### Mediator model Call: glm(formula = bili_bin ~ trt + age + male + stage, family = binomial(link = "logit"), data = data) Coefficients: Estimate Std. Error z value Pr(>|z|) (Intercept) -1.53024 0.85116 -1.798 0.07220 . trt -0.17117 0.25982 -0.659 0.51003 age -0.01386 0.01299 -1.067 0.28610 male 1.33046 0.43911 3.030 0.00245 ** stage 0.74640 0.16356 4.563 5.03e-06 *** --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 (Dispersion parameter for binomial family taken to be 1) Null deviance: 382.49 on 275 degrees of freedom Residual deviance: 349.60 on 271 degrees of freedom AIC: 359.6 Number of Fisher Scoring iterations: 4 ### Outcome model Call: lm(formula = alk_phos ~ trt + bili_bin + trt:bili_bin + age + male + stage, data = data) Residuals: Min 1Q Median 3Q Max -2024.9 -1078.3 -594.4 44.3 12074.4 Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) 2140.824 918.685 2.330 0.0205 * trt -52.733 359.220 -0.147 0.8834 bili_bin 565.487 816.683 0.692 0.4893 age -4.433 12.830 -0.346 0.7300 male -15.412 407.373 -0.038 0.9698 stage -49.156 159.301 -0.309 0.7579 trt:bili_bin 42.041 510.197 0.082 0.9344 --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Residual standard error: 2116 on 269 degrees of freedom Multiple R-squared: 0.02133, Adjusted R-squared: -0.0004967 F-statistic: 0.9772 on 6 and 269 DF, p-value: 0.441 ### Mediation analysis est se Z p lower upper cde 7.3490099 638.701879 0.01150617 0.9908196 -1244.483670 1259.18169 pnde -32.9351555 318.191908 -0.10350721 0.9175604 -656.579835 590.70952 tnie -33.1774995 56.236639 -0.58996235 0.5552159 -143.399286 77.04429 tnde -35.4628271 312.964803 -0.11331251 0.9097828 -648.862569 577.93691 pnie -30.6498279 49.883072 -0.61443344 0.5389289 -128.418853 67.11920 te -66.1126550 318.108265 -0.20783067 0.8353612 -689.593397 557.36809 pm 0.5018328 2.489371 0.20159023 0.8402371 -4.377244 5.38091 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: age male stage c_cond (covariate vector value) = 50 1 2 Note that effect estimates can vary over m_cde and c_cond values when interaction = TRUE. ### Re-evaluation at c_cond = cmean est se Z p lower upper cde 7.3490099 638.701879 0.01150617 0.9908196 -1244.483670 1259.181690 pnde -37.7519518 310.711544 -0.12150161 0.9032937 -646.735388 571.231484 tnie -33.9211917 57.035087 -0.59474252 0.5520156 -145.707909 77.865525 tnde -40.3362826 311.210717 -0.12961084 0.8968743 -650.298079 569.625514 pnie -31.3368609 50.556449 -0.61983904 0.5353638 -130.425680 67.751958 te -71.6731435 314.416441 -0.22795609 0.8196804 -687.918045 544.571758 pm 0.4732762 2.104913 0.22484353 0.8221010 -3.652278 4.598831