leadership and motivation in hospitality

regarded as indicative of the existence of multivariate non-normality (Bentler
2005 cited in Byrne 2010: 104). Where an optimal model specification
demonstrates a multivariate kurtosis C.R. value greater than 5, the model is re-
estimated, following the procedure described by Byrne (2010: 3 29 - 352), using
AMOS’s bootstrap procedure which generates confidence intervals for each
parameter. In this way parameters are checked for their robustness in the light
of multivariate non-normality as required. Critical ratio estimates for multivariate
normality, and bootstrapped estimates where appropriate, are reported in
Appendix IV.