Reliability and validity analysis and Mokken model of New General Self-Efficacy Scale-Short Form (NGSES-SF)

Objective: To simplify the New General Self-Efficacy Scale and examine its reliability and validity among mainland Chinese residents. Methods: In this study, a total of 11,031 residents in 120 cities across China were selected to participate in a questionnaire survey using a multi-stage stratified whole-group sampling method. The data were randomly divided into two parts. The first batch of data was used to simplify the scale using factor loading, correlation coefficient and Cronbach Alpha in classical test theory (CTT), and Mokken model in item response theory (IRT). And then the second batch of data was used to test the reliability and validity of the simplified version of the new general self-efficacy scale and the Mokken model hypothesis. Results: Compared with the 8-item scale, the 3-item New General Self-Efficacy Short Form (an individual's subjective expectation of his or her ability to successfully achieve goals in a given environment, which is an individual's evaluation of his or her ability and reflects his or her level of self-confidence) showed great reliability and validity. Conclusions: Tested by the Mokken model in classical test theory (CTT) and item response theory (IRT), the simplified version of the new general self-efficacy scale has good reliability and validity, which can be used in relevant research and practice.