Cross-Cultural Stability of the Optimal Categorization of a Self-Efficacy Scale: A Rasch Analysis

Abstract

The main purpose of this study was to apply the Rasch analysis to determine the optimal categorization of the Korean version of a self-efficacy scale and compare it with its English version. To adapt the scale to the Korean population, the subscales' Glide Pull-ups and Glide Presses from its English version were replaced by the Standing Broad Jump and the 50-m Dash, and the modified scale was translated into Korean. The scale was then applied to 627 Korean children (314 boys and 313 girls). The data analyses started by collapsing the original 5 adjacent categories into 2, 3, and 4 categories. A total of 14 data sets were derived. Each of these data sets, including the original one, was analyzed using the Rasch rating model, and a set of Rasch model -- data fit, category, and separation statistics and parameter estimates, as well as three conventional statistics, were computed and compared. We found that, instead of the 5-category construct designed, the optimal order of category meanings of the scale in respondents' perceptions was a 3-category construct. This confirmed a similar finding in the English version of the scale, and the optimal categorization was maintained in the Korean version. The Rasch analysis was thus demonstrated as a useful means in determining the categorization equivalence of different versions of a scale in cross-cultural studies. We also found that the Rasch threshold estimates and separation statistics continuously played critical roles in determining the optimal categorization, whereas other Rasch and conventional statistics, including the commonly used coefficient alpha, were not very helpful.