A statistical analysis of drug seizures and opioid overdose deaths in Ohio from 2014 to 2018

TL;DR

This study analyzes Ohio's drug seizure data from 2014-2018 to understand its relationship with overdose deaths, revealing strong predictive links but no lag time, and differences in seizure weights across law enforcement types.

Contribution

It provides a comprehensive statistical analysis of drug seizures and overdose deaths, highlighting predictive factors and differences across law enforcement agencies.

Findings

Drug seizure composition and weight strongly predict overdose deaths.

No significant lag between drug seizures and overdose deaths.

Different law enforcement agencies have distinct seizure weight distributions.

Abstract

This paper examines the association between police drug seizures and drug overdose deaths in Ohio from 2014 to 2018. We use linear regression, ARIMA models, and categorical data analysis to quantify the effect of drug seizure composition and weight on drug overdose deaths, to quantify the lag between drug seizures and overdose deaths, and to compare the weight distributions of drug seizures conducted by different types of law enforcement (national, local, and drug task forces). We find that drug seizure composition and weight have strong predictive value for drug overdose deaths (F = 27.14, p < 0.0001, R^2 = .7799). A time series analysis demonstrates no statistically significant lag between drug seizures and overdose deaths or weight. Histograms and Kolmogorov-Smirnov tests demonstrate stark differences between seizure weight distributions of different types of law enforcement (p < 0.0001 for each pairwise comparison). We include a discussion of what our conclusions mean for law enforcement and harm reduction efforts.