Date of Award

1-1-2022

Degree Type

Thesis

Degree Name

Master of Science in Statistics

Department

Computer Science and Statistics

First Advisor

Gavino Puggioni

Abstract

The objective of this thesis is to explore the relationship between cry acoustic data and neurological development. The methods used in this project were general linear models as well as XGBoost models. Additional methods explored include general linear mixed effects models and combining mixed effects estimation with machine learning algorithms. A description and simulation to compare those methods is provided, and a discussion on when using mixed effects with machine learning could be beneficial. An analysis was carried out to predict autism spectrum disorder using cry recording data from newborn infants, as well as a simulation study to understand how sample size can impact the results of that modeling. Another analysis was carried out to predict 12 month development index from the cry acoustic data. Cry acoustic data seems to decrease out of sample variation when predicting ASD, but not clear advantage is seen when predicting mental development index.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.