Abstract Details
Activity Number:
|
260
|
Type:
|
Contributed
|
Date/Time:
|
Monday, August 5, 2013 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Section on Statistical Education
|
Abstract - #308284 |
Title:
|
Improving Efficiency of Computerized Classification Tests Using Modified SPRT
|
Author(s):
|
Haskell Sie*+ and Jim Rosenberger
|
Companies:
|
Pennsylvania State University and Penn State University
|
Keywords:
|
Computerized classification test ;
Item response theory ;
Sequential probability ratio test
|
Abstract:
|
In recent years, Computerized Classification Testing (CCT) has gained popularity due to its efficiency in classifying examinees into proficiency groups based on their test responses. Crucial to the administration of CCT is the choice of stopping rule that allows for early test termination for examinees whose responses clearly indicate mastery or non-mastery. The most commonly used stopping rule in the psychometric literature is the Sequential Probability Ratio Test (SPRT; Wald, 1947). However, for examinees whose latent ability is around the mastery threshold, the use of SPRT with its parallel stopping boundaries renders a long test that will only stop by means of an abrupt truncation when the maximum test length is reached. We modify the SPRT in the context of CCT using converging boundaries similar to the modified SPRT proposed by Bussgang and Marcus (1967). Using the three-parameter item response model, a simulation study is performed to assess the effect of using different features of stopping boundaries on the average test length and classification accuracy. A second simulation study assesses the effects when content balancing and item exposure control are considered.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2013 program
|
2013 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.