Analysis of variance with ipsative measures.

Abstract

Measures with more than 1 score per participant, when the total for each participant equals the same constant, are said to be ipsative. Ipsativity occurs when data are percentages, with each participant's total equal to 100%, or when data are ranks, with each participant's total equal to the sum of the ranks. When ipsative measures are analyzed with analysis of variance (ANOVA), certain sums of squares equal 0, and the average intercorrelation among measures is negative. These characteristics of ipsativity may result in violations of ANOVA assumptions, producing an inflated Type I error rate and affecting power. The purpose of this Monte Carlo study was to empirically examine the extent to which ANOVA is affected by ipsative data. Findings indicated that, with few exceptions, ANOVA worked quite well with ipsative data. Not only were Type I error rates well preserved, but power was nearly equivalent to that with nonipsative data.

What Do We Assess when We Assess a Big 5 Trait? A Content Analysis of the Affective, Behavioral, and Cognitive Processes Represented in Big 5 Personality Inventories

“…We avoid reliance on and emphasis of multivariate tests due to the nonnormality often associated with ipsative data (Greer & Dunlap, 1997). However, our multivariate tests nonetheless always revealed statistical signifi cance.…”

Manipulating cues in mind wandering: Verbal cues affect the frequency and the temporal focus of mind wandering

“…The analysis was carried out on participants who reported at least 3 thoughts, and the epsilon correction for the degrees of freedom suggested by Greer and Dunlap (1997) was used to take into account that, for each participant, the sum of the values (proportion) across the conditions of the temporal focus factor is constant, namely 1. These data suggest that the exposure to verbal cues affected the temporal orientation of MW.…”

Hypergravity within a critical period impacts on the maturation of somatosensory cortical maps and their potential for use-dependent plasticity in the adult

“…Repeated-measures ANOVA was used to compare ipsative data (i.e., a set of responses that always sums to the same total: 100%) consisting of the proportions of neuronal responses to nail displacement falling within the defined categories (cf. Greer and Dunlap 1997). Repeated-measures ANOVA was also used to compare forepaw prints collected over time or under different gravity conditions in the same animals.…”

“…The proportions of neuronal responses to nail displacement are ipsative data, i.e., a given set of responses always sums to the same total (100%). We used repeated-measures ANOVA to compare the proportions of responses obtained in HG and NG rats, a procedure that takes into account the inter-individual variability within each experimental group (Greer and Dunlap 1997;Shaffer 1981).…”