STA 207: Statistical Methods for Research II

Subject: STA 207
Title: Statistical Methods for Research II
Units: 4.0
School: College of Letters and Science LS
Department: Statistics STA
Effective Term: 2013 Fall


Learning Activities

  • Lecture - 3.0 hours
  • Discussion/Laboratory - 1.0 hours

Description

Linear and nonlinear statistical models emphasis on concepts, methods/data analysis using professional level software; formal mathematics kept to minimum. Topics include linear mixed models, repeated measures, generalized linear models, model selection, analysis of missing data, and multiple testing procedures.

Prerequisites

STA 206; Knowledge of vectors and matrices.

Expanded Course Description

Summary of Course Content: 
This course will focus on linear and nonlinear statistical models that are widely used in scientific research. The emphasis will be on concepts, methods and data analysis, and formal mathematics will be kept to the necessary minimum. Topics include linear mixed models, repeated measures, generalized linear models, model selection, analysis of missing data, and multiple testing procedures. Data analysis part of this course will be done using a professional level software such as MATLAB, SAS or R. 

Illustrative Reading: 
Applied Regression Analysis and other Multivariable Methods, by Kleinbaum, D,. Kupper, L. Nizam, A. and Muller, K. Thompson, Brooks-Cole. 

Potential Course Overlap: 
There is some overlap with materials taught in Statistics 106. However, Statistics 207 covers much more materials than STA106. It will be taught at a level that is more advanced mathematically and computationally. There is also some overlap with STA/BST 223, 224 and STA 243. However, STA/BST 223 and 224 are required courses for the Ph.D. students in Biostatistics, their coverage are far wider and deeper and these courses are taught at a substantially higher level. STA243 is a course on computational statistics for Ph.D. students in Statistics and the only potential overlap with this course is in the treatment of missing data and the use of the EM algorithm.