 Is there a “Socratic Effect†in Nonexperimental Panel Studies?Wolfgang Jagodzinski,
M. KÃœHNEL Steffen and
Peter Schmidt
Sociological Methods & Research, 1987, vol. 15, issue 3, 259-302 Abstract: It has often been observed in experimental studies that the reliability of items increases if the same questions are asked of the same respondents more than once. This phenomenon, called the “Socratic effect,†also occurs in nonexperimental, short-wave panel studies. In the first section of this article a number of hypotheses presumed to underlie the “Socratic effect†are presented. It is argued that a distinction must be made between consistency processes at the structural level (latent attitudes) and the observational level (respondent behavior). Given this distinction, the hypotheses are tested within a LISREL framework that takes this differentiation into account. The hypotheses are then evaluated using four items to measure respondents' attitudes toward guestworkers in West Germany. By and large the central hypotheses are confirmed. It is also shown that two different models can be fit to the observed data equally well, and therefore a nonstatistical criterion has to be invoked to decide which model to use as the basic model for describing the stability and reliability of the attitude. Date: 1987 Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:sae:somere:v:15:y:1987:i:3:p:259-302 DOI: 10.1177/0049124187015003004 Access Statistics for this article More articles in Sociological Methods & Research |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.