Skip to main content
. Author manuscript; available in PMC: 2016 May 1.
Published in final edited form as: Epidemiology. 2015 May;26(3):414–420. doi: 10.1097/EDE.0000000000000279

Figure 3.

Figure 3

Effect estimates, as published and bias-adjusted, based on the median of four prior studies comparing conventional to atypical antipsychotic and risk of mortality in the elderly

1. The estimated proportion of defiers was 10%; the estimated proportion of compliers was 34%. Two of the four studies provided information to estimate the proportion of compliers minus the proportion of defiers assuming the proposed instrument was valid: in one study, this was 14%, and in the other it was 30%.