Erin Lake

Instructor of Biostatistics

Co-Director, SM Biostatistics Programs

Director of Student Development

Department of Biostatistics


Dr. Erin (Kammann) Lake is Instructor of Biostatistics, Co-Director of the SM BIO Programs, and the department lead on career development efforts within the Department of Biostatistics at the Harvard T.H. Chan School of Public Health at Harvard University.

Teaching and Advising

Dr. Lake is passionate about teaching, and works to bring statistical enlightenment, and a dynamic, devoted style to her courses and students. Graduate students are inherently at an important juncture along their career and life trajectories.  The teaching, mentoring and advisement of students in the Department of Biostatistics at Harvard, and in the courses she teaches, is a deeply cherished role to Dr. Lake.

Recent courses:

  • BST 210: Applied Regression Analysis (for doctoral and master’s students)
  • BST 254: Special Topics in Biostatistics (co-taught with Paige Williams; for doctoral students)

Other previous courses:

  • Calculus I and II, Pre-calculus, Intro Probability, Advanced Topics in Mathematics and Probability


Dr. Lake’s early training  was in theoretical mathematics, and later in biostatistics.  Her interests and work began in the area of difference and differential equations, and ultimately, after inspirational work around the complexities of modeling Lyme disease and the controversial prophylactic treatment thereof, evolved into the methodological development of topics ranging from mixed and additive models in disease mapping, to dynamic randomizations, and special cases of the Andersen-Gill formulation of the Cox model in clinical trials.

Funded by a National Institute of Allergy and Infectious Diseases (NIAID) training grant awarded by the Department of Biostatistics at HSPH, Dr. Lake studied HIV and infectious disease during her initial doctoral work, and ultimately disease mapping, funded by the National Institute of Environmental Health Sciences (NIEHS).

In her dissertation ‘Geoadditive and Robust Mixed Models‘ with advisor Matt Wand, Dr. Lake laid out the defining properties of the union of additive and mixed models in the context of disease mapping, which provides a likelihood-based, low-rank, generalized framework for accommodating nonlinear covariate effects and spatial correlation.  The Geoadditive Model enjoys countless applications in areas ranging from finance to ecology to medicine and public health, and has received hundreds of citations.


Dr. Lake has extensive industry experience in clinical trial methodology and practice (including but not limited to cluster randomized trials, dynamic randomization schemes, survival modeling, pilot studies), and has been the lead statistician on phase III pivotal trials.

She has consulting experience on a varied scope of application and methods in fields including education and healthcare.  Dr. Lake has worked within a hospital-based consulting group, and was Co-Founder and CEO of a private consulting company.

Career Development

Dr. Lake leads the Career Development Series for the Department of Biostatistics.  The field of biostatistics is currently influenced by a rapidly shifting landscape of tech advancement and high performance computing, and through such, has expanded to include close collaboration with the fields of data science, computational biology, quantitative genetics, and more. The importance of staying abreast of the field, learning collaboration and soft skills, and gleaning insights from those already out in the field, has never been greater.

The Career Development Series provides students, postdocs and faculty a sequence of seminars that delineate the myriad of skills necessary for job, internship, and research project searches, CV/resume and cover letter development, interview prep, and the general caveats and nuances of the field, both within and beyond academia.

Dr. Lake’s introductory seminar, ‘What is Your Biostatistics Parachute?’ is a staple to the seminar series, and explores the various paths a student might take within our rich and technical field.  The series ultimately includes a number of guest speakers and visits from alumnae out in the field across academia, industry, government, nonprofits, consulting, tech and business.

Select Awards

  • Letter of high rating for teaching evaluations, Fall 2020, Harvard TH Chan School of Public Health
  • 2-time HSPH school-wide Teaching Assistant of the Year, Harvard School of Public Health, 1999, 2000
  • Student Paper Award, International Biometrics Society (ENAR), 2000
  • Excellence In Research Award, Association for Women in Mathematics/SIAM, 2001

Select Publications

Birk N, Matsuzaki M, Fung T, Li Y, Batis C, Stampfer M, Deitchler M, Willen W, Fawzi W, Bromage S, Kiera S, Bhupathiraju S*, Lake E* (2021). (* senior author) Exploration of Machine Learning and Statistical Techniques in Development of a Low-Cost Screening Method Featuring the Global Diet Quality Score for Detecting Prediabetes in Rural India. Journal of Nutrition, 151:110S-118S.

Lake, E. (2021). On the Data Frontline: Biostatisticians in the Hospital Research Setting. AMSTAT (STATtr@k). May issue.

Deng W, Liu ZL, Lake E, Coull B (under revision, 2021). Robust Estimation and Testing for Nonlinear Effects using Kernel Machine Ensemble.

Staudenmayer, J, Lake, EE & Wand, MP (2009). Robustness for general design mixed models using the t-distribution. Statistical Modeling, 9:235-255.

Kammann, EE & Wand, MP (2003). Geoadditive ModelsJournal of the Royal Statistical Society, Series C, 52:1-18.

Lake SL, Kammann EE, Klar N, Betensky R (2002). Sample size reestimation in cluster randomization trialsStatistics in Medicine, 21:1337-50.

Cohn SE, Kammann E, Williams P, Currier JS, Chesney MA (2002). Association of adherence to Mycobacterium avium complex prophylaxis and antiretroviral therapy with clinical outcomes in Acquired Immunodeficiency SyndromeClinical Infectious Disease, Apr 15;34(8):1129-36.

French, JL, Kammann, EE and Wand, MP (2001). Semiparametric nonlinear mixed-effects models and their applications. Journal of the American Statistical Association, 96:1285–1288.

Atlas SJ, Chang Y, Kammann E, Keller RB, Deyo RA, Singer DE (2000). Long-term disability and return to work among patients who have a herniated lumbar disc: the effect of disability compensationJournal of Bone and Joint Surgery Am., Jan;82(1):4-15.

Lai F, Kammann E, Rebeck GW, Anderson A, Chen Y, Nixon RA (1999). APOE genotype and gender effects on Alzheimer disease in 100 adults with Down syndromeNeurology, Jul 22;53(2):331-6.

Kelly C, Kammann E, Bak J, Mather T (1999). An improved method for predicting duration of black-legged tick (Ixodes scapularis) attachmentSystematic and Applied Acarology, 1999;4:31–38.

Select Software

Wand, MP, Coull, BA, French, JL, Ganguli, B, Kammann, EE, Staudenmayer, J and Zanobetti, A (2005). SemiPar 1.0. Functions for semiparametric regression corresponding to the book: Ruppert, D., Wand, M.P. and Carroll, R.J. (2003) “Semiparametric Regression”. R package. (


Erin Lake is a lifelong, avid distance runner, and has coached youth running and Nordic skiing in the Boston area since 2010.


Sc.D. Biostatistics, 2001, Harvard University