PA GE 20
80 IPRC 2022/BOR A- Psychometry 01
Test Validity Using Multiple Facet Rasch Models on Leaderless Group Discussion for Employee Performance Evaluation
Dian Din Astuti1, Gilman Hisbun Islam Zein2
[email protected]1, [email protected]2
Universitas Mercu Buana1, Kementerian Hukum dan HAM2 Indonesia
ABSTRACT
Content validity is useful for determining whether test items are compatible with the capabilities and materials being measured. This validity is done by testing the feasibility of the instrument through panel discussions by experts who are competent in their fields. In this study, content validity was applied to the leaderless group discussion simulation. The purpose of this study is to utilize the Many Facet Rasch (MFRM) model in evaluating the validity of the LGD simulation. A work-sample evaluation known as LGD involves a small group of 5-7 people participating in a problem-solving simulation for 45 to 60 minutes with no designated leader. The validity of the LGD simulation will be evaluated using the Many Facet Rasch (MFRM) model in this study. There are 3 validators judment who assess the LGD simulation. The validation was carried out by assigning scores between 1-4 to each of the seven aspects- situation, mandatory, actor, role, task, instruction, systematics, and writing format. This study adopted the Minifacets software, the MFRM computer statistics program to define many aspects of content simulation, assessment dimensions to analyze content simulation, rater severity, interrater reliability, dimensional difficulty and rating scale. The results showed that this rasch scored exhibited unidimensionality. Furthermore, discrepancies in ratings between expert raters were also identified and modeled by the many-facet Rasch model. The implications for applying the many-facet Rasch model in validation LGD simulation at the tertiary level were discussed.
Keywords: leaderless group discussion, many-facet Rasch model, personnel assessment