September 2005-May 2006 Meetings
Tuesday, September 20, 2005
Speaker: Zachary Skrivanek, Ph.D., Eli Lilly and Company
Topic: Adaptive Design with Variance as the Endpoint
In typical clinical trials the design is fixed and the statistician does not analyze the data until the study is terminated. Adaptive designs allow the statistician to gather information during the study and modify the design according to some pre-defined criteria. The modifications encompass sample size adjustments, treatment allocation ratios and selection of treatments/doses.
In order to preserve the overall type I error, often non-standard statistical procedures are implemented. Conditional power calculation methods have been proposed as a criterion to extend a study where a treatment shows an effect just shy of statistical significance. Two-stage procedures based on conditional power that preserve type I error have been described, but they are limited to an analysis of the mean.
Some times the variance may be of interest, rather than the mean, however. For example, it is of crucial importance to provide as good reproducibility as is possible of repeated insulin injections in the same individual with regard to the achieved insulin levels and glycaemic levels in the post-injection period. I.E. intra-subject reproducibility of the Pharmacokinetic (PK) and Pharmacodynamic (PD) profiles is clinically important. A compound may be preferred to another because it has a lower intra-subject variance. We will describe an adaptive design that compares two treatments in terms of intra-subject variance. We will use a two-stage approach and the criterion to continue the study will be based on the conditional power.
Monday, April 17, 2006
Speaker: Prof. Benzion Boukai, Chairman of Department of Mathematics, IUPUI
Topic: On Simultaneous Bayesian – Frequentist Sequential Testing
The second annual Bernhard Flury Memorial Lecture was presented on the Indiana University Bloomington campus in Swain East, room 140, at 4:00 PM.
Wednesday, May 3, 2006
Propensity Scoring Workshop
[1] Prof. Andrew Leon, Cornell University
Bias Reduction with a Longitudinal Propensity Adjustment
[2] Brenda Crowe, PhD, Eli Lilly & Co.
Imputation of Missing Baseline Covariates
[3] Bob Obenchain, PhD, Eli Lilly & Co.
Propensity Scoring: Balancing Covariate Distributions while
Preserving Treatment Fraction Imbalance
8:30AM. to 1:00PM, Eli Lilly Corporate Center campus, Building 87.
Tuesday, May 9, 2006
Wednesday, May 10, 2006
2006 International Science and Engineering Fair
ISEF was held in Indianapolis, May 07 – 13. The Central Indiana Chapter provided "special judges" for three national ASA awards. The preliminary judging took place on Tuesday, May 09, and screened about 1,200 projects for statistical content. For more details on Central Indiana ASA's state and national judging activities, see our SEFI page.
Wednesday, October 25, 2006
Short Course: Dr. Ralph O’Brien
Topic: Sample Size Analysis for Study Planning
Make plans now to attend this Indy ASA sponsored short course. More details on this full day course will be provided in the coming months.
.