ABSTRACT
Factor analysis is a technique that is widely used in psychometrics. It can be applied to any set of data where the number of subjects exceeds the number of variables. The variables involved in the use of factor analysis are usually item scores or subtest scores. The analysis will provide a set of results that give an indication of the underlying relationships between the items or subtests. It will tell us which set of items or subtests go together, and which stand apart. Factor analysis identifies what are called ‘factors’ in the data. These factors are underlying hypothetical constructs that often can be used to explain the data. Factor analytic computer programs will give an estimate of how many such factors there may be in a set of data, and of how these factors relate to the items or subtests. By selecting items that relate to particular factors, we are able to put together subtests of the construct that the factor represents. Factor analytic computer programs also give eigenvalues, statistics that are able to represent the relative importance of a factor, and can give estimates of the scores of individuals on any of the factors identified.
