Reader Comments

Post a new comment on this article

The original authors did the same thing

Posted by droodman on 10 May 2012 at 21:07 GMT

Given the concerns about Lu and colleagues' model choice, we repeated the analysis using an alternative statistical model to assess the robustness of the relationship between DAH and GHE-S. We used ordinary least squares regression with country fixed effects, clustered by country, for the main model estimation of the association between DAH and GHE-S.
http://plosmedicine.org/article/info:doi/10.1371/journal.pmed.1001214#article1.body1.sec3.p3

The implication here is that this alternative estimator is an innovation. But the original authors did it too: "To test the sensitivity of our findings from the ABBB model, we also used a fixed-effects model with robust SEs..." The only apparent difference is small: here the standard errors are clustered by country.

No competing interests declared.