|
Activity Number:
|
236
|
|
Type:
|
Roundtables
|
|
Date/Time:
|
Tuesday, August 4, 2009 : 7:00 AM to 8:15 AM
|
|
Sponsor:
|
Section for Statistical Programmers and Analysts
|
| Abstract - #304722 |
|
Title:
|
Issues Around Repeated and Random Statements and Considering the Time as Class versus Continuous Variable
|
|
Author(s):
|
Radhi F. Abdulnabi*+
|
|
Companies:
|
Ovation Pharmaceuticals, Inc
|
|
Address:
|
1756 Reserve Way, Ann Arbor, MI, 48103,
|
|
Keywords:
|
Repeated measures ; Random coefficients ; Covariance structure ; Time effect
|
|
Abstract:
|
The Repeated Measures Data for the same subject are correlated, and this correlation must be taken into account in a longitudinal data analysis. Repeated and Random Statements in SAS procedures are used to specify the variance and covariance structure for the repeated measurements of an individual subject. In this round table discussion we will talk about the use of random and repeated statements to specify the random effect and select the appropriate covariance structure for repeated measures and also discuss the effect of considering the time effect as a classification variable versus using time as a continuous variable. We will also discuss the random coefficient models showing their adequacy compared to other traditional methods. Later, we will present the SAS codes for each method and when we will consider to use the time as fixed effect and when as random effect.
|
