Journal of Obesity

Research Article

The Association of Pension Income with the Incidence of Type I Obesity among Retired Israelis

Table 13

Random-Effect Regression 2015-2016: stratification by Overweight (BMI ≥ 25), Type I (BMI ≥ 30), and Type II (BMI ≥ 35) obesity among males above 67 years.


Variables	(1)	(2)	(3)	(4)	(5)	(6)
	Full	Stepwise	Full	Stepwise	Full	Stepwise
	BMI25	BMI25	BMI30	BMI30	BMI35	BMI35

Constant	1.4435	1.3911	0.3330	0.2715	0.0424	0.0256
	(0.0002)	(0.0001)	(0.3526)	(<0.0001)	(0.8479)	(0.0088)
INCPENS ÷ (10⁵)	0.0018	—	0.0015	—	0.0005	−
	(0.4404)	—	(0.4225)	—	(0.5758)	−
Owner	0.0025	—	−0.0342	—	0.0274	0.0255
	(0.9489)	—	(0.3460)	—	(0.0400)	(0.0431)
Books	−0.0535	—	0.0013	—	0.0467	—
	(0.1509)	—	(0.9875)	—	(0.5461)	—
Car	0.0050	—	0.0610	0.0641	0.0074	—
	(0.8735)	—	(0.0897)	(0.0469)	(0.4648)	—
Age	−0.0103	−0.0099	0.0003	—	−0.0004	—
	(0.0328)	(0.0450)	(0.9494)	—	(0.8297)	—
Academic	−0.0579	—	−0.1014	−0.0993	0.0225	—
	(0.2690)	—	(0.0118)	(0.0106)	(0.6095)	—
HHSIZE	0.0051	—	0.0059	—	0.0101	—
	(0.7859)	—	(0.7551)	—	(0.4697)	—
Married	0.0126	—	−0.0442	—	−0.0489	—
	(0.9057)	—	(0.7685)	—	(0.3894)	—
Divorced	−0.0515	—	−0.1623	—	−0.0538	—
	(0.6554)	—	(0.3060)	—	(0.3428)	—
Widow	−0.0101	—	−0.1004	—	−0.0504	—
	(0.9233)	—	(0.5222)	—	(0.3341)	—
IMM_EUROPE_AMERICA	0.0718	—	−0.0767	−0.0899	−0.0197	—
	(0.1637)	—	(0.0821)	(0.0398)	(0.4167)	—
IMM_ASIA_AFRICA	−0.0450	—	−0.1163	−0.1199	−0.0036	—
	(0.4567)	—	(0.0245)	(0.0200)	(0.8975)	—
OVERALL_HEALTH	0.0027	—	−0.0345	—	−0.0164	—
	(0.9232)	—	(0.2439)	—	(0.3300)	—
Gender	Males	Males	Males	Males	Males	Males
Age	Above 67	Above 67	Above 67	Above 67	Above 67	Above 67
Observations	850	850	850	850	850	850
R-squared	0.0255	0.00900	0.0560	0.0370	0.0157	0.00573
Households	466	466	466	466	466	466
Wald chi²: all coef. equals zero	13.48	4.020	25.09	19.67	8.487	4.091
Individual effect F-Statistics	7.13	7.07	4.58	4.69	13.38	11.06
Variance inflation factor (VIF)	2.78	1.00	2.78	1.25	2.78	1.00

Note. The table reports the estimation results of equation (3) for the group of retired men estimated via the random effect regression. The results of individual-effect F-statistics justify this procedure, which includes the individual effect dummies of households. The dependent variables are BMI25, BMI30, BMI35, and dummy variables, which equal one for Overweight (BMI ≥ 25), Type I (BMI ≥ 30), and Type II Obesity (BMI ≥ 35) and zero otherwise. The stepwise procedure gradually omits variables with coefficients for whom . Variance inflation factor (VIF) is a measure for collinearity among independent variables. VIF < 10 implies low collinearity. Robust p values are given in parentheses. . . .