Skip to main content
Fig. 2 | BMC Medical Research Methodology

Fig. 2

From: A comparison of methods to estimate the survivor average causal effect in the presence of missing data: a simulation study

Fig. 2

Identification of principal strata dependant on observed exposure and survival status. Under the assumption of monotonicity, there are no defiant-survivors; all survivors who had low iron intake at baseline can be identified as always-survivors but survivors who had high iron intake at baseline could be always-survivors or compliant-survivors. When the monotonicity assumption has been violated, participants who survive following low iron intake may be always-survivors or defiant-survivors (grey stripes). White boxes represent survivors and grey boxes represent those who do not survive

Back to article page