Categorical Data Analysis Using Logistic Regression - CDAL92
This course focuses on analysing categorical response data in scientific fields. The SAS procedures addressed are PROC FREQ, PROC LOGISTIC, and PROC GENMOD. The course is not designed for predictive modelers in business fields.
|3 days - Classroom|
Learn how to
- Recognise when logistic regression is appropriate
- Write code in the LOGISTIC procedure for binary, ordinal, and nominal logistic regression
- Create effect plots and odds ratio plots using ODS Statistical Graphics
- Create logit plots and use the FREQ procedure for preliminary analyses
- Use automatic model building options in PROC LOGISTIC
- Assess models for fit and influential observations using PROC LOGISTIC
- Create ROC curves for measuring sensitivity and specificity
- Perform exact and conditional logistic regression with PROC LOGISTIC
- Analyze repeated and clustered data using GEE's in the GENMOD procedure.
Who should attend:
Biostatisticians, epidemiologists, social scientists, and physical scientists who analyze categorical response data
Before attending this course, you should
- Be able to execute SAS programs and create SAS data sets. You can gain this experience by completing the SAS Programming I: Essentials course.
- Have experience analyzing frequency tables using SAS software.
- Have completed a course in statistics that covers linear regression and logistic regression. You can gain this experience by completing the Statistics I: Introduction to ANOVA, Regression, and Logistic Regression course.
Contingency Table Analysis
- Using measures and tests of association
- Performing stratified data analysis
Binary Logistic Regression
- Fitting the model
- Creating effect plots and odds ratio plots
- Using model selection strategies
- Assessing the fit of the model
Advanced Regression Topics
- Fitting GEE models
- Fitting ordinal logistic regression models
- Fitting nominal logistic regression models
- Fitting exact logistic regression models
- Fitting conditional logistic regression models
This course addresses the following software product(s): SAS/STAT, SAS/GRAPH.