Predictive Models to Estimate Probabilities of Injuries and Adverse Performance Outcomes in U.S. Army Basic Combat Training

Abstract

Negative training outcomes in U.S. Army basic combat training (BCT) are costly and difficult to prevent and manage. This report provides details from statistical models predicting probabilities of injury (as defined by 5 separate injury indices), attrition from BCT, and failing the Army Physical Fitness Test (APFT) conducted near the end of BCT. The models were derived from multivariate logistic regression analyses of data from a study conducted at Fort Jackson, SC from 7 June-13 August 2010. The sample consisted of 563 recruits (414 men and 149 women). Data were assembled from demographic databases, baseline APFT, and a survey of self-reported lifestyle characteristics. Statistical models predicting probability of injury included: gender, initial fitness test scores, race/ethnicity, self-reported physical activity level prior to BCT, injuries sustained prior to BCT, height, and tobacco use. Models predicting probability of APFT failure and attrition included gender, initial fitness test scores, age, and tobacco use as predictors.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 2014
Accession Number
ADA609367

Entities

People

  • Joseph J Knapik
  • Marilyn A. Sharp
  • Stephen C. Allison

Organizations

  • United States Army Research Institute of Environmental Medicine

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Attrition
  • Basic Training
  • Computational Science
  • Data Analysis
  • Data Mining
  • Data Science
  • Databases
  • Health Services
  • Information Science
  • Injury Prevention
  • Military Training
  • Pain
  • Physical Activity
  • Predictive Modeling
  • Regression Analysis
  • Surveys
  • Training

Readers

  • Computational Modeling and Simulation
  • Exercise and Sports Science.
  • Military Training and Readiness Simulation