Figure 3From: Detecting and correcting the bias of unmeasured factors using perturbation analysis: a data-mining approach Results of the perturbation analysis for the hypothetical population in Table 1 (A: perturbation test for positive confounding; B: perturbation test for negative confounding; C: perturbation adjustment for positive confounding; D: perturbation adjustment for negative confounding; solid lines: f PV  = 0.05; dotted lines: f PV  = 0.025; horizontal lines: standardized relative risks). Back to article page