1st Edition
Using SAS for Data Management, Statistical Analysis, and Graphics
Introduction to SAS
Installation
Running SAS and a sample session
Learning SAS and getting help
Fundamental structures: Data step, procedures, and global statements
Work process: The cognitive style of SAS
Useful SAS background
Accessing and controlling SAS output: The Output Delivery System
The SAS Macro Facility: Writing functions and passing values
Interfaces: Code and menus, data exploration, and data analysis
Miscellanea
Data Management
Input
Output
Structure and meta-data
Derived variables and data manipulation
Merging, combining, and subsetting datasets
Date and time variables
Interactions with the operating system
Mathematical functions
Matrix operations
Probability distributions and random number generation
Control flow, programming, and data generation
Further resources
HELP examples
Common Statistical Procedures
Summary statistics
Bivariate statistics
Contingency tables
Two sample tests for continuous variables
Further resources
HELP examples
Linear Regression and ANOVA
Model fitting
Model comparison and selection
Tests, contrasts, and linear functions of parameters
Model diagnostics
Model parameters and results
Further resources
HELP examples
Regression Generalizations and Multivariate Statistics
Generalized linear models
Models for correlated data
Further generalizations to regression models
Multivariate statistics and discriminant procedures
Further resources
HELP examples
Graphics
A compendium of useful plots
Adding elements
Options and parameters
Saving graphs
Further resources
HELP examples
Advanced Applications
Simulations and data generation
Power and sample size calculations
Sampling from a pathological distribution
Read variable format files and plot maps
Data scraping and visualization
Missing data: Multiple imputation
Further resources
Appendix: The HELP Study Dataset
Bibliography
Subject Index
SAS Index
Biography
Ken Kleinman is an associate professor in the Department of Population Medicine at Harvard Medical School in Boston, Massachusetts. His research deals with clustered data analysis, surveillance, and epidemiological applications in projects ranging from vaccine and bioterrorism surveillance to observational epidemiology to individual-, practice-, and community-randomized interventions. Nicholas J. Horton is an associate professor in the Department of Mathematics and Statistics at Smith College in Northampton, Massachusetts. His research interests include longitudinal regression models and missing data methods, with applications in psychiatric epidemiology and substance abuse research.
This book is a well-organized reference text that summarizes and illustrates SAS code and common SAS features most often used by statistical analysts and others engaged in research and data analysis. … a handy reference tool for common tasks performed in SAS due to the book’s task-oriented nature and the broad range of topics covered. This book would also nicely serve as a supplemental reference text for an introductory SAS programming class.
—Journal of Biopharmaceutical Statistics, Issue 3, 2011
