Skip to main content
. Author manuscript; available in PMC: 2018 Apr 19.
Published in final edited form as: Soc Sci Med. 2017 Jul 31;189:145–151. doi: 10.1016/j.socscimed.2017.07.004

Table 2.

Multilevel models testing exposure to violence on daily obesogenic behaviors.

Statistic Daily Obesogenic Outcomes
Unhealthy Dietary Consumption Feeling Tired Physically Active
Fixed Effects (intercepts, slopes) b (SE) OR b (SE) OR b (SE) OR
 Exposure to Violence (ETV) 0.12**(0.05) 0.03 0.46** (0.16) 1.58 0.48** (0.14) 1.61
 Percentage of Days ETV (Person Level) 0.002 (0.004) 0.02 ?0.002 (0.01) 1.00 0.002 (0.01) 1.00
 Intercept 1.24*** (0.05) – 0.57*** (0.14) 1.77 0.94*** (0.13) 2.57
Random Effects (variances, covariances) Estimate SE Estimate SE Estimate SE
 Intercept 0.41*** 0.05 2.45*** 0.36 2.00*** 0.30
 Autocorrelation 0.15*** 0.02 0.11*** 0.02 0.17*** 0.02
 Residuala 0.70*** 0.02 0.87+ 0.85+
Variance Explained Estimate Estimate Estimate
 R2f 0.2% 0.1% 0.3%
 R2fr 39.4% 36.3% 29.0%

Note. OR=Odds ratio from a multilevel logistic model. b = unstandardized logit regression coefficient, VAR = variance parameter, COV = covariance parameter, CORR = correlation. R2f = Pseudo R2 for full model using fixed effects; R2fr = Pseudo R2 for full model using fixed and random effects.

***

p < 0.001,

**

p < 0.01,

*

p < 0.05.

a

For logistic models, the residual is a dispersion parameter tested against 1. Models where the 95% confidence interval for the dispersion parameter does not include 1 are marked with a +.