Statistics from Altmetric.com
If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.
Factor analysis is a broad term that refers to a set of statistical methods used to detect underlying patterns in the relationships among a number of observed variables. Its origins were in the large scale studies defining the dimensions of intelligence pioneered by Thurstone.1 ,2 Factor analysis can appear complicated to the general reader but the main principle is relatively straightforward: what it aims to do is identify whether the correlations between a set of multiple observed variables are explicable or can be summarised in terms of a smaller number of underlying, latent, unobserved variables, also called factors. It is useful to have a basic understanding of the specific techniques when reading articles about factor analysis. There are two main approaches: exploratory factor analysis and confirmatory factor analysis.
EXPLORATORY FACTOR ANALYSIS
Exploratory factor analysis is used for the preliminary investigation of a set of observed variables, especially where there are multiple variables, such as each question on the Hopkins Symptom Checklist.3 In a population or sample where a diverse range of symptoms is under study, as is often the case in mental health research, the advantage of this method is that it makes no a priori assumption about the composition of underlying latent variables or factors. The applications of exploratory factor analysis are wide ranging:
1. Data reduction when multiple (over 25) variables have been measured, providing a parsimonious description of the data.
2. Classification of symptoms into clinically meaningful concepts especially when symptoms are many and diverse such as medically unexplained symptoms, symptoms to describe stress, multiple health beliefs and behaviours.
3. Definition of subscales of new measures of psychological functioning—a par exemplar is the validation of the well known General Health Questionnaire4 which was shortened to 12 items after identifying which symptoms in the 60-item version were …
Competing interests: None declared.