Bootstrap Methods Within Bayesian Networks For Estimating Statistics Students Knowledge of Hypothesis Tests
- Author
- McIntyre, Thomas
- Published
- [University Park, Pennsylvania] : Pennsylvania State University, 2020.
- Physical Description
- 1 electronic document
- Additional Creators
- Pearl, Dennis Keith and Schreyer Honors College
Access Online
- honors.libraries.psu.edu , Connect to this object online.
- Restrictions on Access
- Open Access.
- Summary
- Technology is becoming a larger part of everyday life in today's world. This also correlates into the realm of academia. Specifically, STEM teaching and learning can be enhanced through the use of interactive educational R Shiny applications. The BOAST team from Pennsylvania State University Statistics Department set out to create a wide variety of applications to assist in teaching the undergraduate courses. After the first semester of field testing the applications, they appeared to be effective. During the past year there has been a collection of log files recording students actions while using the applications. Bayesian network models will be used in this paper to create a model for measuring student knowledge of learning objectives for one of the applications to determine what areas of the application are working the best to improve undergraduate students knowledge. The goal is to examine if a Bayesian network can accurately determine the areas of the R Shiny applications that are most effective in assessing the students knowledge of statistics and if the R package bnlearn using maximum likelihood estimates is a useful tool in understanding the variability of the estimates in these networks using bootstrap methods.
- Other Subject(s)
- Genre(s)
- Dissertation Note
- B.S. Pennsylvania State University 2020.
- Technical Details
- The full text of the dissertation is available as an Adobe Acrobat .pdf file ; Adobe Acrobat Reader required to view the file.
View MARC record | catkey: 30585394