NUR 3114 - APPLIED REGRESSION FOR HEALTH SCIENCE RESEARCH

Minimum Credits: 3
Maximum Credits: 3
This course covers general principles, purposes, and methodologies of regression analysis with application to the health sciences. A primary focus will be on multiple linear regression with both continuous and categorical predictors as well as incorporating interaction terms for non-additivity and polynomials for non-linearity. Regression diagnostics for assessing underlying assumptions, evaluating variable and case influences on model fit and valid inference will be examined. Remedial strategies to address violations and issues found in diagnostics will be explored. Basic concepts and techniques for model selection and predictive modeling, such as algorithms for variable selection and cross-validation, will be introduced. Generalized Linear Modeling will be presented for doing regression analysis when outcomes are not expected to be linear functions of predictors or have normal error distributions (e.g., Logistic regression for categorical outcome variables and Poisson regression for discrete count outcome variables). Implementation of regression using statistical software will be presented using data examples from health science research. Labs are available for SPSS, Stata, R, and SAS.
Academic Career: Graduate
Course Component: Seminar
Grade Component: Grad Letter Grade
Course Requirements: PREQ: NUR 3112 and NUR 3113

Click here for class schedule information.

Add to Portfolio(opens a new window)