The National Institutes of Health (NIH) Office of Behavioral and Social Sciences Research (OBSSR) invites you to attend the NIH OBSSR Methodology Seminar: Predictive Modeling for Behavioral and Social Sciences Health Research on Friday, October 12, 2018, from 9:00 am to 4:00 pm on the NIH main campus in Bethesda, MD (bldg. 35A, room 610).

Registration
Free registration for this event is required. This meeting will not be live webcast.

View the seminar agenda.

View the speakers' biographies.

Objective
This one-day methodology seminar sponsored by the NIH OBSSR will showcase principles and techniques for prediction modeling from machine learning via specific case examples presented by scientists who are applying predictive algorithms to health-related behavioral and social sciences data. This seminar is intended for scientific program and review officers and other interested NIH staff, fellows, or intramural scientists engaged in evaluating research proposals or conducting research featuring predictive algorithms. Attendees will gain a broad understanding and appreciation for the capabilities of prediction modeling to advance research in health by complementing the more traditional and exclusive focus on explanation. This workshop will include a public access video archive. The seminar will not be live webcast. In person attendance is encouraged.

Background
Behavioral and social science research in health funded by the NIH historically has been concerned with explaining the causal mechanisms that give rise to behavior. Under this tradition the primary focus is investigating mediating and moderating variables that explain attitudes, beliefs, behaviors and health outcomes in observational studies, field experiments, and randomized clinical trials. This near-total emphasis on explaining the causes of health behavior has led to research programs that offer intricate theories of mechanisms but that have little ability to predict future behaviors in the general population with any appreciable accuracy.

Principles and techniques from machine learning may help health behaviors research become more predictive, and in so doing, may generate theories about social and behavioral aspects of health to inform our causal experiments. In social science disciplines outside of health research, where machine learning has been more readily applied, a field of “computational social science” is growing and beginning to reverse the traditional bias against predictive modeling. The addition of prediction models as analytic tools to complement pure explanatory statistical models may lead to better, more replicable behavioral and social science health research.

Speakers
Jake Hofman, Ph.D., Microsoft Research
Matthew Salganik, Ph.D., Princeton University
Emily Putnam-Hornstein, Ph.D., University of Southern California
Ziad Obermeyer, M.D., University of California Berkeley

For more information, please contact: Elizabeth Ginexi, Ph.D., NIH/OBSSR, at Lginexi@mail.nih.gov.

Meeting Venue
National Institutes of Health
Porter Neuroscience Research Center
Building 35A, Room 610
9000 Rockville Pike
Bethesda, MD 20892

Lunch and refreshments will be on your own. Located within building 35 is a dining center that offers food and beverages.

Getting to the Building 35A (Visitor Information)
All visitors must enter the NIH campus through the NIH Gateway Center, located adjacent to the Medical Center Metro Station at the South Drive entrance to campus from Rockville Pike / Wisconsin Avenue (Route 355). You will be asked to submit to a vehicle or personal inspection. Visitors will be required to show one (1) form of identification (a government-issued photo ID-driver's license, passport, green card, etc.) and to state the purpose of their visit.

Please note: visitor parking is limited at NIH. Visitors are encouraged to use public transportation such as the Metrorail subway system which has a convenient stop (Medical Center) on the NIH campus. Visit the "Metro" site for information on fares and schedules.

For visitors arriving in vehicles, on motorcycles or bicycles, the Gateway Vehicle Inspection Station (Building 66A), provides multiple inspection lanes and allows visitors to go through inspection and get a visitor badge in one centralized, efficient process. Vehicles enter the Gateway Center complex through a new roadway, "NIH Gateway Drive," just south of the intersection of the previous visitor entrance at South Drive and Rockville Pike. Vehicles that choose to bypass parking in MLP-11 will go through inspection and enter campus at Center Drive near the National Library of Medicine. (See Gateway Map)

Following the security process, you can either walk to Building 35A, or catch the NIH campus (red line) shuttle. If you are taking the shuttle you will get off at the Building 35/36/37 stop, which is approximately a 10-minute ride. From there, walk to Building 35A. You will enter on the ground floor of the building. Room 610 is on that floor.

Visit the NIH Visitor’s Center for more information about the NIH security process, visitor’s parking, and parking fares.

Accommodations
Individuals with disabilities who need reasonable accommodations to participate in the event should contact OBSSRNews@mail.nih.gov.