Abstract
In this article, the authors examine whether different results occur when items are added to a scale. Because different measures of leader-member exchange (LMX) have included different numbers of items, the authors used the LMX scale. The results, consistent across two studies, support the hypothesis that results based on earlier versions of the LMX measure differ from those of subsequent scales where items were added. The implications of this type of finding for scale development and meta-analysis are discussed. It is suggested that validity as well as reliability be considered when adding new items to scales.
Get full access to this article
View all access options for this article.
