We use 9 Add Health high schools with longitudinal network data to assess whether adolescent drinkers choose friends who drink, prefer friends whose friends drink, if selection differs between new and existing friends...We use 9 Add Health high schools with longitudinal network data to assess whether adolescent drinkers choose friends who drink, prefer friends whose friends drink, if selection differs between new and existing friendships, and between schools. Utilizing dynamic social network models that control for friend influences on individual alcohol use, the results show that drinkers do not strongly prefer friends who drink. Instead, they favor close friends whose friends’ drink, suggesting that alcohol matters for selection on the social groups and environments that friends connect each other to. The role of alcohol use differs by whether friendships are new or existing, however, with bridging connections being less stable. Moreover, selection processes, and the implications of alcohol use for friendship, vary in important ways between schools.展开更多
文摘We use 9 Add Health high schools with longitudinal network data to assess whether adolescent drinkers choose friends who drink, prefer friends whose friends drink, if selection differs between new and existing friendships, and between schools. Utilizing dynamic social network models that control for friend influences on individual alcohol use, the results show that drinkers do not strongly prefer friends who drink. Instead, they favor close friends whose friends’ drink, suggesting that alcohol matters for selection on the social groups and environments that friends connect each other to. The role of alcohol use differs by whether friendships are new or existing, however, with bridging connections being less stable. Moreover, selection processes, and the implications of alcohol use for friendship, vary in important ways between schools.
