McLean Hospital 115 Mill Street Belmont, MA 02478
Garrett M. Fitzmaurice, ScD, is the director of the Psychiatric Biostatistics Laboratory at McLean Hospital, and a professor of psychiatry at Harvard Medical School (HMS). As a senior academic biostatistician, Dr. Fitzmaurice has research interests in statistical methodology and collaborative projects in mental health. His principal achievements in statistical research have been to develop methodology for longitudinal analysis, missing data, and psychiatric epidemiology.
As director of the Psychiatric Biostatistics Laboratory, Dr. Fitzmaurice is integrally involved in projects with psychiatric researchers at McLean and HMS. Working collaboratively, he contributes to the design and analysis of studies of the longitudinal course and outcomes of patients with borderline personality disorder, to studies of treatment interventions for patients with co-occurring bipolar and substance use disorders, and to studies of sensitive periods in brain development and depression. He also provides statistical mentoring to numerous junior investigators at McLean.
Biostatistics is key to the rigorous research for which McLean Hospital is known. Founded in 2007 and led by Dr. Fitzmaurice, the Psychiatric Biostatistics Laboratory collaborates with investigators across McLean’s research programs from the early stages of developing grant proposals through to the publication of findings. Dr. Fitzmaurice’s expertise includes experimental study design, statistical methodologies, and the analysis and interpretation of results.
Short-term biostatistical support is available to McLean investigators through the lab’s biostatistical consulting service.
In addition, Dr. Fitzmaurice’s group pursues their own research interests in statistical methods. These include methods for analyzing longitudinal data (e.g., repeated measures of depression on individuals over time) and social network data, methods for causal mediation analysis (e.g., methods to better understand the mechanism of action through which a treatment affects some mental health outcome of interest), general missing data problems, and methods for detecting and adjusting for overdispersion (i.e., adjusting for the presence of greater variability in a data set than would be expected based on a chosen statistical model for the data). The lab’s research in psychiatric epidemiology has concentrated on methodological problems surrounding the use of multiple informant data (e.g., parents’, teacher’s and child’s reports of a child’s own levels of anxiety) in mental health surveys.
Dr. Fitzmaurice and his staff develop statistical collaborations with McLean Hospital investigators on a wide variety of clinical and basic research projects in psychiatry and neuroscience. The following are examples of collaborative projects.
Over two decades, McLean scientists have built a rich database that is advancing the understanding of borderline personality disorder. Statistical analysis of these data is helping to clarify the factors affecting outcomes and the presentation of symptoms over time.
Using a factorial design, the lab has collaborated on a study of alternative interventions for alcohol abuse in TB patients, which examines both behavioral and pharmacological interventions simultaneously. This is an efficient and cost-effective approach in terms of sample size, enabling more than one intervention to be assessed in the same study participants.
Using novel causal mediation analysis approaches, the lab has examined the mediating and interactive role of symptoms and side effects in explaining the effect of antipsychotics on social functioning among schizophrenic patients. These analytic methods can provide insights on the complex interactions between patients’ symptoms improvements and side effects that commonly occur and thereby better inform clinical practice and new drug development.
Zanarini MC, Frankenburg FR, Wedig MM, Fitzmaurice GM. Cognitive experiences reported by patients with borderline personality disorder and axis II comparison subjects: a 16-year prospective follow-up study. American Journal of Psychiatry 2013;170:671-9.
McHugh RK, Kaufman JS, Frost KH, Fitzmaurice GM, Weiss RD. Positive affect and stress reactivity in alcohol-dependent outpatients. Journal of Studies on Alcohol and Drugs 2013;74:152-7.
Fitzmaurice GM, Lipsitz SR, Arriaga A, Sinha D, Greenberg C, Gawande AA. Almost efficient estimation of relative risk regression. Biostatistics 2014;15(4):745-56.
SAS, SPSS, and STATA macros for mediation analysis allowing for exposure-mediator interaction and non-continuous outcome or mediator.
SAS macro for mediation analysis allowing for exposure-mediator interaction and failure time outcome.
Fitzmaurice GM, Davidian M, Verbeke G, Molenberghs G., (eds.) Longitudinal data analysis: a handbook of modern statistical methods. London: Chapman & Hall/CRC Press, 2008.
Fitzmaurice GM, Laird NM, Ware JH. Applied longitudinal analysis, 2nd ed. New Jersey: Wiley, 2011.
Molenberghs G, Fitzmaurice GM, Kenward MG, Tsiatis A, Verbeke G. Handbook of missing data methodology. London: Chapman & Hall/CRC Press, 2014.
Belmont campus - North Belknap, Room 309