Introduction to Statistical Models
Revised: September 2020
Course Description
The foundation of this course is linear models, which are then compared to nonlinear
approaches. Topics include estimation and testing, simulation and resampling, introduction
to linear models including simple linear, multivariate and generalized linear models,
and introduction to model selection and performance. Prerequisite: MATH 270 or MATH
370. Three semester hours.
Student Learning Objectives
By the end of the course students will be able to:
- Minimize a loss function in the estimation of model parameters
- Estimate population parameters using intervals and testing
- Compare statistical and algorithmic approaches to point and interval estimation
- Construct a simulation to interpret model parameters
- Choose a set of explanatory variables for a simple or multiple linear regression model
using an appropriate model selection technique
- Choose the best model based on a balance between prediction and parsimony
Text
Determined by instructor, but one suggestion might be:
- A Modern Approach to Regression with R, by Simon Sheather
Grading Procedure
Grading procedures and factors influencing course grade are left to the discretion
of individual instructors, subject to general university policy.
Attendance Policy
Attendance policy is left to the discretion of individual instructors, subject to
general university policy.
Course Outline
- Chapter 1: Introduction (1 week)
- Chapter 2: Simple Linear Regression (2 weeks)
- Chapter 3: Diagnostics and Transformations for Simple Linear Regression (2 weeks)
- Chapter 4: Weighted Least Squares (1 week)
- Chapter 5: Multiple Linear Regression (2 weeks)
- Chapter 6: Diagnostics and Transformations for Multiple Linear Regression (2 weeks)
- Chapter 7: Variable Selection (1 week)
- Chapter 8: Logistic Regression (1 week)