FACTOR-ANALYSES OF POOLED HAND QUESTIONNAIRE DATA ARE OF QUESTIONABLE VALUE

A number of researches have used factor analyses and principal components analyses on handedness questionnaire data in order to learn something about handedness. However, these researchers have analyzed pooled data from righthanders and lefthanders. The practice of pooling groups that are known in advance to be heterogeneous is highly questionable because it is not possible to disentangle the sources of variance that are contributed by within group differences from those that arise from between group differences. The factor structure and item loadings that result from pooled data are misleading and cannot inform meaningfully about the relation of hand preference to handedness. Similar problems can be anticipated in other neuropsychological applications of factor analysis, where data from heterogeneous groups is pooled.