This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.

Abstract Details

Activity Number: 625
Type: Contributed
Date/Time: Thursday, August 5, 2010 : 8:30 AM to 10:20 AM
Sponsor: Biopharmaceutical Section
Abstract - #308685
Title: Selecting Covariance Structures in 3, 4, and 6 Period PK and PD Crossover Trials
Author(s): Deborah Panebianco*+ and Tom Bradstreet and Andrea Maes and Lata Maganti
Companies: Merck & Co., Inc. and Merck & Co., Inc. and Novartis Pharmaceuticals Corporation and Merck & Co., Inc.
Address: PO Box 1000, North Wales, PA, 19454-1099,
Keywords: Crossover Trial ; Covariance Structure ; Type I Error ; Power ; Small Sample Size ; Real Data Guided Simulation
Abstract:

The covariance structures of 162 data sets from 3, 4, and 6 period pharmacokinetic (AUC and Cmax) and pharmacodynamic crossover trials, generally including 12 to 36 subjects, were modeled. Akaike's Corrected Information Criterion was used to determine the best fit for each data set among 9 candidate covariance models. For AUC the most common fits (88%) were compound symmetry (CS, 54%), compound symmetry with heterogeneous treatment variances (CSH-T, 20%), unstructured by treatments (UN-T, 7%), and AR(1) by periods (7%). The best model fit for AUC and Cmax was generally the same (50%), or one family of models was not too far from the other (40%), e.g. CS and CSH-T. These empirical results were used to guide the design and conduct of a simulation study to evaluate the Type I error rate and power of competing pairs of modeled vs. true covariance structures including CS, CSH-T, and UN-T.


The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.

Back to the full JSM 2010 program




2010 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.