Higher‐order factor analysis of an instrument with dichotomous data

Abstract

This article reports the use of higher-order factor analysis to examine the underlying dimensions of an instrument designed to measure community acceptance of nurse practitioners/physician's assistants. The instrument consisted of both dichotomous and Likert scale items. Use of factor analysis with dichotomous data is controversial. Higher-order factor analysis provides a potential solution to this dilemma. Following initial factor analysis using maximum likelihood extraction with oblique rotation, the factor correlation matrix was factored to obtain second order factors. The second order factors were interpreted using the factor pattern matrix and examining correlations of individual survey items with the second order factors. This procedure provides additional factorial validity of the underlying uni- and multidimensional concepts related to acceptance of NPs and PAs in rural settings: knowledge, competence, access, and trust.

An introduction to the Rasch measurement model: An example using the Hospital Anxiety and Depression Scale (HADS)

“…This idea is not new, and both classical and modern psychometric theories have developed approaches to test the validity of such scales. In classical test theory a second‐order factor analytic approach has been used to confirm higher‐order dimensions, although its utility with just two or three factors is unclear (Baldwin et al , 2005). In modern test theory, most recently, multidimensional Rasch models have been proposed, which also test for higher‐order measurement constructed from valid subscales, although this approach has yet to gain widespread use (Briggs & Wilson, 2003).…”

An assessment method comparison study of clinician adherence to cognitive processing therapy for posttraumatic stress disorder

“…Given several of the variables were highly correlated, this suggested that certain factors might measure aspects of common underlying dimensions. As summarized by Baldwin et al (2005), the use of factor analysis with dichotomous variables is controversial, but many statistical experts agree on its use, with caution, and many studies have used techniques to apply factor analysis to dichotomous data (e.g., Banos & Franklin, 2002;Bartholomew, 1980;Gorsuch, 1983;Mundform, Bradley & Whiteside, 1993;Tabachnick & Fidell, 2001;Tomas-Sabado, & Gomez-Benito, 2005). Specifically, given the aim of this research question was to examine components (factors) among dichotomous variables in a measure, in order to validate underlying constructs, the use of factor analysis was justified.…”

Everyday pain, analgesic beliefs and analgesicbehaviours in Europe and Russia: An epidemiologicalsurvey and analysis

“…Тези методи от по-висок порядък подсилват надеждността на факторната структура при наличие на противоречиви данни и включват извършването на два факторни анализа. Първоначалният се състои от противоречиви отговори за определяне на факторите от по-висок порядък, а вторият се състои от факторите от по-нисък порядък за установяване на фактори, които са от по-висок порядък и са доминиращи [13].…”