Second Language Testing: Assessing the Psychometric Properties Causes of Second Language Writing Anxiety Scale (SLCWAS) Using Rasch Model Analysis

Abstract

Purpose. The aim was to develop and validate (SLCWAS)so as to provide support for its application among primary school students. It was postulated the following: (1) the (SLCWAS) was developed for application to primary school students in a Saudi Arabian cultural context; and (2) the (SLCWAS) has appropriate psychometric properties. Methods and Procedure. 190 primary school students were included in this study. CFA was conducted for testing item-factor structure of the scale. The fit indices were found to be Chi square = 32.16 (p < .001), degree of freedom = 190 (χ2 = 32.16; df = 190, χ2/df = 3.24), root mean square error of approximation (RMSEA) = .07 (p < .05) standardized root mean- square residual (SRMR) = .05, comparative fit index (CFI) = .93, non-normed fit index (NNFI) = .96, goodness of fit index (GFI) = .96, and adjusted goodness of fit index (AGFI) = .95. These outcomes prove that SLCWAS is a valid and reliable measure. Results. Findings indicate that the empirical ICC curves fit well with the expected ICC curves for all the items. the levels of SLCWAS in primary school students are widely distributed. Higher Logits scores indicated that students have higher levels of SLCWAS. Males and females had the same location in answering SLCWAS items and that there was no DIF for the SLCWAS items with respect to gender. Conclusions: SLCWAS was validated in the Rasch analysis with a sample of primary school students. The preliminary reliability investigation revealed a very high internal consistency for the scale.