no more than 25% exceeded the range of +/- 2.0. None of the fell outside this range (for both
skewness and kurtosis). Then the Kaiser-Meyer-2ONLQWHVWDQGWKH%DUWOHWW¶VWHVWRIVSKHULFLW\ZDV
applied to make sure that the correlation matrix was appropriate to produce a factor structure which
would not occur just because of chance (Hair et al., 1998; Tabachnick & Fidell, 2007). The Kaiser-
Meyer-Olkin test was .923, well above the required minimum value of .50. The approximate chi-
VTXDUHRIWKH %DUWOHWW¶VWHVW RIVSKHULFLW\ ZDV VLJQLILFDQW 8446.683, df=595, p<.001), indicating a
discoverable factor structure in the data. Therefore, it was concluded that the necessary conditions for
finding a stable factor structure were met.
In stage two, the number of factors to be extracted from the data was determined. The Kaiser 1 rule
was used to determine the maximum number of factors. Seven factors were found with an Eigenvalue
higher than 1, explaining 63 % of the variance. The Eigenvalues were 10.953, 3.418, 2.200, 1.763,
1.294, 1.244, 1.124. In stage 3, the items that best fitted the seven factors were selected. Items had to
have a minimum factor loading of .40 (Ferguson & Cox, 1993) (see Table 7-3).