Algorithms For Parameter Estimation In The Rasch Model
Door: Ruitenburg, J. van | 01-01-2005 We compare several methods to find the parameters of the Rasch Model, well-known in psychometrics. This search entails finding the maximum of the concave conditional log-likelihood function.We focus on iterative minorization and interval algorithms, which update one parameter per iteration, and are guaranteed to converge. We present six algorithms, an acceleration method, and perform a small simulation
study with them. This study shows that the convergence time of the algorithms depends on the shape of the likelihood function.
Kunnen we je helpen?
Stel je vraag via onze kanalen of kijk in de veelgestelde vragen.
Voor scholen: Vergeet niet om het brinnummer bij de hand te hebben en/of in de mail te vermelden, zodat we jouw vraag sneller kunnen behandelen!