Paired-comparison format questionnaires that measures two latent traits suffer from the problem of unidentifiability in the Thurstonian item response model. This study proposes a new method that enables us to identify this model. Specifically, we pro- pose to use every item twice in the questionnaire. In simulation studies, our proposed method recovered the respondent parameters at least as well as the control method, which required analysts to fix some of the parameters to their true values. In the real data analysis, the proposed method was applied to data obtained by two types of psychological scales, one of which contained only positively keyed items, whereas the other contained both positively and negatively keyed items. Item parameters and trait scores estimated using the former data resulted in large posterior standard deviations. In contrast, those estimated with the latter data exhibited better estimation proper- ties. Although it generally does not allow for precise measurement, we show that the proposed method is applicable to empirical analysis. It achieved progress, in that, it negates the need for the unrealistic assumption of fixing parameters to their true values.

In the research area of evaluating the effectiveness of study abroad programs, adopting counterfactual frameworks such as DID, PSM or IV has been considered a valid analytical approach. Previous findings drawn based on these conventional frameworks suggest that even short-term study abroad programs have a significant effect on the improvement of TOEIC scores. However, these studies are often designed to estimate the effects with students’ prior TOEIC scores, and only controlling departmental or school affiliations, while confounding factors, particularly students’ competency such as learning attitudes as well as learning motivations, remain uncontrolled. This study attempts to extract students’ competency from high-dimensional data with a large volume of missing values in student’s test score sheets, using the Alternating Least Squares (ALS) method. Injecting the extracted competency in the subsequent regression analysis en ables us to accurately estimate the causality between the study abroad experience and the observed outcomes. Our analysis result reveals that, unlike findings from earlier studies, once students’ competency is properly controlled, the estimated effect of the study abroad programs becomes negligible with no significance. Therefore, the finding suggests that the causal effect claimed by the previous studies might be due to a bias engendered by students’ self-selection. The result also indicates that datasets readily accessible at any university, such as student test score sheets, could effectively be used for project evaluations within an institution, notably because the confounding factors are properly controlled as suggested by the current study.

A comprehensive survey of child abuse by the Ministry of Health, Labor and Wel- fare of Japan (2019) identified 420 potential risk assessment items. However, using all of these assessment items at a child guidance center would overwhelm their capacity and be thus unrealistic. This study aims to select essential assessment items so that they are usable in actual practice, while maintaining its predictive validity. Here, we used the Random Forests algorithm and predicted classifications to identify the need for child protection by child guidance centers or referral to them from child welfare facili- ties of each municipality. We selected the top 30 items adopted by feature importance in the algorithm from the items evaluated to be easily acquirable in the initial action (50 points or more). The model maintained a moderate level of accuracy 0.783 and AUC-ROC 0.900.