Statistical Methods for Data Analysis (MAT2104.01)

Kathryn Montovan

In this course, we will focus on developing the statistical skills needed to answer questions by collecting data, designing experimental studies, and analyzing large publicly available datasets. The skills learned will also help students to be critical consumers of statistical results. We will use a variety of datasets to develop skills in data management, analysis, and effective presentation of results. Emphasis will be placed on gaining a solid conceptual understanding of the big ideas in statistics, a solid working knowledge of the main statistical tests, and practical skills for conducting data analysis in a statistical software package called R. We will use R to do all computational and graphical aspects of data analysis and visualization and there will be minimal use of formulas in this course. Key statistical tests covered will include randomization simulations, chi-square, ANOVA, and linear and logistic regression.

This is a 2000 level course because there are no formal prerequisites. No prior experience with statistics or computer programming is required but you must be willing to work hard and to engage deeply with the course materials and in the research projects. This is a rigorous and challenging course, which provides participants with practical and widely applicable skills in data analysis.


Learning Outcomes:
In this course, you will:
• Use simulations to make inferences about data and answer questions
• Assess the strength of evidence based on data using statistical methods
• Learn and apply standard inferential statistics tests
• Use R to clean datasets, visualize data, and apply statistical tests
• Design your own statistical inquiry, research your question, clean and analyze a large dataset, and present/communicate your results



Delivery Method: Fully in-person
Course Level: 2000-level
Credits: 4
T/F 8:30AM - 10:20AM (Full-term)
Maximum Enrollment: 20
Course Frequency: Once a year

Categories: All courses , Mathematics , Fully In-Person
Tags: , , , ,