<![CDATA[Item Response Theory (IRT) is an approach that can be used to analyze the responses/answers given by respondents to a measurement instrument. Unlike the classical test theory (CTT) approach that measures the latent traits of respondents based on the total score, IRT measures latent traits based on the responses given by respondents to each item. Another difference between CTT and IRT is that the CTT approach is theory-based while IRT is model-based. The purpose of this study is to apply Item Response Theory (IRT) to analyze the item responses of the employees of the Kementerian Desa, Pembangunan Daerah Tertinggal, dan Transmigrasi/KDPDTTT (Ministry of Village, Development of Disadvantaged Regions and Transmigration) on the items in the instrument/questionnaire which was administered to the employees, in order to understand their attitudes towards the changes management and organizational culture in the KDPDTT. We applied item response theory to analyze the answers provided by the respondents to the items. These responses were modelled based on the dichotomous IRT models, namely the 1PL, 2PL, and 3PL models. The IRT modeling in this study is based on the results of a survey conducted by KDPDTTT in 2020. Among the three models, the 2PL model is the most suitable for our item responses data because it has the smallest AIC, BIC, and G2. Based on the 2PL model, the probability for endorsing the items related to the change management ranges from 0.68 to 0.95. Meanwhile, the probability for endorsing items related to organizational culture ranges from 0.87 to 0.98. Although each item in the instrument has three response options, namely "disagree", "undecided (neutral)", and "agree", we will treat them as dichotomous. We classify the "undecided" answer as the "disagree" category. The reason is that many Indonesian people usually find it hard to say "disagree" for a question related to the evaluation of a policy. They tend to feel safer by choosing “undecided”. Therefore, the item responses that have been analyzed in our study are dichotomous, that is, "agree" or "disagree". The novelty of this research is utilizing a non-classical approach, namely IRT, which has several advantages over Classical Test Theory (CTT), including that item characteristics do not depend on respondent characteristics, and vice versa.]]>
