Abstract
The sample survey, involving the use of specially developed questionnaires and instruments, is an important source of data regarding individual experiences and social-psychological characteristics for use in social indicator research. Variable errors of measurement are often given only cursory attention in presentations of survey sampling and social indicator theory and in the analysis of such data. These errors may, however, result in reduced precision of estimates and may affect statistical inferences drawn from the data. Some procedures for assessing the extent of variable measurement error are described and examples of their use in evaluating a survey instrument and data collected are discussed.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Author information
Authors and Affiliations
Additional information
William E. Pollard is an Assistant Professor of Psychiatry at Northwestern University. He was Research Associate on the Sickness Impact Profile Project from October 1972 to August 1975. Ruth A. Bobbitt is Research Professor of Health Services and Methodologist on the Sickness Impact Profile Project, and Marilyn Bergner is Associate Professor of Health Services and Co-Principal Investigator on the Sickness Impact Profile Project, University of Washington, Seattle, Washington.
This investigation was supported by the HMO Service of the Health Services and Mental Health Administration, Contract No. HSM 110-72-420.
Rights and permissions
About this article
Cite this article
Pollard, W.E., Bobbitt, R.A. & Bergner, M. Examination of variable errors of measurement in a survey-based social indicator. Social Indicators Research 5, 279–301 (1978). https://doi.org/10.1007/BF00352935
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF00352935