Aging; Bayes Theorem; Geriatrics; Comorbidity; Statistics; Biostatistics; Propensity Score
Dr. Murphy is a member of the biostatistics staff of the Program on Aging. With twelve years experience in the design and manufacture of clinical instrumentation and advanced training in engineering statistics, he is interested in the application of engineering tools to research on aging. Current areas of investigation include multivariate statistics for characterization of multiple co–morbidity, robust design techniques for assessing the tradeoffs of multiple medication use, and the use of hierarchical models, propensity scores, and Bayesian techniques to enhance the analysis of non-randomized interventional designs such as the fall–related utilization of healthcare services by older persons in the state of Connecticut.
Specialized Terms: Aging; Bayesian methods; Spatial modeling; Non-randomized interventional designs; Multistate modeling
Extensive Research Description
YCCI-T3 Murphy (PI) 5/01/2011 - 4/30/13
Yale Center for Clinical Investigation
Enhancing Non-Randomized Studies in Public Health: A Novel Statistical Technique to Strengthen Causality of an Obesity Prevention Intervention for Children
The goal of this project is to integrate propensity scores into a spatial modeling framework to provide greater evidence of causality in this observational study.
Role: Principal Investigator
1R21AG033130 Murphy (PI) 9/30/2010 - 8/31/2012 NIH/NIA
Enhanced Evaluation of Second Stage Translational Research
- Murphy TE, Van Ness PH , Araujo KLB, Pisani MA. Bayesian time series analysis of a repeated measures Poisson outcome with excess zeroes. American Journal of Epidemiology; 2011; Dec 1;174(11):1230-7. Epub 2011 Oct 24. PMID: 22025357.
- Murphy TE, Han L, Allore HG, Peduzzi PN, Gill TM, Lin HQ. Treatment of death in the analysis of longitudinal studies of gerontological outcomes. J Gerontol A Biol Sci Med Sci. 2011;66(1):109-114. PMCID: PMC3011957.
- Murphy TE, Allore HG, Leo-Summers L, Carlin BP. Bayesian hierarchical modeling for a non-randomized, longitudinal fall prevention trial with spatially correlated observations. Statistics In Medicine 2011 30(5): 522-530. PMID 21294148.
- Tinetti ME, Baker DI, King M, Gottschalk M, Murphy TE, Acampora D, Carlin BP, Leo-Summers L, Allore HG. Effect of diseemination of evidence in reducing injuries from falls. N Engl J Med 2008 359:252-261. PMID: 18635430
- Murphy TE, Agostini JV, Van Ness PH, Peduzzi P, Tinetti ME, Allore HG. Assessing the probabilities of harms and benefits of multiple medication use. J Aging Health. 2008 Sep20(6):694-709. Epub 2008 Jul 14. PMID: 18625759
- Murphy TE, Tinetti ME, Allore HG. Hierarchical models to evaluate translational research: Connecticut collaboration for fall prevention. Contemp Clin Trials. 2008 May29(3):343-50. Epub 2007 Oct 26. PMID: 18054289