Date of Award


Document Type


Degree Name

Master of Arts in Mathematics



First Reader/Committee Chair

Ratnasingam, Suthakaran


Change point analysis is a method used to estimate the time point at which a change in the mean or variance of data occurs. It is widely used as changes appear in various datasets such as the stock market, temperature, and quality control, allowing statisticians to take appropriate measures to mitigate financial losses, operational disruptions, or other adverse impacts. In this thesis, we develop a change point detection procedure in the Inverse Gaussian (IG) model using the Modified Information Criterion (MIC). The IG distribution, originating as the distribution of the first passage time of Brownian motion with positive drift, offers flexibility and effectively models a wide range of data shapes. Moreover, it handles outliers and skewness better than some other distributions. Extensive simulation studies are conducted to illustrate the performance of our proposed method compared to existing methods across various settings, in terms of type I error, power, and confidence set. The results indicate that our MIC-based approach is comparable to the Schwarz Information Criterion method. Further, the proposed method has an advantage, especially when the change occurs at the very beginning or at the very end of the dataset. Finally, we present two real-world data applications to demonstrate the advantage of our proposed method.