摘要：The purpose of this study was to validate the test items of science achievement, which were used as a test at Pancasakti Science Competition, in order to obtain enough valid test items with the Rasch model application. Validation model used in this research is Messick validity covering aspects such as (1) content, (2) substantive, (3) structural, (4) external and (5) consequential. To achieve these objectives, this study investigates the quality of the items that include matching items, Person-Items Folder, Person/Item Folder, Information Function Tests, Person Fit Statistic, Collapsed Deviance, Casewise Deviance, Hosmer-Lemeshow, accuracy, sensitivity, specificity, unidimensional, invariance, separation and DIF. The test was given in the form of multiple choice as many as 40 items consisting of 15 items of physics, 10 items of chemistry, and 15 items of biology. The participants were 85 biology students who were given 60 minutes to do the test. Item analysis was conducted by using R 3:12 Program, eRm package version 0.15-6. The study results showed that the test items of science achievement were proven valid by the application of Rasch Model. The test items have met construct validity according to Messick (1996) which includes such aspects: (1) content, (2) substantive, (3) Structural, (4) External and (5) consequential.
关键词：validation; Messick; Rasch model; science achievement test
