Related Experiment Video
Updated: Jul 30, 2026

Inverse Probability of Treatment Weighting (Propensity Score) using the Military Health System Data Repository and National Death Index
Published on: January 8, 2020
Trends in adolescent suicide: misclassification bias?
1Department of Maternal and Child Health, Harvard School of Public Health, 677 Huntington Ave, Boston, MA 02115, USA. bmohler@hsph.harvard.edu
Objectives:
This study investigated the effect of misclassification of accidental deaths and undetermined deaths on age-, sex-, and race/ethnicity-specific adolescent suicide rates from 1979 through 1994.
Methods:
Official mortality data were used to present suicide mortality trends. Two estimates of misclassified suicides in other death categories were applied to calculate "corrected" trends of adolescent suicide.
Results:
The corrected trends showed a downward adjustment for Black adolescent males and young adolescents. This result does not, however, substantially alter the trend toward a recent increase in suicide in these groups.
Conclusions:
Despite misclassification, the true direction of trends in adolescent suicide is reflected in recent official data. However, suicide rates should continuously be tested for misclassification, mainly in populations with proportionately high accidental and undetermined death rates.
Related Concept Videos
Reliability and Validity
Regression Toward the Mean
Self-Presentation: Self-Monitoring and Self-Handicapping
Bullying
Bias in Epidemiological Studies
Assumptions of Survival Analysis

