The cause and effect problem: Is there mutual obesity among Arab Israeli couples?

Abstract

The influence of the health-related behavior of one spouse on that of the other is an important research question with public policy reprecussions. Yet, we are unaware of any previous study, which considered endogeneity problems between couples. Moreover, only a few studies considered ethnic origin differences among couples. Based on the 2016 wave of the Israeli longitudinal survey, we observe the cross-sectional correlation between the married couples' BMI, age, and accumulated wealth. The BMI (= [Formula: see text]) is a conventional measure of obesity, where BMI≥25 is considered overweight. Using a 3SLS methodology (in an effort to correct the endogeneity problem associated with BMI couples), the analysis tests the mutual obesity hypothesis among married couples. This hypothesis states that the BMI of the male influences that of a female and vice versa. Results indicate that on the one hand, a one-percent BMI increase among Arab Israeli males is associated with a projected 0.969 percent BMI increase among Arab Israeli females (p = 0.017); and in the case that an Arab Israeli male suffers from overweight, the projected probability of his Arab Israeli female counterpart to suffer from overweight as well rises (p = 0.050). On the other hand, one cannot reject the null hypothesis that projected BMI of the Arab Israeli male is unaffected by that of his Arab Israeli female counterpart (p = 0.907 and p = 0.853). As for the Jewish Israeli population, in the case that the 3SLS methodology is employed, so that the endogeneity problem among couples is considered, a one-percent BMI increase among Jewish Israeli females is associated with a projected 0.639 percent BMI increase among Jewish Israeli males (p = 0.091). Unlike Arab Israeli couples, no support is found to indicate the influence in the other direction, namely, the BMI of the male influences that of the female spouse. Research findings may thus be of relevance to public health and policy planners. Two limitations of this research lie in: 1) the self-reported BMI (which might be different from the measured BMI); and 2) missing confounders, such as regional dummies, which are not available in the dataset.