Mathematical Statistician, Biostatistics Research Branch
Michael P. Fay is a Mathematical Statistician who has worked for over 25 years at the National Institutes of Health, first at the National Cancer Institute and currently at the National Institute of Allergy and Infectious Diseases. He helps design and analyze medical studies, focusing on parasitic diseases and hypereosinophilic syndrome. Additionally, he develops statistical methods with expertise in hypothesis testing and survival analysis. He has served as associate editor for Biometrics, and Clinical Trials and is a Fellow of the American Statistical Association. He is a co-author on over 100 papers in statistical and medical journals and has written and maintains over a dozen R packages on CRAN. He is the coauthor with Erica Brittain of Testing Statistical Hypotheses in Context.
Measures of Agreement, Interval Censored Data, Permutation Tests, Malaria Vaccine Development
Statistical Hypothesis Testing in Context: Reproducibility, Inference, and Science. by Michael P. Fay and Erica H. Brittain (2022, Cambridge University Press).
Fay, MP, Brittain, EH, Proschan, MA (2013). Pointwise confidence intervals for a survival distribution with small samples or heavy censoring. Biostatistics 2013; doi: 10.1093/biostatistics/kxt016
Fay MP, Follmann DA, Lynn F, Schiffer JM, Stark GV, Kohberger R, Quinn CP, Nuzum EO. (2012). Anthrax Vaccine Induced Antibodies Provide Cross-Species Prediction of Survival to Aerosol Challenge. Science Translational Medicine 4: 151ra126.
Fay MP, Shih JH. (2012). Weighted Logrank Tests for Interval Censored Data when Assessment Times Depend on Treatment. Statistics in Medicine. doi: 10.1002/sim.5447.
Fay, M.P., Halloran, M.E., Follmann, D.A., Diemert, D., Dicko, A., Thera, M., Sagara, I., Klion, A., Doumbo, O., Saul, A. (2005). The Design of a Phase 2 Malaria Vaccine Trial Based on a Cohort Study. Poster presented at 4th MIM Pan-African Malaria Conference.
Fay, M.P., Huang, C-Y., Twum-Danso, N.A.Y. (2007). Monitoring Rare Serious Adverse Events from a New Treatment and Testing for Difference from a Baseline Rate. (PDF) Poster presented at 2007 EMR-IBS conference, Eilat, Israel.
Software Written by Michael Fay
The exact2x2 R package that gives matching confidence intervals for Fisher’s exact test and Blaker’s exact test as described in Fay (2009).
hbim R package to perform calculations related to the Hill/Bliss independence model as applied to mulitcomponent vaccines as described by Saul and Fay (2007).
Note this package is the exactly the same as the one on the PLoS ONE site, except the reference has been updated, and the date on the vignette (calculation details document) was changed when it was rebuilt.
choplump R package to perform permutation tests when there are a high proportion of zeros for responses as described in Follmann, Fay, and Proschan (2007).
Interval Censored Data Functions (R package interval) as described in Fay and Shaw (2010)
Small Sample Adjustments for Wald-type Tests using Sandwich Estimators (saws R package)
MChtest R package to perform Monte Carlo hypothesis testing with sequential stopping as described in Fay, Kim, and Hachey (2007)
ssanv R package to calculate sample sizes that account for variability as described in Fay, Halloran, Follmann. (2007)
Software Developed With Collaborators
Conditional Logistic Regression with Sandwich Estimators (see clogistCalc function in saws R package)
Joinpoint Regression (PC executable with GUI)
Probability of Developing or Dying of Cancer (PC executable with GUI)