Lee Kennedy-Shaffer, PhD
Cards
Education
Harvard University, Biostatistics (2020)
Harvard University, Biostatistics
Contact Info
About
Titles
Assistant Professor of Biostatistics
Biography
Lee Kennedy-Shaffer is an Assistant Professor (Educator-Scholar Track) in Biostatistics. Lee received his PhD in Biostatistics under Dr. Michael Hughes in the Harvard T.H. Chan School of Public Health and conducted epidemiologic research there with Drs. Marc Lipsitch and Michael Mina in the Center for Communicable Disease Dynamics. He was an Assistant Professor in the Vassar College Department of Mathematics and Statistics from 2020–2024.
His research focuses on randomized and observational study designs and methods for the analysis of infectious disease interventions. This includes mathematical modeling, cluster-randomized trials, and quasi-experimental designs, all with an eye toward broader population health impacts than are usually addressed by individually randomized trials. He has worked on COVID-19 data collection and analysis as well, in particular accounting for the timing and correlation of infections in interpreting test results. This work has been published in journals such as Science, Statistics in Medicine, Clinical Trials, the American Journal of Epidemiology, and the American Journal of Public Health, among others. In addition, he has written on the history of statistics, FDA policy, statistics education, and causal inference in baseball.
Appointments
Biostatistics
Assistant ProfessorPrimary
Other Departments & Organizations
Education & Training
- PhD
- Harvard University, Biostatistics (2020)
- MA
- Harvard University, Biostatistics
- BS
- Yale University, Mathematics
Research
Overview
Infectious disease studies face many statistical and epidemiological challenges, of which three of the most significant and unique are: (1) clustering and correlation of outcomes among individuals; (2) high spatiotemporal variation, especially in outbreak and epidemic settings; and (3) different estimands at individual and population levels. These make common statistical assumptions—including independence, parallel trends, exchangeability, and homogeneous effects—unlikely to hold for a variety of exposures and outcomes. Understanding infectious disease interventions thus requires the development of new study designs and new methods for analysis, or the modification of existing ones to address these challenges. These engender tradeoffs, however, on the epidemiological, statistical, and policy levels.
Specific areas of research include:
- Developing cluster-randomized trial and stepped-wedge trial designs and analysis methods,
Quantifying and using spatiotemporal variation in infectious disease outbreaks to improve surveillance and studies of interventions,
Designing studies to understand the full spectrum of effects of vaccines and other infectious disease interventions,
The communication, education, and history of statistics, and
Exploring the policy implications of statistical methods.
Medical Subject Headings (MeSH)
ORCID
0000-0001-7604-3638- View Lab Website
Lab Website
Research at a Glance
Research Interests
Models, Statistical
Publications
Featured Publications
Quasi-experimental methods for pharmacoepidemiology: difference-in-differences and synthetic control methods with case studies for vaccine evaluation
Kennedy-Shaffer L. Quasi-experimental methods for pharmacoepidemiology: difference-in-differences and synthetic control methods with case studies for vaccine evaluation. American Journal Of Epidemiology 2024, 193: 1050-1058. PMID: 38456774, PMCID: PMC11228849, DOI: 10.1093/aje/kwae019.Peer-Reviewed Original ResearchCitationsAltmetricMeSH Keywords and ConceptsConceptsSynthetic control methodDifference-in-differencesHealth policyCase studyAverage treatment effectQuasi-experimental methodPolicyQuasi-experimental designWeight assumptionPopulation-level effectsTime trendsStudy designSources of evidenceConfounding factorsEvaluation studiesPharmacoepidemiologyTarget estimandAbsence of contaminationTeaching the Difficult Past of Statistics to Improve the Future
Kennedy-Shaffer L. Teaching the Difficult Past of Statistics to Improve the Future. Journal Of Statistics And Data Science Education 2023, 32: 108-119. DOI: 10.1080/26939169.2023.2224407.Peer-Reviewed Original ResearchCitationsAltmetricConceptsPublic Health Impacts of Vaccines for COVID-19 and Beyond: Opportunities to Overcome Technical and Regulatory Barriers for Randomized Trials.
