Markov Chains for Random Urinalysis III: Daily Model and Drug Kinetics
Abstract
This is the third in a series of reports on the use of Markov chains for the analysis of random urinalysis programs. A Markov model for random drug urinalysis testing that allows for daily variations in testing probabilities was developed. The formulation allows for any fixed length cycle (e.g., week, month) . Drug kinetics and drug user gaming are incorporated into the Markov model via conditional probabilities. The Markov chain provides estimates of the distribution of time to detection and mean time to detection. The analyses have shown that time to detection varies dramatically with varying (observed) daily testing rates. Unequal daily testing rates provide opportunities for gaming drug users to extend the mean time to detection. Gaming is not possible with equal probabilities of testing across days. Drug urinalysis, Markov chains, Cocaine, Pharmacokinetics.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 1994
- Accession Number
- ADA275540
Entities
People
- James P. Boyle
- Theodore J. Thompson
Organizations
- Bureau of Naval Personnel