CONTACT US: Contact info
|
Citation |
Li H. Eur. J. Humanit. Soc. Sci. 2021; (5): 67-73. |
|
Copyright |
(Copyright © 2021, European Journal of Humanities and Social Sciences) |
|
DOI |
|
PMID |
unavailable |
|
Abstract |
Youth suicide has been an ongoing issue in the United States. One out of every 53 high school students is reported to have made a suicide attempt in their youthhood. Thus, it is imperative for groups like parents, guardians, doctors, and teachers to develop a more in-depth understanding of the causes that lead to youth suicide. In this report, response data of 13.677 high school students of 14 to 17 years old from the 2019 Youth Risk Behavior Surveillance Survey are analyzed. Several pre-processing techniques such as missing value exclusion, and min-max scaling are applied to prepare the data set for model-building. Then a list of selected variables including physical attributes, demo- graphic variables, and drinking behaviors are used to develop and validate two predictive models for predicting the probability of committing suicide. The predictive models are further validated by an overall evaluation of the model, statistical tests of individual predictors, and an assessment of rela - tive importance of the independent variables. The predictive models demonstrate good and similar performance. The AUC of the models are 0.676 and 0.692, respectively. The results indicate that limiting adolescents' access to cigarettes should be the most effective way to decrease adolescents' suicide possibility. Language: en |