Skip to main content

Table 6 Confounding scenarios for indirect ICS effect on BW with heterogeneity of errors

From: On the use of the outcome variable “small for gestational age” when gestational age is a potential mediator: a maternal asthma perspective

Scenario
(model, interpretation of effect)
mean se null ICS effect?
Confounding 1 (M1, total) −513.28 0.2388 no
Confounding 1 (M1,V, total) −366.76 0.2579 no
Confounding 1 (M2, direct) −0.2363 0.2328 yes
Confounding 1 (M2,V, direct) −0.2306 0.2353 yes
Confounding 1 (M3, total) 1.5614 0.0015 no
Confounding 1 (M3,V, total) 1.1601 0.0016 no
Confounding 1 (M4, direct) −0.0011 0.0015 yes
Confounding 1 (M4,V, direct) −0.0001 0.0016 yes
Confounding 2 (M1, total) −366.46 0.2600 no
Confounding 2 (M1,V, total) −366.58 0.2312 no
Confounding 2 (M2, direct) 24.188 0.2168 no
Confounding 2 (M2,V, direct) −0.1823 0.2167 yes
Confounding 2 (M3, total) 1.0759 0.0012 no
Confounding 2 (M3,V, total) 1.1475 0.0012 no
Confounding 2 (M4, direct) 0.0125 0.0013 no
Confounding 2 (M4,V, direct) 0.0127 0.0013 no
Confounding 3 (M1, total) −406.71 0.2335 no
Confounding 3 (M1,V, total) −366.76 0.2593 no
Confounding 3 (M2, direct) −40.210 0.2226 no
Confounding 3 (M2,V, direct) −0.2394 0.2378 yes
Confounding 3 (M3, total) 1.3095 0.0017 no
Confounding 3 (M3,V, total) 1.1839 0.0019 no
Confounding 3 (M4, direct) 0.1738 0.0014 no
Confounding 3 (M4,V, direct) 0.0050 0.0016 no
Confounding 4 (M1, total) −553.28 0.2444 no
Confounding 4 (M1,V, total) −366.76 0.2579 no
Confounding 4 (M2, direct) −10.454 0.2361 no
Confounding 4 (M2,V, direct) −0.2306 0.2353 yes
Confounding 4 (M3, total) 1.6301 0.0013 no
Confounding 4 (M3,V, total) 1.1518 0.0014 no
Confounding 4 (M4, direct) 0.1859 0.0014 no
Confounding 4 (M4,V, direct) 0.0120 0.0015 no
  1. Legend. Mean of the estimated exposure (ICS) effect (mean difference or log odds ratio) on the outcome (BW, LBW or SGA) based on 1000 samples of size 20,000, with Monte Carlo standard error (se)
  2. Confounding Scenario 1: confounder between ICS and GA; Confounding Scenario 2: confounder between GA and BW; Confounding Scenario 3: confounder between ICS and BW; Confounding Scenario 4: confounder between ICS, GA and BW
  3. M1: BW ~ ICS; M2: BW ~ ICS + GA; M 3 : LBW ~ ICS; M4: SGA ~ ICS;
  4. null ICS effect = yes if 0 mean ± 1.96se
  5. Models subscripted by V additionally include the V variable in the regression model
  6. Abbreviations: BW birth weight, GA gestational age, ICS inhaled corticosteroids, LBW low birth weight, SGA small for gestational age