Sponsor
Portland State University. Department of Mathematics and Statistics
First Advisor
Daniel Taylor-Rodriguez
Date of Award
Spring 2021
Document Type
Thesis
Department
Mathematics and Statistics
Subjects
Aphasia -- Statistical methods -- Evaluation, Psychometrics
Abstract
For persons with aphasia, naming tests are useful for assessing the severity of the disease and observing progress toward recovery. The Philadelphia Naming Test (PNT) is a leading naming test composed of 175 items. The items are common nouns which are one to four syllables in length and with low, medium, and high frequency. Since the target word is known to the administrator, the response from the patient can be classified as correct or an error. If the patient commits an error, the PNT provides procedures for classifying the type of error in the response. Item response theory can be applied to PNT data to provide estimates of item difficulty and subject naming ability.
Walker et al. (2018) developed a multinomial processing tree (MPT) model to draw more insight from the types of errors patients commit in responding to an item. The MPT model expands on existing models by considering items to be heterogeneous and estimating multiple latent parameters for patients to more precisely determine at which step of word production a patient's ability is affected. These latent parameters represent the theoretical cognitive steps taken in responding to an item, shown in Figure 1.
The purpose of this paper is to provide an assessment of the goodness-of-fit of the MPT model through posterior predictive checking. Background information for the MPT model is provided, followed by details of the statistical methods applied and results. The paper concludes with a discussion of areas for improvement for the MPT model and implications of use with the current design.
Rights
In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/ This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).
Persistent Identifier
https://archives.pdx.edu/ds/psu/41056
Recommended Citation
Crisp, Ashlynn, "Posterior Predictive Critique of a Psychometric Bayesian Model for Assessing Aphasia" (2021). Mathematics and Statistics Dissertations, Theses, and Final Project Papers. 2.
https://pdxscholar.library.pdx.edu/mth_grad/2
Comments
An undergraduate honors project submitted in partial fulfillment of the requirements for the Fariborz Maseeh Department of Mathematics and Statistics Honors Track.