Statistical Tools - NIA IMPACT Collaboratory

The Design and Statistics Core has developed novel methodology and statistical tools related to design and analyses of embedded pragmatic clinical trials. These methods along with corresponding manuscripts, statistical programs, and interactive tools are shared by the developers to help disseminate best practices and provide practical tools to the research community.

Interactive Resources

Tool to calculate intra-cluster correlation coefficients for designing cluster randomized trials
Tool to calculate intra-cluster correlation coefficients for designing cluster randomized trials
Tool to simulate intra-cluster correlation coefficients among Medicare beneficiaries with dementia for hospitalizations, ED visits, and death across US hospital referral areas
Tool to simulate intra-cluster correlation coefficients among Medicare beneficiaries with dementia for hospitalizations, ED visits, and death across US hospital referral areas

Manuscripts & R Source Code

Information content of stepped-wedge designs when treatment effect heterogeneity and/or implementation periods are present
Information content of stepped-wedge designs when treatment effect heterogeneity and/or implementation periods are present

July 18, 2019

ADDITIONAL STATISTICAL PROGRAMS

Statistical tools developed by members of the IMPACT Design & Statistics Core are available at the Geriatric Research Algorithms & Statistical Programs (GRASP) hosted by the Claude D. Pepper Older Americans Independence Centers National Coordinating Center.

Analyzing dyad data with additional clustering (Katie Newkirk, Joan Monin, Heather Allore, Holly Laws)
Sample size and power calculations for designing stepped wedge cluster randomized trials with subclusters (Kendra Plourde, Monica Taljaard, Fan Li)