CHS 627: Multivariate Methods in Health Statistics
SPRING, 2002

Requirements for Second Statistical Analysis Report

Introduction
  • Brief description of where your data came from
  • Definitions of the variables being used.
Logistic
Regression
  • Conduct an all-inclusive logistic regression analysis.
    • Use a combination of categorical and continuous predictors.
    • Discuss results, including a consideration of multicollinearity.
  • Conduct a stepwise logistic regression analysis.
    • Use the same variables as in the all-inclusive model.
    • Interpret the results at each step. 
    • Compare to the all-inclusive model.
Log-linear
Analysis
  • Conduct a log-linear analysis.
    • Use the same outcome as in the logistic regression analysis.
    • Use two or more categorical predictors. 
    • Interpret results, including the use of graphs. 
    • Compare the results to the logistic regression results.
Multivariate
Analysis
of
Variance
  • Conduct a MANOVA with two or more continuous outcomes and one categorical predictor.
    • Discuss results and assumptions. 
  • Conduct a MANOVA with the same two or more continuous outcomes and two or more categorical predictors. 
    • Discuss results and assumptions.
Summary
  • Discuss what did and what did not influence your outcome variable. 
  • Among the analyses conducted, which seem to be the most appropriate and useful?
  • A major proportion of your grade will depend on the accuracy, thoroughness, and clarity of your discussions.

 
Page editor is Julia Hartman.

Last modified December 17, 2002.
The information in this site is current through August 15, 2002.
Although the authors of this Web site have made every reasonable effort to be factually accurate, no responsibility is assumed for editorial or clerical errors or error occasioned by honest mistake. All information contained on this Web site is subject to change by the appropriate officials of The University of Alabama without prior notice. Material on this Web site does not serve as a contract between The University of Alabama and any other party.