Skip to main content

Table 4 Confounding scenarios for indirect ICS effect on BW

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?

association confounded?

Confounding 1 (M1, total)

−513.25

0.2041

no

yes

Confounding 1 (M1,V, total)

−366.72

0.2189

no

no

Confounding 1 (M2, direct)

−0.1645

0.1814

yes

no

Confounding 1 (M2,V, direct)

−0.1614

0.1823

yes

no

Confounding 1 (M3, total)

1.7763

0.0017

no

yes

Confounding 1 (M3,V, total)

1.3296

0.0018

no

no

Confounding 1 (M4, direct)

−0.0011

0.0015

yes

no

Confounding 1 (M4,V, direct)

−0.0001

0.0016

yes

no

Confounding 2 (M1, total)

−366.44

0.2292

no

no

Confounding 2 (M1,V, total)

−366.56

0.1973

no

no

Confounding 2 (M2, direct)

24.232

0.1690

no

yes

Confounding 2 (M2,V, direct)

−0.1271

0.1694

yes

no

Confounding 2 (M3, total)

1.2508

0.0014

no

no

Confounding 2 (M3,V, total)

1.3351

0.0014

no

no

Confounding 2 (M4, direct)

0.0008

0.0013

yes

no

Confounding 2 (M4,V, direct)

0.0010

0.0013

yes

no

Confounding 3 (M1, total)

−406.67

0.1950

no

yes

Confounding 3 (M1,V, total)

−366.72

0.2189

no

no

Confounding 3 (M2, direct)

−40.136

0.1714

no

yes

Confounding 3 (M2,V, direct)

−0.1614

0.1823

yes

no

Confounding 3 (M3, total)

1.4315

0.0021

no

yes

Confounding 3 (M3,V, total)

1.2931

0.0023

no

no

Confounding 3 (M4, direct)

0.2212

0.0013

no

yes

Confounding 3 (M4,V, direct)

0.0006

0.0014

yes

no

Confounding 4 (M1, total)

−553.24

0.2109

no

yes

Confounding 4 (M1,V, total)

−366.72

0.2189

no

no

Confounding 4 (M2, direct)

−10.382

0.1854

no

yes

Confounding 4 (M2,V, direct)

−0.1614

0.1823

yes

no

Confounding 4 (M3, total)

1.8558

0.0016

no

yes

Confounding 4 (M3,V, total)

1.3321

0.0016

no

no

Confounding 4 (M4, direct)

0.2212

0.0013

no

yes

Confounding 4 (M4,V, direct)

0.0006

0.0014

yes

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; M3: 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
Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us