What This Document Is
These are lecture notes from STAT 710: Mathematical Statistics, taught at the University of Wisconsin-Madison by Jun Shao. The notes cover advanced statistical methodologies, specifically focusing on the analysis of categorical data through contingency tables and related hypothesis testing. This material builds upon foundational statistical concepts and delves into more complex applications of statistical inference. The notes represent a single lecture session within the course, detailing theoretical frameworks and approaches to statistical problems.
Why This Document Matters
Students enrolled in advanced mathematical statistics courses, or those preparing for graduate-level work in statistics, biostatistics, or related fields will find these notes exceptionally valuable. They are particularly useful for individuals seeking a deeper understanding of how to apply statistical tests to real-world data scenarios involving multiple categories. These notes can serve as a strong supplement to textbook readings and classroom lectures, offering a focused perspective on specific techniques. Researchers needing a refresher on these methods will also benefit.
Common Limitations or Challenges
These notes represent a single lecture and therefore do not provide a comprehensive overview of all statistical testing methods. They assume a solid foundation in probability theory, statistical inference, and basic hypothesis testing. The notes focus on the theoretical underpinnings and may not include detailed, step-by-step computational examples. Access to the full material is required for a complete understanding of the derivations and applications discussed.
What This Document Provides
* Exploration of r x c contingency tables as an extension of 2x2 tables.
* Discussion of hypothesis testing related to the independence of categorical variables.
* Investigation into methods for comparing multinomial distributions.
* Examination of maximum likelihood estimation (MLE) within the context of contingency tables.
* Theoretical foundations for chi-square tests and their modifications.
* Consideration of the number of degrees of freedom in statistical tests.
