Application of Latent Class Analysis for Screening Test of Adolescents Suicidal Behavior in United States (1991-2011 YRBSS Survey)

Hani Samawi, Ryan Christopher Butterfield

Research output: Contribution to conferencePresentation

Abstract

According to World Health Organization (WHO) estimates, in the year 2000, approximately one million people died from suicide, and 10 to 20 times more people attempted suicide worldwide. They reported in 2005 that there were a total of 32,559 deaths from suicide in the United States of those 32,559 there were 4,474 deaths between the ages 5-24. From the Youth Risk Behavior Surveillance System (YRBSS) (CDC, 2009) it is reported that almost 9% of adolescents of high school age attempted suicide at some point in the 12 months prior to survey administration. Screening for a specific disease or condition is a fundamental component of human disease control and prevention. One of the our primary goals is to use the latent class approach to estimate the sensitivity and the specificity of the screening test for Adolescents Suicidal Behavior in United States using data from 1991-2011 YRBSS Survey. Our preliminary results indicated the validity of using this technique. Also, we found that using the four suicide behavior indicators (Ideation, Planning, Attempt and Injury from attempt) as screening test has a high Sensitivity (0.9946) and Specificity (0.9233) from 2009 data.

Original languageAmerican English
StatePublished - Mar 1 2014
EventEastern North American Region International Biometric Society Annual Conference (ENAR) -
Duration: Mar 15 2015 → …

Conference

ConferenceEastern North American Region International Biometric Society Annual Conference (ENAR)
Period03/15/15 → …

Disciplines

  • Biostatistics
  • Public Health

Keywords

  • Adolescents
  • Latent class analysis
  • Screening test
  • Suicidal behavior
  • Survey
  • YRBSS

Fingerprint

Dive into the research topics of 'Application of Latent Class Analysis for Screening Test of Adolescents Suicidal Behavior in United States (1991-2011 YRBSS Survey)'. Together they form a unique fingerprint.

Cite this