Methods Seminar

Statistics faculty run the Department of Health Care Policy's Methods Seminar, which covers methodological topics of interest to health policy and health services researchers. It draws a mixed audience of students, fellows, staff, and faculty.  These happy hour seminars are Tuesday afternoons from 4 to 5 pm in the Department of Health Care Policy at Harvard Medical School, 180-A Longwood Ave.


February 12, 2019: Selection bias

Howe and Robinson. Survival-related selection bias in studies of racial health disparities: The importance of the target population and study design. Epidemiology. 29(4):521-4, 2018.

Hernán, Hernández-Díaz, Robins. A structural approach to selection bias. Epidemiology. 15(5): 615-25, 2004.

March 12, 2019 

April 23, 2019 


November 13, 2018: Novel and nontraditional data

Gebru et al. Using deep learning and Google Street View to estimate the demographic makeup of neighborhoods across the United States. PNAS. 114(50): 13108-13113, 2017.September 25, 2018: Matching and weighting for causal inference in observational studies

King & Nielsen. Why propensity scores should not be used for matching. Working paper. 2016.

Garrido et al. Methods for constructing and assessing propensity scores. Health Services Research. 49(5):1701-20, 2014.

October 23, 2018: Risk of bias tools to evaluate study quality

Losilla, Oliveras, Marin-Garcia, Vives. Three risk of bias tools lead to opposite conclusions in observational research synthesis. Journal of Clinical Epidemiology. 101:61-72, 2018.

April 17, 2018: Divide and recombine for distributed analysis

Lee, Brown, & Ryan. Sufficiency revisited: Rethinking statistical algorithms in the big data era. The American Statistician. 71(3): 202-8, 2017.

March 6, 2018: Machine learning and artificial intelligence for the analysis of medical images

Oakden-Rayner. Exploring the ChestXray14 Data Set: Problems

February 13, 2018: Nonlinear Models

          Karaca-Mandic, Norton, Dowd. Interaction terms in nonlinear models. Health Services Research, 47(1):255-274, 2012.

December 5, 2017: Sensitivity analyses

VanderWeele and Ding. Sensitivity analysis in observational research: Introducing the e-value. Ann Intern Med, 167:268-74, 2017.

Rosenbaum. Design of Observational Studies. Ch 3 pp.65-94 New York: Springer, 2010.

November 7, 2017: Discontinuity designs

Moscoe, Bor, Barnighausen. Regression discontinuity designs are underutilized in medicine, epidemiology, and public health: a review of current and best practice. J Clin Epidemiol, 68:132-143, 2015.

Cattaneo, Idrobo, and Titiunik. A practical introduction to regression discontinuity designs. Cambridge Elements: Quantitative and Computational Methods for Social Science. [May 29, 2017 draft].

October 10, 2017: Instrumental variables

Baiocchi, Cheng, Small. Instrumental variable methods for causal inferenceStatist Med, 33:2297-40, 2014.

Hernan and Robins. Instruments for Causal Inference: An Epidemiologist’s Dream? Epidemiology, 17(4): 360-72, 2006.

September 12, 2017: Matching and weighting methods

Garrido et al. Methods for constructing and assessing propensity scores. HSR,49(5):1701-20, 2014.

King and Nielsen. Why propensity scores should not be used for matching. Working paper. 16 Dec 2016.

May 16, 2017: The trouble with p-values

Hatch, Wise, Rothman. Inappropriate reliance on p-values in medical research. Twitter, May 9, 2017.

Lappe et al. Effect of Vitamin D and calcium supplementation on cancer incidence in older women: a randomized clinical trial. JAMA, 317(12):1234-43, 2017.

Wasserstein and Lazar. The ASA's statement on p-values: Context, process and purpose. The American Statistician, 70:2:129-133, 2016.

April 18, 2017: Algorithms for billing claims data

DuGoff, Walden, Ronk, Palta, Smith. Can claims data algorithms identify the physician of record? Medical Care, 2017.

March 21, 2017: Hospital safety evaluation

Hatfield, Baugh, Azzone, Normand. Regulator loss functions and hierarchical modeling for safety decision making. Medical Decision Making, 2017.

Spiegelhalter, et al. Statistical methods for healthcare regulation: rating, screening and surveillanceJRSSA, 175(1):1-47, 2012.

February 21, 2017: Ethics in machine learning

Corbett-Davies, Pierson, Feller, Goel. A computer program used for bail and sentencing decisions was labeled biased against blacks. It’s actually not that clear. Washington Post, October 17, 2106.

Kleinberg, Luwig, Mullainathan. A guide to solving social problems with machine learning. Harvard Business Review, December 8, 2016.

Angwin and Lawson. Bias in criminal risk scores is mathematically inevitable, researchers say. ProPublica, December 30, 2106.

November 15, 2016: Family leave policies

           Antecol et al. Equal but inequitable: Who benefits from gender neutral tenure clock stopping policies? (Preprint)

          The Upshot. A family-friendly policy that's friendliest to male professors. June 24, 2016.

          The Hardest Science Blog. Don't change your family-friendly tenure extension policy just yet. June 28, 2016

October 18, 2016: Correcting the scientific record, outcome switching

COMPare Project Blog

September 20, 2016: Medical errors

Makary and Daniel. Medical error-- the third leading cause of death in the US. BMJ, 353, 2016. 

