Individual response spread in self-report scales: personality correlations and consequences

We consider the phenomenon of individual differences in the use of questionnaire scales and examine some of its consequences. Results from two illustrative studies on farmers and consultant doctors are used to demonstrate that individual standard deviation of response option usage is a consistent trait which is significantly correlated with the personality dimension of conscientiousness. A mathematical model of individual response spread is also devised and it is shown that significant spurious correlations between responses to independent items can arise. This model is extended by estimating individual response thresholds from our two illustrative data sets; numerical simulation using these thresholds confirms the occurrence of spurious correlations. The distribution of correlation coefficients r is also very different from the standard form used for estimating levels of significance. There are widespread consequences of these observations for standard multivariate methods of analysing self-report data.