Thursday, February 23
PS1 Poster Session 1 and Opening Mixer Thu, Feb 23, 5:30 PM - 7:00 PM
Conference Center AB

Smoking Tendencies Among Junior High--School Students in Ghana: Applications of ROC Curve and AUC (303415)

Isaac Dompreh, U.S. Census Bureau 
Seidu Sofo, Southeast Missouri State University 
*Emmanuel Thompson, Southeast Missouri State University 

Keywords: Receiver operating characteristic curve, Area under the curve, Predictive model, Ghana

Globally, six million people die annually as a result of tobacco use. Research suggests that the rate of smoking among Ghanaian youth is higher than that of the general population. Data on the key triggering factors of youth smoking tendencies in Ghana is scarce. Therefore, the purpose of the present study was to recommend a predictive model for determining smoking tendencies among junior high school students in Ghana. The 2006 and 2009 Global Youth Tobacco Survey (GYTS) served as the data sources. The GYTS is a school-based survey designed to monitor tobacco use among youth and to guide the implementation and evaluation of tobacco control and prevention programs. Forward selection with Bayesian Information Criterion (BIC) were used to select the best model. Binary logistic regression was used to predict smoking tendencies. Receiver operating characteristic (ROC) curve and area under the curve (AUC) were validation tools used to assess the predictive power of the selected model. Results of the study showed promising potential for the predictive model based on the BIC.