Kennedy-Shaffer L. Public Health Impacts of Vaccines for COVID-19 and Beyond: Opportunities to Overcome Technical and Regulatory Barriers for Randomized Trials. American Journal Of Public Health 2023, 113: 778-785. PMID: 37104734, PMCID: PMC10262256, DOI: 10.2105/ajph.2023.307302.Peer-Reviewed Original ResearchCitationsMeSH Keywords and ConceptsConceptsPublic health impactCOVID-19 pandemicPopulation healthEvidence baseCOVID-19Health impactsInfectious disease outbreaksCommunity levelRandomized trialsIndividual levelRegulatory barriersPivotal trialsClinical benefitTrialsClinical trialsVaccine trialsPrevent infectionStrategic deploymentVaccineHealthBaseball's Natural Experiment
Kennedy-Shaffer L. Baseball's Natural Experiment. Significance 2022, 19: 42-45. DOI: 10.1111/1740-9713.01691.Publications for non-academic audiencesAltmetricThe required size of cluster randomized trials of nonpharmaceutical interventions in epidemic settings
Sheen J, Haushofer J, Metcalf C, Kennedy‐Shaffer L. The required size of cluster randomized trials of nonpharmaceutical interventions in epidemic settings. Statistics In Medicine 2022, 41: 2466-2482. PMID: 35257398, PMCID: PMC9111156, DOI: 10.1002/sim.9365.Peer-Reviewed Original ResearchAltmetricMeSH Keywords and ConceptsConceptsCluster randomized trialEffectiveness of interventionsSample sizeRandomized trialsPlanning such trialsApproximate sample size formulaeReduce transmissionEffect sizeNonpharmaceutical interventionsInfectious disease outbreaksObservational studyInterventionEpidemic settingsSample size methodsAdequate powerSARS-CoV-2 pandemicSARS-CoV-2 transmissionSample size formulaTested individualsSimulated bankTreatment effectsTrialsCommunity transmissionOutbreak settingsSize formulaEstimating Vaccine Efficacy Against Transmission via Effect on Viral Load
Kennedy-Shaffer L, Kahn R, Lipsitch M. Estimating Vaccine Efficacy Against Transmission via Effect on Viral Load. Epidemiology 2021, 32: 820-828. PMID: 34469363, PMCID: PMC8478108, DOI: 10.1097/ede.0000000000001415.Peer-Reviewed Original ResearchCitationsAltmetricMeSH Keywords and ConceptsConceptsViral load measurementsVaccine efficacyViral loadMeasure of vaccine efficacyRandomized controlled trialsEstimates of vaccine efficacyVirological testingAsymptomatic infectionVaccine effectivenessSevere diseaseControlled trialsViral variantsSARS-CoV-2Estimate efficacyEfficacySARS-CoV-2 pandemicVaccineLoad measurementsInfectionVirus transmissionEstimating epidemiologic dynamics from cross-sectional viral load distributions
Hay J, Kennedy-Shaffer L, Kanjilal S, Lennon N, Gabriel S, Lipsitch M, Mina M. Estimating epidemiologic dynamics from cross-sectional viral load distributions. Science 2021, 373: eabh0635. PMID: 34083451, PMCID: PMC8527857, DOI: 10.1126/science.abh0635.Peer-Reviewed Original ResearchCitationsAltmetricMeSH Keywords and ConceptsSnowball Sampling Study Design for Serosurveys Early in Disease Outbreaks
Kennedy-Shaffer L, Qiu X, Hanage W. Snowball Sampling Study Design for Serosurveys Early in Disease Outbreaks. American Journal Of Epidemiology 2021, 190: 1918-1927. PMID: 33831177, PMCID: PMC8083564, DOI: 10.1093/aje/kwab098.Peer-Reviewed Original ResearchCitationsAltmetricPerfect as the enemy of good: tracing transmissions with low-sensitivity tests to mitigate SARS-CoV-2 outbreaks
Kennedy-Shaffer L, Baym M, Hanage W. Perfect as the enemy of good: tracing transmissions with low-sensitivity tests to mitigate SARS-CoV-2 outbreaks. The Lancet Microbe 2021, 2: e219-e224. PMID: 33748803, PMCID: PMC7954468, DOI: 10.1016/s2666-5247(21)00004-5.Peer-Reviewed Original ResearchCitationsAltmetricMeSH Keywords and ConceptsStatistical Properties of Stepped Wedge Cluster-Randomized Trials in Infectious Disease Outbreaks
Kennedy-Shaffer L, Lipsitch M. Statistical Properties of Stepped Wedge Cluster-Randomized Trials in Infectious Disease Outbreaks. American Journal Of Epidemiology 2020, 189: 1324-1332. PMID: 32648891, PMCID: PMC7604531, DOI: 10.1093/aje/kwaa141.Peer-Reviewed Original ResearchCitationsAltmetricMeSH Keywords and ConceptsConceptsWedge trialsParallel-arm cluster-randomized trialsStepped wedge cluster randomized trialStatistical propertiesCluster randomized trialStatistical disadvantageStepped wedge trialIndividual randomizationInfectious disease outbreaksCluster randomized designEvaluation of interventionsEvaluate various designsTrial designDetect intervention effectsWedge designRandomized controlled trialsIntervention effectsEffect estimatesControlled trialsParallel-armEpidemic settingsLogistical factorsAdequate powerInfectious disease incidenceRandomized trials
Get In Touch
Contacts
Locations
300 George Street
Academic Office
Ste 501, Rm 529b
New Haven, CT 06511
Events
Yale Only Lee Kennedy-Shaffer, PhD