Years have passed since patient safety culture began to be measured. Several measurement instruments have been developed and used in the field, including the Safety Attitudes Questionnaire (SAQ). Validation is an essential step when administering these instruments to health care professionals. The problem is that confirmatory factory analysis (CFA) has mainly been used for the validation, despite the fact that CFA only works well with continuous responses. Yet SAQ and its variants, including the Korean version, use a 5-point Likert scale, which is by definition not a continuous, but a categorical measure. To resolve this conflict, we used item response theory (IRT) graded response model (GRM), an extension of CFA to categorical variables, to revalidate the SAQ-K and unravel the properties of each item and the SAQ-K instrument as a whole. We calculated difficulty and discriminating parameters for all items first. Then, based on the results, we estimated the expected score of each domain along the latent trait continuum, showing how the current SAQ behaves. We also used the itemlevel and domain-level information function, which can enlighten us on how to improve the precision of the current instrument. Most importantly, we obtained IRT-based empirical Bayes estimates of the latent trait level of each person and compared them with the traditional 0 to 100 SAQ arithmetic mean domain score scale. The correlation coefficients were very high, but when plotted we observed a considerable discrepancy between them. This finding led to the validity of the traditional scoring method in question. We expect the results and methodology of this study to bring about active discussions on the use of such safety culture instruments and help future studies on improving patient safety. Despite the successful application of such instruments in gauging patient safety culture in health care, we have to admit that those safety culture instruments, including SAQ-K, should be revalidated for several reasons. In most cases, the critical part of the survey questionnaire validation process has been conducted using confirmatory factor analysis (CFA) [19]. The problem here is that CFA can and should only be used for continuous responses, not for categorical responses such as a 5-point Likert scale, because CFA is basically a linear regression model. Therefore, it cannot appropriately deal with the errors in a measurement model for dichotomous or categorical responses-errors that can neither be normally distributed nor have constant variance. In addition, in the CFA paradigm, the probability of choosing an option for an item can go out of bounds [20]. Simply put, validating a Likert scale-based instrument with CFA is theoretically incorrect. Unfortunately, however, the original SAQ and all its variants, including SAQ-K, measure responses on a 5-point Likert scale (1= disagree strongly, 2= disagree slightly, 3= neutral, 4= agree slightly, 5= agree strongly) and then convert them to a scale from 0 to 100, with 25-point intervals. In all ho...