Course Description
Statistical modeling using nonlinear regression is considered. Topics include fixed-effects nonlinear regression models, nonlinear least squares, computational methods and practical matters, growth models, and compartmental models. Nonlinear mixed-effects models are discussed, including model interpretation, estimation and inference. Examples will be drawn from forestry, pharmaceutical sciences, and other fields.
Athena Title
APPL NONLINEAR REG
Prerequisite
STAT 4230/6230 or STAT 6320 or STAT 6420 or permission of department
Semester Course Offered
Offered fall
Grading System
A - F (Traditional)
Course Objectives
Course is intended to provide an introduction to both fixed- and mixed-effects nonlinear regression models with emphasis on the practical aspects of the use of these models in the analysis of real data. Fixed-effects nonlinear regression is given only brief coverage in existing courses and mixed-effects nonlinear models are not taught at all. This limited coverage is despite these models common and increasing use in modeling biological growth (e.g., in Forest Biometrics), chemical kinetics and dynamics (e.g., in Pharmaceutical Sciences), and other processes. In this course students will be introduced to the general classes of normal error fixed- and mixed-effects nonlinear models. They will learn practical aspects of how to fit, interpret and make inferences from these models, and they will study the important special cases of these models that are most often encountered in applications.
Topical Outline
Review of linear regression. Fixed-effects nonlinear models (NLMs). Nonlinear least-squares. Computational methods and other practical considerations. Growth models. Compartmental models. Nonlinear mixed-effects models (NLMMs). Methods of estimation and inference in NLMMs. Software for NLMs and NLMMs.
Syllabus
Public CV