Activity Number:
|
424
- Recent Advances in Educational and Psychological Data Analysis
|
Type:
|
Invited
|
Date/Time:
|
Thursday, August 6, 2020 : 10:00 AM to 11:50 AM
|
Sponsor:
|
Journal of Educational and Behavioral Statistics
|
Abstract #309252
|
|
Title:
|
Compound Sequential Detection of Compromised Items
|
Author(s):
|
Xiaoou Li* and Yunxiao Chen
|
Companies:
|
University of Minnesota and London school of economics and political science
|
Keywords:
|
test security;
sequential analysis;
change-point detection;
continuous testing;
compound sequential decisions
|
Abstract:
|
We propose a compound sequential change detection method for monitoring the item pool in an educational test. Taking a Bayesian change point model, we propose a compound detection method that maximizes the utilization of the items while controlling the proportion of compromised items among the ones being used at all the time points. We provide theoretical results regarding the uniform optimality of the proposed approach among all compound sequential detection rules and illustrate its use and performance through numerical examples.
|
Authors who are presenting talks have a * after their name.