Comparison of Maximum Likelihood with Conditional Pairwise Likelihood Estimation of Person Parameters in the Rasch Model

Draxler, Clemens; Tutz, Gerhard; Zink, Katharina; Gürer, Can (2016): Comparison of Maximum Likelihood with Conditional Pairwise Likelihood Estimation of Person Parameters in the Rasch Model. In: Communications in Statistics - Simulation and Computation, Vol. 45, No. 6: pp. 2007-2017

Abstract

This paper is concerned with person parameter estimation in the binary Rasch model. The loss of efficiency of a pseudo, quasi, or composite likelihood approach investigated. By means of a Monte Carlo study, two quasi likelihood estimators are compared to two well-established maximum likelihood approaches, one of which being a weighted likelihood procedure. The results show that the observed values of the root mean squared error are practically equivalent for the compared estimators in the case of a sufficiently large number of items.

• Item Type: Journal article
• Form of publication: Publisher's Version
• Keywords: Pairwise conditional maximum likelihood estimator; Person parameter; Rasch model
• Faculties: Mathematics, Computer Science and Statistics > Statistics > Chairs/Working Groups > Seminar for Applied Stochastic
• Subjects: 500 Science > 510 Mathematics
• ISSN: 1532-4141; 0361-0918
• Language: English