Non–Fisher-Information Item Selection Criteria 1 Running head: Non–Fisher-Information Item Selection Criteria Comparison of Non–Fisher-Information Item Selection Criteria in Fixed-Length Computerized Adaptive Testing

نویسنده

  • Kyung T. Han
چکیده

The maximized Fisher information (MFI) criterion has been the mainstream of the item selection algorithm in many computerized adaptive test (CAT) programs because of its effectiveness and simplicity. There are still several issues with the MFI criterion, however, that need to be resolved in the field, specifically regarding estimation accuracy at the beginning of CAT administration and item pool utilization. Several non-MFI criteria (or approaches) to item selection have been developed, but practitioners still lack insight into the consequential differences among those nonMFI approaches in terms of proficiency estimation and item pool utilization. This study compared five non-MFI item selection approaches (a-stratification, interval information, likelihood weighted information, global information, and gradual maximum information ratio) and attempted to find the item selection criteria that struck a good balance between performance and efficiency in pool utilization. The study found that the gradual maximum information ratio criterion resulted in the most efficient pool use while achieving proficiency estimation as good as the MFI with various test lengths.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Effects of Item-Selection Criteria on Classification Testing with the Sequential Probability Ratio Test

This paper presents comparisons among three item-selection criteria for the sequential probability ratio test. The criteria were compared in terms of their efficiency in selecting items, as indicated by average test length (ATL) and the percentage of correct decisions (PCD). The item-selection criteria applied in this study were the Fisher information function, the KullbackLeibler information f...

متن کامل

A Gradual Maximum Information Ratio Approach to Item Selection in Computerized Adaptive Testing

For long-term quality control of computerized adaptive test (CAT) programs, optimizing the usage of the item bank (i.e., controlling item exposure rate) is critical. Selecting the best item often conflicts with the procedure for item exposure control, however. In this study, a newly proposed approach to item selection in CAT, in which the efficiency of items is considered in the early stages of...

متن کامل

Severity of Organized Item Theft in Computerized Adaptive Testing: A Simulation Study

Criteria had been proposed for assessing the severity of possible test security violations for computerized tests with high-stakes outcomes. However, these criteria resulted from theoretical derivations that assumed uniformly randomized item selection. This study investigated potential damage caused by organized item theft in computerized adaptive testing (CAT) for two realistic item selection ...

متن کامل

Bayesian Item Selection Criteria for - Adaptive Testing

DOCUMENT RESUME TM 027 361 van der Linden, Wim J. Bayesian Item Selection Criteria for Adaptive Testing. Research Report 96-01. Twente Univ., Enschede (Netherlands). Faculty of Educational Science and Technology. 1996-10-00 32p. Faculty of Educational Science and Technology, University of Twente, P.O. Box 217, 7500 AE Enschede, The Netherlands. Reports Evaluative (142) MF01/PCO2 Plus Postage. A...

متن کامل

Ensuring the Future of Computerized Adaptive Testing

Capitalization on chance is a huge problem in computerized adaptive testing (CAT) when Fisher information is used to select the items. Maximizing Fisher information tends to favor items with positive estimation errors in the discrimination parameter and negative estimation errors in the guessing parameter. As a result, information in the resulting tests is overestimated and measurement precisio...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2010