Explanatory Item Response Time Modeling

Doctoral Dissertation
Thumbnail

Abstract

Response time data from educational and psychological assessments have become more widely available in recent years. Although much research has been done on response time models, there is large variability between assessments and the factors that may affect response times. On the person’s side, familiarity with online environments may largely predict response times. On the item’s side, item type and number of words in item stem may account for a substantial variability in response times. In this dissertation, an explanatory framework for response time modeling is proposed. Among the advantages, this explanatory approach provides a more interpretable model for understanding variability in response time due to person or item characteristics, while decreasing the number of parameters to be estimated. Furthermore, including additional information when modeling response times may improve estimation of one’s working speed. Using survey data from a high school sample, we explore also response times, background variables, and process data to illustrate this explanatory framework. Implications and future research directions are also discussed.

Attributes

Attribute NameValues
Author Daniella Rebouças-Ju
Contributor Ying Cheng, Research Director
Contributor Guangjian Zhang, Committee Member
Contributor Ross Jacobucci, Committee Member
Contributor Lijuan Wang, Committee Member
Degree Level Doctoral Dissertation
Degree Discipline Psychology, Research and Experimental
Degree Name Doctor of Philosophy
Banner Code
  • PHD-PSYC

Defense Date
  • 2021-06-17

Submission Date 2021-07-13
Subject
  • response time

  • mixed-effects model

  • process data

  • explanatory models

  • explanatory IRT

Record Visibility Public
Content License
Departments and Units
Catalog Record

Files

Please Note: You may encounter a delay before a download begins. Large or infrequently accessed files can take several minutes to retrieve from our archival storage system.