D-Optimal Sequential Sampling Designs for Item Response Theory Models
Author:
- 1 March 1994
- journal article
- Published by American Educational Research Association (AERA) in Journal of Educational Statistics
- Vol. 19 (1) , 43-56
Abstract
The selection of optimal designs in IRT models encounters at least two problems. The first problem is that Fisher’s information matrix is generally not independent of the values of the IRT parameters, and the second problem is that the design points are unknown parameters and have to be estimated together with the other parameters. In this study, these two problems are taken care of by a sequential design procedure. This procedure is a modification of a D-optimality procedure proposed by Wynn (1970) . The results show that this algorithm leads to consistent estimates and that errors in selecting the abilities generally do not affect optimality very much.Keywords
This publication has 21 references indexed in Scilit:
- Nonlinear Experiments: Optimal Design and Inference Based on LikelihoodJournal of the American Statistical Association, 1993
- On the Efficiency of IRT Models When Applied to Different Sampling DesignsApplied Psychological Measurement, 1991
- Sequential maximum likelihood estimation with applications to logistic regression in case-control studiesJournal of Statistical Planning and Inference, 1989
- Standard Errors of Item Parameter Estimates in Incomplete DesignsApplied Psychological Measurement, 1988
- Inference and sequential designBiometrika, 1985
- Efficient Sequential Designs with Binary DataJournal of the American Statistical Association, 1985
- An Investigation of Methods for Reducing Sampling Error in Certain IRT ProceduresApplied Psychological Measurement, 1984
- A sequentially constructed design for estimating a nonlinear parametric functionBiometrika, 1980
- On the Sequential Construction of D-Optimal DesignsJournal of the American Statistical Association, 1976
- A Stochastic Approximation MethodThe Annals of Mathematical Statistics, 1951