PATH-ANALYSIS WITH PARTIAL ASSOCIATION MEASURES

This paper discusses the use of partial association measures for carry ing out path analyses on categorical data. The measures considered are essentially PRE (proportion of reduction in error of prediction) meas ures for nominal variables and concordance-discordance indices for ord inal ones. These measures provide a natural way to evaluate the streng th of the path linking a non-measurable response variable to one of se veral categorical explanatory factors. Concerning the decomposition of raw association into direct and indirect effects, it is shown, howeve r, that they do not share the properties of conventional path coeffici ents for measurable variables. Especially purely nominal association m easures need to be interpreted with care. The scope of the partial mea sures for path analysis is illustrated through a study of the relation ships between the educational styles experienced by swiss adolescents and their self-esteem.