Skip to main content
. Author manuscript; available in PMC: 2018 Oct 1.
Published in final edited form as: Menopause. 2017 Oct;24(10):1190–1199. doi: 10.1097/GME.0000000000000897

Table 3.

Coefficients for moderated mediation models with BMI as outcome. N = 815.

Predictor Variables Outcome Variables
M (Stress Eating) Y (BMI)
Coeff. SE p Coeff. SE p
Figure 1
 Constant 2.4 0.8 < .05 17.9 2.8 < .001
 X (Depressive Symptoms) −0.1 0.1 0.3 −0.4 0.4 0.3
 M (Stress Eating) ––– ––– ––– 0.6 0.4 0.1
 W (Menopausal Status) −0.3 0.2 0.2 −2.2 0.2 0.1
 Depressive Symptoms x Status ––– ––– ––– 0.2 0.2 0.4
 Stress Eating x Status 0.2 0.1 < .05 0.3 0.2 0.2
 C1 Self-Rated Health 0.3 0.1 < .001 2.0 0.2 < .001
 C2 Annual Income 0.0 0.0 0.1 0.0 0.0 0.1
 C3 Race 0.0 0.1 0.7 −0.1 0.2 0.4
 C4 Age 0.0 0.0 0.2 0.1 0.1 < .05
R2 = 0.1 R2 = 0.2
F(7, 765) = 6.3, p < .001 F(9, 763) = 25.4, p < .001
a

Labels within the table reflect the following: X refers to the independent variable (depressive symptoms), Y refers to the dependent variable (BMI), M refers to the mediator (stress eating), W refers to the moderator (menopausal status), and Cx refer to covariates (self-rated health, annual income, race, age).

b

p values in bold indicate a statistically significant effect.

c

“Status” in the “Depressive Symptoms x Status” and “Stress Eating x Status” refers to menopausal status (W).