A longitudinal investigation of the relationship between disordered eating attitudes and behaviors and parent-child conflict: a monozygotic twin differences design

Abstract

Few studies have examined nonshared environmental risk factors for disordered eating, and none have done so using a longitudinal design. The current project used a longitudinal, monozygotic twin differences design to examine parent-child conflict as a nonshared environmental risk factor for disordered eating. Participants included 468 monozygotic female twins (234 pairs) from the Minnesota Twin Family Study, who completed surveys every 3 years from ages 11 to 17 years. Twin differences in disordered eating were assessed with the Total Score, Body Dissatisfaction, Weight Preoccupation, and Binge Eating subscales of the Minnesota Eating Behavior Survey. Differences in parent-child conflict were assessed with the Parental Environment Questionnaire. Cross-lagged models were used to examine longitudinal associations among these variables, controlling for within-age associations. Only the longitudinal association between twin differences in disordered eating at age 14 years and differences in parent-child conflict at age 17 years were significant; twin differences in disordered eating predicted later differences in parent-child conflict rather than the reverse. Findings suggest differences in parent-child conflict between genetically identical twins may be a consequence of, rather than a risk factor for, differences in disordered eating.

Figure 1. Cross-Lagged Model Examining Longitudinal Relationships between Variables

Partial regression coefficients are on the cross-age paths (‘b’). Within-age correlations are illustrated by curved lines (‘r’). Residual variance at ages 14 and 17 are denoted by the letter ‘e.’ The figure was reproduced by permission from Burt et al. (2006).

Figure 2. Cross-Lagged Models of Twin Differences in Disordered Eating Attitudes and Behaviors and Parent-Child Conflict

Standardized path coefficients are represented using single-headed arrows; correlations are represented with double-headed arrows. Root Mean Square Error of Approximation=RMSEA ***p<.001, **p<.01, *p<.05, two-tailed.