5. After item reduction analyses the first full version and final short version of the instrument were tested on the non-imputed dataset (N = 204). Listwise deletion of missing data on the basis of the 18 items in the short version resulted in N = 221. We re-ran the final short version on this sample.
Lisrel 9.1 Download Full 531
The final short version consisted of 18 items with three items for each subscale (table 1). Item reduction was possible without loss of model fit; in fact, its overall fit was better than the full version. Due to a decrease in the number of estimated parameters, the Normal Theory Weighted Least Square χ2 significantly decreased to 530.427. RMSEA still indicated reasonable fit. The value of IFI improved to 0.967, indicating that the specified relations between variables were well supported by the data. The SRMR index decreased to 0.0669, still considerably below the cut-off point of 0.08, indicating good global fit. The final short model on imputed data resulted in comparable factor loadings. A re-run of the full model and item reduction analysis on the non-imputed dataset (N = 217) resulted in somewhat less favourable but still acceptable fit indices and comparable factor loadings.
This study uses survey data collected from active female entrepreneurs across Japan. The questionnaire items of this survey were adopted from the previous literature. The original English version was translated into Japanese by the authors. We conducted a set of two pilot tests with a group of ten female entrepreneurs between June and July 2015 to check the content and relevance of the items before emailing a packet that included our questionnaires together with a cover letter to the population of interest. Based on the feedback received from the pilot group, we carefully amended the questionnaire to clarify the wording of ambiguous questions prior to survey distribution and data collection. 2ff7e9595c