The study of the effect of item parameter drift on ability estimation obtained from adaptive testing under different conditions

Abstract

Item parameter drift (IPD) is the systematic differentiation of parameter values of items over time due to various reasons. If it occurs in computer adaptive tests (CAT), it causes errors in the estimation of item and ability parameters. Identification of the underlying conditions of this situation in CAT is important for estimating item and ability parameters with minimum error. This study examines the measurement precision of IPD and its impacts on the test information function (TIF) in CAT administrations. This simulation study compares sample size (1000, 5000), IPD size (0.00 logit, 0.50 logit, 0.75 logit, 1.00 logit), percentage of items containing IPD (0%, 5%, 10%, 20%), three time points and item bank size (200, 500, 1000) conditions. To examine the impacts of the conditions on ability estimations; measurement precision, and TIF values were calculated, and factorial analysis of variance (ANOVA) for independent samples was carried out to examine whether there were any differences between estimations in terms of these factors. The study found that an increase in the number of measurements using item bank with IPD items results in a decrease in measurement precision and the amount of information the test provides. Factorial ANOVA for independent samples revealed that measurements precision and TIF differences are mostly statistically significant. Although all IPD conditions negatively affect measurement precision and TIF, it has been shown that sample size and item bank size generally do not have an increasing or decreasing effect on these factors.