Shojania. Re: Medical error-- the third leading cause of death in the US. (Rapid Response)

May 17, 2016: Price Transparency

Desai, Hatfield, Hicks, Chernew, and Mehrotra. Association between availability of a price transparency tool and outpatient spending. JAMA, 315:1874-1881, 2016. 

Whaley, et al. Association between availability of health service prices and payments for these services. JAMA, 312:1670-1676, 2014.

April 19, 2016: Quality Measurement

Porter, Larsson, and Lee. Standardizing patient outcome measurement. NEJM, 374:504-6, 2016.

Casalino et al. US physician practices spend more than $15.4 billion annually to report quality measures. Health Affairs, 35:401-6, 2016.

March 15, 2016: Mortality Trends

Case and Deaton. Rising morbidity and mortality in midlife among white non-Hispanic Americans in the 21st centuryPNAS, 112:15078–83, 2015.

Gelman. What happened to mortality among 45-54-year-old white non-Hispanics? It declined from 1989 to 1999, increased from 1999 to 2005, and held steady after that. Nov 6, 2015.

The Upshot. More details on rising mortality among middle-aged whites. Nov 6, 2015.

February 16, 2016: Reproducibility

Allison, Brown, George, and Kaiser. A tragedy of errors. Nature, 530:27-29, 2016.

Nuzzo. How scientists fool themselves -- and how they can stopNature, 526:182-5, 2015.

November 17, 2015: Model Robustness

Gelman. A Bayesian formulation of exploratory data analysis and goodness-of-fit testingInternational Statistical Review, 71:369-382, 2003.

Refaeilzadeh, Tang, Liu. Cross-Validation. In Encyclopedia of Database Systems. Editors: Özsu and Liu. Springer, 2009.

October 27, 2015: Open Science

Download the slides

Open Science Collaboration. Estimating the reproducibility of psychological science. Science, 349:aac4716, 2015.

Stodden. Reproducing statistical results. Annual Review of Statistics and Its Applications, 2: 1-19, 2015.

September 22, 2015: Simulations

Rutter, Zaslavsky, and Feuer. Dynamic microsimulation models for health outcomes: A review. Medical Decision Making, 31:10-18, 2011.

Hallgren. Conducting simulation studies in the R programming environment. Tutorials in Quantitative Methods for Psychology, 9:43-60, 2013.

Lofland and Ottesen. Simulation in SAS with comparisons to R. Proceedings of the 2015 Western Users of SAS Software Conference.

Thomas Lumley's post on Herd Immunity Simulations (with movies).

August 25, 2015: Multiple Treatment Comparisons

Download the slides

Moore, Neugebauer, van der Laan, and Tager. Causal inference in epidemiological studies with strong confounding. Statistics in Medicine, 31:1380-1404, 2012. 

Salanti, Ades, and Ioannidis. Graphical methods and numerical summaries for presenting results from multiple-treatment meta-analysis: an overview and tutorial. Journal of Clinical Epidemiology,64:163-171, 2011.

July 28, 2015: Health Disparities

Scanlan. Can we actually measure health disparities?Chance, 19:47-51, 2006.

Chetty and Hendren. The impacts of neighborhoods on intergenerational mobility: childhood exposure effects and county-level estimates. 2015.

June 30, 2015: Finding and Accessing Data

Discussed multiple data sources and policies for obtaining access. Summary file will remain a living document.

April 14, 2015: Health Innovation

Discussed ADHD 200, Heritage Health PrizeKaggle, and Health 2.0 Challenges.

March 10, 2015: Difference-in-Differences

Ryan, Burgess, and Dimick. Why we should not be indifferent to specification choices for difference-in-differencesHealth Services Research, 50:1211-1235, 2015.

February 17, 2015: Productivity Growth

Romley, Goldman, and Snood. US hospitals experienced substantial productivity growth during 2002-11Health Affairs, 34:511-518, 2015. 

January 20, 2015: Prediction

Zhao and Weng. Combining PubMed knowledge and EHR data to develop a weighted Bayesian network for pancreatic cancer predictionJournal of Biomedical Informatics, 44:859-68, 2011. 

Rose. Mortality risk score prediction in an elderly population using machine learningAmerican Journal of Epidemiology, 177:443-452, 2013. 

November 13, 2014: Missing Data

Little and Rubin. Causal effects in clinical and epidemiological studies via potential outcomes: Concepts and analytical approachesAnnual Review of Public Health, 21:121-45, 2000. 

White and Carlin. Bias and efficiency of multiple imputation compared with complete-case analysis for missing covariate valuesStatistics in Medicine, 29:2920-31, 2010. 

October 9, 2014: Observational Studies

Madigan,  et al. A systematic statistical approach to evaluating evidence from observational studiesAnnual Review of Statistics and Its Application, 1:11-39, 2014. 

Cook, Shadish, and Wong. Three conditions under which experiments and observational studies produce comparable causal estimates: New findings from within‐study comparisonsJournal of Policy Analysis and Management, 27.4:724-750, 2008. 

September 11, 2014: Propensity Scores

Brooks and Ohsfeldt. Squeezing the balloon: propensity scores and unmeasured covariate balanceHealth Services Research, 48(4): 1487-507, 2013. 

Ali, Groenwold, and Klungel. Propensity score methods and unobserved covariate imbalance: comments on "squeezing the balloon"Health Services Research, 49(3): 1074-82, 2014.