Statistical Tutorials cost $45 each and you will receive appropriate handouts.
There are two choices in each of the concurrent sessions.
Sunday, April 10
Power and Sample Size Computations
Instructor: John Castelloe, SAS
Power determination and sample size computations are an important aspect of
study planning and help produce studies with useful results for minimum
resources. This statistical seminar reviews basic methodology for power and
sample size computations for a number of analyses including proportion tests,
t tests, confidence intervals, equivalence tests, survival analyses,
correlation, regression, ANOVA, and more complex linear models. The seminar
illustrates these methods with numerous examples using new SAS software: the
POWER and GLMPOWER procedures and the PSS web interface. The seminar details
how to use the software to compute power and sample size, perform sensitivity
analyses for other factors such as variability and type I error rate, and
produce customized tables, graphs, and narratives. Some basic understanding
of power and sample size computations is assumed.
Analysis of Survival Data With SAS Software
Instructor: Gordon Johnston, SAS
The analysis of lifetime data is an important aspect of statistical work in a
variety of fields, including the biomedical and engineering sciences. This
seminar provides an overview of the methodology available in the SAS System
for the analysis of censored survival data. The seminar illustrates
nonparametric methodology, semi-parametric regression models, and fully
parametric regression models with numerous examples using the LIFETEST, PHREG,
LIFEREG, and RELIABILITY procedures. Basic concepts and methods of survival
data analysis the attention in the seminar. The rest of the course focuses on
more advanced topics, such as correlated survival data and data from recurrent
events. Attendees should have a background in basic statistical methodology,
but the seminar provides most of the required background in survival analysis.
Introduction to Logistic Regression
Instructor: Bob Derr, SAS
Logistic regression is one of the basic modeling tools for a statistician or data
analyst. This tutorial focuses on the basic methodology behind logistic regression
and discusses parameterization, testing goodness of fit, model-building procedures,
and model evaluation. The tutorial focuses on the dichotomous response, but
direction for handling the ordinal response will also be provided. Attendees should
have a solid foundation in regression.
Using Mixed Models for Repeated Measures and Random Effects Data
Instructor: Tonya Etchison Balan, SAS
Data which are clustered or correlated are commonplace in a variety of statistical
applications. The general linear mixed model is a useful tool to analyze such data
and draw meaningful inferences. We will discuss the mixed model and apply it to
prototypical examples. Related topics include the verification of underlying
assumptions and the validity of associated statistics. Mixed models are fit with the
MIXED procedure, and examples of the use of PROC MIXED are discussed. Attendees
should have a solid background in regression and linear models.