and Standards, Department of Commerce, U.S. Bureau of the Census. He has taught at the University of Michigan since 1975 and is author of several books, the most recent of which is Survey Errors and Survey Costs (Wiley, 1989).

LARS E. LYBERG is Head of the Secretariat for International Research at Statistics Sweden, Stockholm, Sweden, where he has worked since 1968. He is also Chief Editor of the Journal of Official Statistics. Dr. Lyberg is President-Elect (1993) of the International Association of Survey Statisticians.

NANCY A. MATHIOWETZ is Special Assistant Director for Statistical Design, Methodology, and Standards at the U.S. Bureau of the Census. Prior to joining the Census Bureau in 1990, Dr. Mathiowetz worked at Westat and the Agency for Health Care Policy and Research.

SEYMOUR SUDMAN is the Walter A. Stellner Professor of Marketing and Deputy Director of the Survey Research Laboratory at the University of Illinois, Urbana-Champaign. He is past President of the American Association for Public Opinion Research.

Aus dem Klappentext

The widespread use of surveys in fields as diverse as sociology, psychology, statistics, communication science, business, and economics makes the potential effects of measurement error as far-reaching as survey results themselves. Measurement Errors in Surveys documents the current state of the field, reports new research findings, and promotes interdisciplinary exchanges in modeling, assessing, and reducing measurement errors in surveys. The book begins with an in-depth look at current issues in questionnaire design. Choice and presentation order of both questions and response alternatives are examined in detail. This section also compares the effects of questionnaire mode on cognitively designed questions. The results of research on the effects of context and question wording are probed as well. Special consideration is given to measurement error in business surveys. In studying respondents and responses, contributors consider recall error; differences in self vs. proxy responses; alternative approaches to obtaining personal history data; and item count techniques as a method of indirect questioning. Another section on interviewers and alternate means of data collection discusses the reduction of interviewer-related error through training; design and analysis of reinterview; and more. A case study examines the review of errors of direct observation in crop yield surveys. Contributors also outline factors affecting respondent-interviewer interaction?such as the role of conversation, interview style, interviewer behavior, and response behavior. The second part of Measurement Errors in Surveys develops a fundamental approach to measurement errors. Both bottom-up and top-down versions of total survey error are presented. Modeling measurement errors and their effects on estimation and data analysis are considered and a mixed model for analyzing measurement errors for dichotomous variables demonstrated. The book ends with several chapters on data analysis. Discussions center on measurement errors in cross-national surveys and regression estimation in the presence of response error. Chi-squared tests for complex survey data are offered. A final study examines the effects of measurement error on event history analysis.