Skip to main content
. Author manuscript; available in PMC: 2015 Jan 29.
Published in final edited form as: Epidemiology. 2014 Nov;25(6):889–897. doi: 10.1097/EDE.0000000000000160

Figure 1.

Figure 1

Directed acyclic graph showing hypothesized causal relationships among study variables for days k − 1 and k. This graph demonstrates bias in regression stratification methods in estimating the effect of exposure over time (GνHDk−1, GνHDk) on subsequent death when time-varying factors on confounding pathways (Relapsek) may be affected by prior exposure.