Variance is usually measured using the standard deviation. It was decidedto examine the standard deviation for the rescaled 5- and 7-point datacompared to the 10-point data. If the data are not dependent on the choiceof scale format, then once the data are rescaled to a score out of 10, allthree scale formats should exhibit the same standard deviation.Looking across the three scale formats in Table 5, the differences instandard deviation for the individual scale items are quite small, of theorder of zero to 0.2. It appears that scale format does not have a markedinfluence on variation about the mean. To clarify this formally, it wasdecided to test the overall average score for each format using the Levenetest for homogeneity of variance. The test was not significant (Levene statistic = 0.21; df 2,732; p = 0.81). Scale format therefore did not have anassociation with variance in this experiment.An examination of the standard deviation tells us about the dispersionof scores about the mean for a particular questionnaire item or variable. Itdoes not, however, tell us about how individual respondents have used thescale. For example, if we ask respondents to answer eight questions usinga 1 to 5 scale, how many different scale points will they use? Obviouslythe precise answer depends on what the questions pertain to. However,researchers generally want respondents to use more response options overa series of questions, rather than fewer. The reason is that this indicatesthose questions are generating more discrimination in responses.Therefore, as a supplementary analysis, I also examined how manydifferent scale points respondents actually used, and whether this differedaccording to the scale format. I found that, over the eight questions, theaverage number of scale points used for the 5-point scale was 2.9, for the7-point scale it was 3.6 and for the 10-point scale respondents used 4.0different scale points on average. An analysis of variance confirmed thatthere was a statistically significant difference between the scale formats interms of the number of scale points used by respondents (F = 54; df 2,732;p < 0.01). Therefore, there is evidence that respondents do use more scalepoints when given a scale format with more response options.