In Spring 2022, there are three different topics being offered as Stat 479.
Lec 001: Statistical Data Visualization
Pre-reqs: Stat 240 or 303
Techniques for visualization within data science workflows. Topics include data preparation; exploratory data analysis; spatial, tabular, and graph structured data; dimensionality reduction; model visualization and interpretability; interactive manipulation and navigation.
Lec 003: Data Science Computing Project
Pre-reqs: (Comp Sci 200, 220, or 300) and (Stat 240 or 303)
The development of tools necessary for collecting, managing, and analyzing large data sets. Examples of techniques and programs utilized include Linux, R, distributed computing, text editor(s), git/github, and other related tools. Work in the class will be done in teams to research, develop, write, and make presentations related to a variety of data analysis projects.
Lec 005: Evaluating Methodological Errors in Research
Pre-reqs: Stat 310, 333, or 340
The published literature is filled with methodological errors.Some of these errors are small and unlikely to change the broad conclusions of the paper. Some of these errors are much larger and lead us to fundamentally question the conclusions.These errors survive through peer review! The former editor of BMJ (a major medical journal) Richard Smith said “Publication is not the end of the peer review process but a part of it.” Finding these errors helps to improve science, but it is challenging. If it was easy, then the errors would not survive peer review! We will learn how to critically read and evaluate the use of statistics in published research. We will do this by developing various “statistical reasoning devices” and apply these devices to papers. These are (for example) general questions that you could ask of any paper and help to reflect upon your understanding of what was done and potentially highlight issues within the paper. For example, two deceptively simple questions “what groups does this paper compare?” and “why does this provide evidence for their broad conclusions”? Sometimes the answers to these questions are obvious. However, sometimes when used properly, these questions illuminate fundamental problems in the statistical reasoning of the paper. Perhaps you can develop a device for us to use 1) in class and 2) in our research!
Lec 002, 004, and 006 are not open for undergraduates to enroll in.