Analysis of Multiple Respondent Data

Abstract

The nature of family research is such that several family members may be asked to comment on identical items. The purpose of this article is to discuss several approaches for analysis of multiple respondent data applicable to family research. Analysis techniques will focus on one dependent variable. Of special consideration in analysis of multiple respondent data is the violation of statistical assumptions, specifically, the assumption of sphericity. One method of handling this assumption violation will be addressed. An example from a recent family-focused study will be provided to demonstrate differences in significance obtained through use of one-way analysis of variance (ANOVA), repeated measures ANOVA, and Hotellings T 2 .The nature of family research is such that the perceptions, opinions, and behaviors of a number of people within the family are often the focus of research questions. Several family members may be asked to comment on identical items.