
Health survey data are an important and efficient source of information for policy makers and administrators. But caution is warranted: surveys do not show cause-and-effect relations, and they are no substitute for randomized controlled experimentation in predicting behavior. The variety of surveys-governmental and private-is increasing, and both methodology employed and interpretation of results can be improved in suggested ways.
Author(s): Stephen E. Fienberg; Elizabeth F. Loftus; Judith M. Tanur
Volume 63, Issue 3
(pages 598–614)
Published in 1985