Work

Five Authors Reply

Year: 2015

Type: letter

Abstract: We appreciate the interest of Smits et al. (1) in our study (2). They raised an interesting point regarding possible “index event bias,” which is essentially a form of collider stratification bias that becomes possible when studying recurrent conditions. This can result in bias toward the null in crude associations between the risk factor of interest and disease outcome. One of the strengths of our study was our ability to adjust for multiple possible risk factors; however, the ability to adjust for unknown risk factors is a limitation in all epidemiologic studies and not only in this setting. Further, we agree with a point made by the authors in a prior publication (3); namely, the methods currently available to address index event bias in research related to the causal etiology of recurrent events are lacking, and additional methodological work is still needed to adequately address this issue.

Source: American Journal of Epidemiology

DOI: 10.1093/aje/kwv277

Authors: Katherine L. Grantz, Stefanie N. Hinkle, Pauline Mendola, Lindsey A. Sjaarda, Paul S. Albert

Institutions: National Institutes of Health, Eunice Kennedy Shriver National Institute of Child Health and Human Development

Language: French

Topic: Statistical Methods in Epidemiology

Subfield: Statistics and Probability

Field: Mathematics

Domain: Physical Sciences

SDG: Good health and well-being

Open Access status: green

Funders: National Institutes of Health, National Institute of Child Health and Human Development, Eunice Kennedy Shriver National Institute of Child Health and Human Development