*Goylette Chami *Prepared for PLoS One manuscript "Social network analysis predicts health behaviors and self-reported health in African villages" *June 2nd, 2014 *VARIABLE EXPLANATION *Identifiers *village_id *household_id *Village dummy variables *village_id_d1 village_id_d2 village_id_d3 village_id_d4 village_id_d5 village_id_d6 village_id_d7 *Dependent Variables *total_people_sick: count of total people sick in household in the month preceding the study. *poor_preventat_healh: count of the following six behaviors (of the household head) done at least once per week: drinking alcohol, smoking, burning cooking fuel indoors, entering freshwater bodies, open defecation, and sleeping outside. *medical_care: total amount spent on drugs and hospital stays over the year preceding the study. *health_decision_susceptibility: to the household head, we asked “Is your decision to seek treatment or to engage in preventative health care behaviors affected by what other villagers are doing?” *Network parameters, must run this code before running regressions. local friends betweenness_fr in_deg_fr *REGRESSIONS WITH ONLY IN-DEGREE, BETWEENNESS, AND VILLAGES TO PREDICT HEALTH VARIABLES *(1a) Prediction of total people sick in the household, negative binomial capture noisily glm total_people_sick `friends' village_id_d1 village_id_d2 village_id_d3 village_id_d4 village_id_d5 village_id_d6 village_id_d7, family(nbinomial) irls nolog *(1b) Prediction of total people sick in household,negative binomial, showing incidence rate ratio capture noisily glm total_people_sick `friends' village_id_d1 village_id_d2 village_id_d3 village_id_d4 village_id_d5 village_id_d6 village_id_d7, family(nbinomial) irls nolog eform *(2) Prediction of poor preventative health, poisson capture noisily glm poor_preventative_health `friends' village_id_d1 village_id_d2 village_id_d3 village_id_d4 village_id_d5 village_id_d6 village_id_d7, family(poisson) irls nolog *(3) Prediction of medical care, gaussian capture noisily glm medical_care `friends' village_id_d1 village_id_d2 village_id_d3 village_id_d4 village_id_d5 village_id_d6 village_id_d7, family(gaussian) irls nolog *(4) Prediction of health decisions influenced by other village members, probit capture noisily glm health_decision_susceptibility `friends' village_id_d1 village_id_d2 village_id_d3 village_id_d4 village_id_d5 village_id_d6 village_id_d7, family(binomial) link(probit) irls nolog *REGRESSIONS PREDICTING MEDICAL CARE WITH TOTAL PEOPLE SICK COVARIATE *(5a) Prediction of medical care whilst controlling for total people sick in the household, Gaussian model capture noisily glm medical_care `friends' total_people_sick village_id_d1 village_id_d2 village_id_d3 village_id_d4 village_id_d5 village_id_d6 village_id_d7, family(gaussian) irls nolog *(5b) Prediction of medical care, Tobit model capture noisily tobit medical_care `friends' village_id_d1 village_id_d2 village_id_d3 village_id_d4 village_id_d5 village_id_d6 village_id_d7, ll(0) *(5c) Prediction of medical care whilst controlling for total people sick in the household, Tobit model capture noisily tobit medical_care `friends' total_people_sick village_id_d1 village_id_d2 village_id_d3 village_id_d4 village_id_d5 village_id_d6 village_id_d7, ll(0) *EXTENDED MODEL REGRESSIONS, ADDITIONAL COVARIATES OF SOCIAL STATUS, AGRICULTURE, HOME QUALITY, and YEARS IN VILLAGE *(6) Prediction of total people sick in household, negative binomial capture noisily glm total_people_sick `friends' years_in_village agriculture social_status home_quality_score village_id_d1 village_id_d2 village_id_d3 village_id_d4 village_id_d5 village_id_d6 village_id_d7, family(nbinomial) irls nolog *(7) Prediction of poor preventative health, poisson capture noisily glm poor_preventative_health `friends' years_in_village agriculture social_status home_quality_score village_id_d1 village_id_d2 village_id_d3 village_id_d4 village_id_d5 village_id_d6 village_id_d7, family(poisson) irls nolog *(8) Prediction of medical care, gaussian capture noisily glm medical_care `friends' years_in_village agriculture social_status home_quality_score village_id_d1 village_id_d2 village_id_d3 village_id_d4 village_id_d5 village_id_d6 village_id_d7, family(gaussian) irls nolog *(9) Prediction of health decisions influenced by other village members, probit capture noisily glm health_decision_susceptibility `friends' years_in_village agriculture social_status home_quality_score village_id_d1 village_id_d2 village_id_d3 village_id_d4 village_id_d5 village_id_d6 village_id_d7, family(binomial) link(probit) irls nolog