### Mediator model Call: glm(formula = bili_bin ~ trt, family = binomial(link = "logit"), data = data) Coefficients: Estimate Std. Error z value Pr(>|z|) (Intercept) 0.08577 0.38245 0.224 0.823 trt -0.08577 0.24091 -0.356 0.722 (Dispersion parameter for binomial family taken to be 1) Null deviance: 382.49 on 275 degrees of freedom Residual deviance: 382.36 on 274 degrees of freedom AIC: 386.36 Number of Fisher Scoring iterations: 3 ### Outcome model Call: glm(formula = platelet ~ trt + bili_bin + trt:bili_bin, family = poisson(link = "log"), data = data) Coefficients: Estimate Std. Error z value Pr(>|z|) (Intercept) 5.48429 0.01640 334.308 < 2e-16 *** trt 0.09494 0.01013 9.375 < 2e-16 *** bili_bin 0.09973 0.02379 4.191 2.77e-05 *** trt:bili_bin -0.15251 0.01497 -10.190 < 2e-16 *** --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 (Dispersion parameter for poisson family taken to be 1) Null deviance: 9286.7 on 275 degrees of freedom Residual deviance: 8861.7 on 272 degrees of freedom AIC: 10894 Number of Fisher Scoring iterations: 4 ### Mediation analysis est se Z p lower upper cde -0.142288731 0.019142202 -7.4332477 1.059153e-13 -0.179806758 -0.10477070 pnde 0.030090423 0.011381342 2.6438379 8.197189e-03 0.007783403 0.05239744 tnie 0.006394558 0.017929837 0.3566434 7.213588e-01 -0.028747278 0.04153639 tnde 0.034738909 0.013527367 2.5680467 1.022734e-02 0.008225758 0.06125206 pnie 0.001746071 0.004904757 0.3559955 7.218439e-01 -0.007867075 0.01135922 te 0.036484981 0.017050765 2.1397856 3.237210e-02 0.003066095 0.06990387 pm 0.177912755 0.435706272 0.4083319 6.830300e-01 -0.676055847 1.03188136 exp(est) exp(lower) exp(upper) cde 0.8673708 0.8354316 0.900531 pnde 1.0305477 1.0078138 1.053794 tnie 1.0064150 0.9716620 1.042411 tnde 1.0353494 1.0082597 1.063167 pnie 1.0017476 0.9921638 1.011424 te 1.0371587 1.0030708 1.072405 pm NA NA NA Evaluated at: avar: trt a1 (intervened value of avar) = 2.3 a0 (reference value of avar) = 1.1 mvar: bili_bin m_cde (intervend value of mvar for cde) = 1.4 cvar: c_cond (covariate vector value) = Note that effect estimates can vary over m_cde and c_cond values when interaction = TRUE.