Person-fit methodology is a promising technique for identifying subjects
whose test scores have questionable validity. Less is known however about
this technique?s ability to predict survey participation longitudinally. This
study presents theory-derived expectations related to social desirability,
the tendency for extreme responding and traitedness for specific deviating
answer patterns and an expected consistence of person-fit scores across 27
personality scales. Data from 5,114 subjects (Amelang, 1997) were reanalysed
with a polytomous-Rasch model to estimate scale scores and von Davier and
Molenaar?s (2003) person-fit statistics. The person-fit statistics of the 27
scales were examined together with the 27 person parameter scores in one
common factor analysis. The person-fit scores served as indicators of the
latent factor ?scalability? while the person-parameter scores were considered
to index the bias introduced by social desirability. The sign of factor
loadings showed consistency and validity of the tendency for social
desirability and extreme responding. Moreover, the personfit- based subject
classification derived from the baseline data was able to predict subjects?
participation at a 8,5-year follow-up. However, the nature of those
associations was contrary to our predictions. The discussion addresses
explanations and practical implications, but also the limitations pertaining
to the identification and interpretation of person-fit scores.
Person-fit statistics, response sets and survey participation in a population-based cohort study
