Date of Award:

5-2018

Document Type:

Dissertation

Degree Name:

Doctor of Philosophy (PhD)

Department:

Mathematics and Statistics

Advisor/Chair:

Joseph V. Koebbe

Abstract

One way that examinees can gain an unfair advantage on a test is by having prior access to the test questions and their answers, known as preknowledge. Determining which examinees had preknowledge can be a difficult task. Sometimes, the compromised test content that examinees use to get preknowledge has mistakes in the answer key. Examinees who had preknowledge can be identified by determining whether they used this flawed answer key. This research consisted of three papers aimed at helping testing programs detect examinees who used a flawed answer key. The first paper developed three methods for detecting examinees who used a flawed answer key. These methods were applied to a real data set with a flawed answer key for which 37 of the 65 answers were incorrect. One requirement for these three methods was that the flawed answer key had to be known. The second paper studied the problem of estimating an unknown flawed answer key. Four methods of estimating the unknown flawed key were developed and applied to real and simulated data. Two of the methods had promising results. The methods of estimating an unknown flawed answer key required comparing examinees’ response patterns, which was a time-consuming process. In the third paper, OpenMP and OpenACC were used to parallelize this process, which allowed for larger data sets to be analyzed in less time.

Checksum

4d2b07aceed380f7099707c442135d0b

Included in

Mathematics Commons

Share

COinS