Research Note: Some Problems with Measurement of Macro-organizational Structure

Publisher Website
Google Scholar
Abstract
Problems associated with the use of Aston psychometrically based measures are evalu ated in the light of experience gained in and the findings of an empirical study of 45 electrical engineering companies in the UK in which the Aston methodology was used. It is shown that (a) the unidimensionality of multi-item measures must be clearly established if loss of information is to be avoided, (b) scales constructed by aggregation of a number of subscales suggested by factor analysis should not be given general labels beyond the description of subscales included in the final scale, and (c) abbreviated scales based on the original study may only reflect sample-specific relationships and may not be used as proxies of original scales in the study of other samples. The objectivity of factor analysis is also addressed.