RTI uses cookies to offer you the best experience online. By clicking “accept” on this website, you opt in and you agree to the use of cookies. If you would like to know more about how RTI uses cookies and how to manage them please view our Privacy Policy here. You can “opt out” or change your mind by visiting: http://optout.aboutads.info/. Click “accept” to agree.
Estimating the effect of preventive services with databases of administrative claims
Reasons to be concerned
Garcia de Albeniz Martinez, X., Hsu, J., Bretthauer, M., & Hernán, M. A. (2019). Estimating the effect of preventive services with databases of administrative claims: Reasons to be concerned. American Journal of Epidemiology, 188(10), 1764-1767. https://doi.org/10.1093/aje/kwz049
We recently used Medicare administrative claims to emulate a target trial of screening colonoscopy and 8-year risk of colorectal cancer in the elderly (1). In his accompanying commentary, which appears in this issue of the Journal, Weiss (2) claims that our effect estimates are biased because we 1) included cancer cases detected by screening colonoscopy and 2) did not censor individuals in the no-colonoscopy group if they later received a screening colonoscopy. Here we first respond to Weiss’s criticisms and then focus on what we suspect to be a point of agreement with Weiss: A key...