Matching With Doses in an Observational Study of a Media Campaign Against Drug Abuse

• Published in: Journal of the American Statistical Association Vol. 96; no. 456; pp. 1245 - 1253
• Main Authors: Lu, Bo, Zanutto, Elaine, Hornik, Robert, Rosenbaum, Paul R
• Format: Journal Article
• Language: English
• Published: Alexandria, VA Taylor & Francis 01.12.2001; American Statistical Association; Taylor & Francis Ltd
• Subjects: Adjustment; Algorithms; Applications; Applications and Case Studies; Bias; Biology, psychology, social sciences; Biometrics; Coherent signed rank test; Control groups; Dosage; Drug abuse; Drug dosages; Drug policy; Drug prevention; Drug use; Epidemiology; Equal percent bias reducing; Estimation bias; Exact sciences and technology; Inhalants; Marijuana; Matching with doses; Mathematics; Media; Methods; Multivariate analysis; Nonbipartite matching; Observation; Observational studies; Optimal matching; Ordinal logit model; Probability and statistics; Propensity score; Public service advertising; Research design; Sampling theory, sample surveys; Scalars; Sciences and techniques of general use; Statistical methods; Statistics; Studies; Substance abuse treatment; Sufficiency and information; U.S.A; Drug abuse; Statistical analysis; Matched sample; Ordinal analysis; Optimal algorithm; Covariance analysis; Matching with doses; Multivariate analysis; Social behavior; Propensity score; Observation data; Nonbipartite matching; Logit model; Sample survey; Rank test; Biased estimation; Madia campaign; Equal percent bias reducing; Ordinal logit model; Observational studies; Optimal matching; Coherent signed rank test
• ISSN: 0162-1459; 1537-274X
• DOI: 10.1198/016214501753381896

Multivariate matching with doses of treatment differs from the treatment-control matching in three ways. First, pairs must not only balance covariates, but also must differ markedly in dose. Second, any two subjects may be paired, so that the matching is nonbipartite, and different algorithms are required. Finally, a propensity score with doses must be used in place of the conventional propensity score. We illustrate multivariate matching with doses using pilot data from a media campaign against drug abuse. The media campaign is intended to change attitudes and intentions related to illegal drugs, and the evaluation compares stated intentions among ostensibly comparable teens who reported markedly different exposures to the media campaign.