Premium
Handling of missing values in path models for opinions or attitudes
Author(s) -
MAASSEN GERALD H.
Publication year - 1996
Publication title -
european journal of social psychology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.609
H-Index - 111
eISSN - 1099-0992
pISSN - 0046-2772
DOI - 10.1002/(sici)1099-0992(199601)26:1<1::aid-ejsp728>3.0.co;2-l
Subject(s) - path analysis (statistics) , missing data , imputation (statistics) , psychology , path (computing) , selection (genetic algorithm) , population , variable (mathematics) , variables , sample (material) , social psychology , econometrics , statistics , computer science , mathematics , artificial intelligence , sociology , mathematical analysis , chemistry , demography , chromatography , programming language
In this article we show, by means of a practical example of a path model to explain opinions or attitudes and using a dataset well‐known in The Netherlands, that the intercorrelations of the variables may be highly dependent on the number of variables and the corresponding number of missing data involved. As a consequence, differences could arise in the results of multiple regressions and path analyses. (The role of a suppressant variable in a path model will be touched on in passing.) Subsequently, the way that the character of the sample can change when a more rigid listwise selection of cases is applied is demonstrated. Since a practical example is involved, substantive arguments may be used for choosing a strategy of handling of the missing values. In our view, with reference to path models of opinions or attitudes, these arguments lead not to the use of one of the current imputation techniques or sophisticated methods to estimate the population values of the model parameters, but to what may be called a differentiated listwise selection.