. Author manuscript; available in PMC: 2021 Dec 13.

Published in final edited form as: Behav Ther. 2014 Sep 18;46(2):257–271. doi: 10.1016/j.beth.2014.09.006

Table 5.

Generalized Estimating Equations Analysis Using a Gamma Distribution of the Lagged Effects of Body-, Eating-, and Exercise-Related Social Comparison and Body Surveillance on Body Dissatisfaction in a Single Model Controlling for Negative Affect

Parameter Estimates	B	SE	Wald χ²	df	p
Outcome variable: body dissatisfaction, N_{Level 1} = 8742, N_{Level 2} = 232
Intercept	2.00	.25	63.60	1	<.001
Lagged Body-related Social Comparison (person-mean centered)	.0002	.001	.10	1	.757
Body-related Social Comparison (person means)	.04	.01	35.27	1	<.001
Lagged Eating-related Social Comparison (person-mean centered)	.002	.001	6.63	1	.010
Eating-related Social Comparison (person means)	−.01	.01	1.74	1	.188
Lagged Exercise-related Social Comparison (person-mean centered)	.001	.001	2.92	1	.087
Exercise-related Social Comparison (person means)	−.00003	.01	.00002	1	.996
Lagged Body Surveillance (person-mean centered)	.02	.01	2.92	1	.087
Body Surveillance (person means)	.19	.06	9.27	1	.002
Time	.001	.0002	21.36	1	<.001
Negative Affect (person-mean centered)	.004	.01	.91	1	.339
Negative Affect (person means)	−.01	.02	.31	1	.576
(Scale)	.89
Pseudo-R² = .221