Poster #11 - The Robustness of Multisite Randomized Designs Against Misspecified Site-by-Treatment Variance

• In Event: 47.099 - MTCC Poster Session 11
  In Poster Session: 47.099-1 - Division D Section 2 Statistical Theory and Quantitative Methodologies

Abstract

We investigate the effect of an incorrect initial site-by-treatment variance estimate on the relative efficiency and statistical power of multisite randomized designs. The results map out how to plan for and accommodate potential misspecifications of the site-by-treatment variance estimate in the design phase (e.g., how do we develop efficient and robust sampling plans when there is a high degree of uncertainty in a priori estimate of site-by-treatment variance).

Authors

• Yanli Xie, University of Cincinnati

• Benjamin Kelcey, University of Cincinnati

• Kyle T. Cox, University of Cincinnati