Heather Allore, PhD

The focus of my research collaborations and methodological development work as previous Director of Biostatistics at the Yale Program on Aging for 12 years and current Leader of the Yale Alzheimer's Disease Research Center's Data Management and Statistics Core. I founded the field of Gerontological Biostatistic. I lead the Design and Statistics Core of Imbedded Pragmatic Alzheimer’s Disease and AD-Related Dementias Clinical Trials Collaboratory. I am Co-director of the Biostatistics and Bioinformatics Core of the Yale Transdisciplinary Collaborative Center for Precision Medicine focused on Health Disparities, especially adults with multiple chronic conditions. I co-authored a paper on health disparities in the Decadal Survey of Behavioral and Social Science Research on Alzheimer’s Disease and Alzheimer’s Disease-Related Dementias. My innovated analytic methods include joint trajectories of cognition, function and mortality. Innovative designs and biostatistical methods are required to rigorously address the myriad of unanswered scientific questions related to older adults and persons with dementia, including risk prediction.

With over 240 peer-reviewed articles and continuous NIH funding since 2000, my research has focused on issues related to the design of clinical trials for and studies of older adults. These and other methodologic advances resulted in me being an invited speaker at an NIH/NIA conference on Longitudinal Methods and another on Clinical Trial Design. In 2017 and 2020, I co-chaired the Study Design and Metrics component of the NIH meeting on the 21^st Century Cures Act: Inclusion Across the Lifespan I and II. I previously chaired the Alzheimer's Disease Research Center's Data Cores Steering Committee, member of the Executive Committee, and Co-Lead of the Data and Measures Committee of the NIA-funded AGING Initiative, which is a collaboration of Older Americans Independence Centers and the Healthcare Systems Research Network. I have a wealth of experience conducting epidemiologic studies and am a recognized authority on longitudinal statistical methods, including extended Cox models for state transitions, generalized estimating equations, mixed effects models, latent class trajectory models, and joint models. A defining hallmark of my biostatistical approach is that instead of developing analytic methods in the absence of a clinical question or adapting the study question to available analytical techniques, I adapt new statistical methods that suitably model the specific study question.