STAT 220
Statistical Modeling for Data Science
Statistics
College of Physical and Mathematical Sciences
Course Description
Statistical thinking, basic probability and random variables, estimation, uncertainty in estimation, inference and interpretation for the linear model, prediction, model comparison, introduction to Bayesian statistics, binary data, evaluating classification models, data ethics and privacy
When Taught
Fall
Grade Rule
Grade Rule 8: A, B, C, D, E, I (Standard grade rule)
Min
3
Fixed
3
Fixed
3
Fixed
0
Title
Random Variables and Distributions
Learning Outcome
Understand the assumptions and properties of the Bernoulli and normal distributions
Title
Maximum Likelihood
Learning Outcome
Understand the basic principles of maximum likelihood estimation
Title
Linear Models
Learning Outcome
Fit the linear regression model using statistical software; predict using the linear model; assess the fit of the linear model, quantify uncertainty associated with the linear model
Title
Data Ethics and Privacy
Learning Outcome
Understand how the use of data can be an invasion of privacy and how privacy should always be protected. Understand the implications of systemic biases that can be embedded in statistical models
Title
Bayes' Theorem
Learning Outcome
Explain how conditional probability and Bayes' Theorem relate to the analysis of data via the Bayesian paradigm
Title
Bayesian Analysis
Learning Outcome
Interpret and explain the results of Bayesian analyses
Title
Logistic Regression
Learning Outcome
Fit and interpret a logistic regression model
