142nd APHA Annual Meeting and Exposition

Annual Meeting Recordings are now available for purchase

Methodology and Causality in Religion and Health Research

142nd APHA Annual Meeting and Exposition (November 15 - November 19, 2014): http://www.apha.org/events-and-meetings/annual
Tuesday, November 18, 2014 : 9:26 AM - 9:44 AM

Tyler VanderWeele, PhD , Department of Epidemiology and Biostatistics, Harvard School of Public Health, Boston, MA
The talk will survey some of the methodological challenges in assessing causality in religion and health research. While the field has seen increasing use of better longitudinal designs in assessing the relationship between religion and health, for certain questions considerable methodological challenges remain. For example, while it is the case that religious participation is longitudinally associated with less depression, it is also the case that those who become depressed are more likely to cease attending religious services. Such feedback, with causality in both directions, renders cross-section data useless, and requires causal modeling techniques, such as marginal structural models, to adequately assess the extent of the effects in both directions. Analyses using marginal structural models with the Nurses' Health Study data will be presented in studying this feedback between religious service attendance and depression. Another set of methodological challenges arises when interest lies in studying mechanisms governing the relationship between religious participation and health outcomes. The relevance of the literature on causal mediation analysis to religion and health research will be discussed generally, and analyses will be presented examining the mechanisms for the religion-mortality relationship in the Nurses' Health Study data.

Learning Areas:

Biostatistics, economics
Diversity and culture
Public health or related research

Learning Objectives:
Analyze the challenges involved in evaluating the extent that religious/spiritual factors exert a causal effect on health.

Keyword(s): Religion, Biostatistics

Presenting author's disclosure statement:

Qualified on the content I am responsible for because: I have a doctorate in biostatistics, have served as associate editor for multiple statistics journals, and have published multiple refereed articles on causal relations, and have a book on the topic in press at Oxford University Press. Religion and health is also an area in which I have published, and where I teach a seminar.
Any relevant financial relationships? No

I agree to comply with the American Public Health Association Conflict of Interest and Commercial Support Guidelines, and to disclose to the participants any off-label or experimental uses of a commercial product or service discussed in my presentation.