Markov transition models for binary repeated measures with ignorable and nonignorable missing values

Xiaowei Yang; Shoptaw, Steven; Kun Nie; Juanmei Liu; Belin, Thomas R.
August 2007
Statistical Methods in Medical Research;Aug2007, Vol. 16 Issue 4, p347
Academic Journal
Motivated by problems encountered in studying treatments for drug dependence, where repeated binary outcomes arise from monitoring biomarkers for recent drug use, this article discusses a statistical strategy using Markov transition model for analyzing incomplete binary longitudinal data. When the mechanism giving rise to missing data can be assumed to be ‘ignorable’, standard Markov transition models can be applied to observed data to draw likelihood-based inference on transition probabilities between outcome events. Illustration of this approach is provided using binary results from urine drug screening in a clinical trial of baclofen for cocaine dependence. When longitudinal data have ‘nonignorable’ missingness mechanisms, random-effects Markov transition models can be used to model the joint distribution of the binary data matrix and the matrix of missingness indicators. Categorizing missingness patterns into those for occasional or ‘intermittent’ missingness and those for monotonic missingness or ‘missingness due to dropout’, the random-effects Markov transition model was applied to a data set containing repeated breath samples analyzed for expired carbon monoxide levels among opioid-dependent, methadone-maintained cigarette smokers in a smoking cessation trial. Markov transition models provide a novel reconceptualization of treatment outcomes, offering both intuitive statistical values and relevant clinical insights.


Related Articles

  • The Impact of Disulfiram Treatment on the Reinforcing Effects of Cocaine: A Randomized Clinical Trial. Haile, Colin N.; De La Garza II, Richard; Mahoney III, James J.; Nielsen, David A.; Kosten, Thomas R.; Newton, Thomas F. // PLoS Clinical Trials;Nov2012, Vol. 7 Issue 11, p1 

    Background: Clinical trials indicate that disulfiram (250 mg/d) reduces cocaine use, though one study found that treatment with lower doses of disulfiram (62.5 and 125 mg/d) increased cocaine use. We conducted the present study to better understand how disulfiram alters the reinforcing effects...

  • The Potential Value of a Negative Finding. Silverman, Kenneth; DeFulio, Anthony; Leoutsakos, Jeannie-Marie // JAMA Psychiatry;Jun2013, Vol. 70 Issue 6, p571 

    The authors reflect on the importance of negative results of a study in clinical trials. They state that negative findings must be included in scientific literature as it may provide extremely useful information based on methodology in clinical trials suggesting the need of further study. The...

  • The effects of auricular acupuncture on smoking cessation may not depend on the point chosen. White, Adrian; Moody, Russell // Acupuncture in Medicine;Dec2006, Vol. 24 Issue 4, p149 

    Introduction Auricular acupuncture is given as a treatment for drug dependence. Points are usually chosen on the assumption that the body is represented somatotopically in the ear, although there is no anatomical basis for this. In clinical trials, sham treatment is often given at points that...

  • The Smoking N-Back: A Measure of Biased Cue Processing at Varying Levels of Cognitive Load. Evans, David E.; Craig, Christine; Oliver, Jason A.; Drobes, David J. // Nicotine & Tobacco Research;Feb2011, Vol. 13 Issue 2, p88 

    Introduction: Recent cognitive models of drug addiction have emphasized attentional bias to drug-related cues. This bias manifests as increased accessibility to affect-laden drug-related content relative to less emotionally evocative stimuli and ideation. We examined whether biased processing of...

  • Psychopharmacology Coke addicts prefer money in hand to snowy future.  // Biomedical Market Newsletter;8/12/2011, Vol. 21, p212 

    The article focuses on the preference of cocaine addicts to money at hand rather than cocaine in a hypothetical situation.

  • DISULFIRAM, COCAINE, AND ALCOHOL: TWO OUTCOMES FOR THE PRICE OF ONE? Gossop, Michael; Carroll, Kathleen M. // Alcohol & Alcoholism;Mar/Apr2006, Vol. 41 Issue 2, p119 

    The article discusses the potential of disulfiram as treatment for cocaine and alcohol dependence. It cites the comparison outcomes of two outpatient groups who were administered disulfiram and placebo. Results show that patients who took disulfiram had reduced cocaine usage than those who were...

  • POISONING & DRUG DEPENDENCE.  // Nurse Practitioners Prescribing Reference;Winter2011/2012, Vol. 18 Issue 4, p265 

    The article offers information on several poisoning and drug dependence medications. It says that acetadote from Cumberland Pharmaceuticals Inc. minimizes hepatic injury after acetaminophen overdose while chantix from Pfizer Inc. provides adult patients with educational and counseling support....

  • Clinical trial comparing nicotine replacement therapy (NRT) plus brief counselling, brief counselling alone, and minimal intervention on smoking cessation in hospital inpatients. Molyneux A; Lewis S; Leivers U; Anderton A; Antoniak M; Brackenridge A; Nilsson F; McNeill A; West R; Moxham J; Britton J; Molyneux, A; Lewis, S; Leivers, U; Anderton, A; Antoniak, M; Brackenridge, A; Nilsson, F; McNeill, A; West, R // Thorax;Jun2003, Vol. 58 Issue 6, p484 

    Background: Guidelines recommend that smoking cessation interventions are offered in all clinical settings to all smokers willing to make a quit attempt. Since the effectiveness of routine provision of behavioural counselling and nicotine replacement therapy (NRT) to smokers...

  • Recruitment Into a Cessation Trial Via the New Zealand Quitline: Many Benefits, Few Limitations. Bullen, Chris; Howe, Colin; Grigg, Michele; Phillips, Frances; Silcock, Rose; Glover, Marewa; McRobbie, Hayden; Whittaker, Robyn // Journal of Smoking Cessation;Apr2008, Vol. 3 Issue 1, p30 

    Objective: To report on the use of the New Zealand Quitline for recruiting participants to a smoking cessation trial. Methods: Analysis of data on trial recruitment and randomisation. Results: 68% of 26,369 callers to the New Zealand Quitline over 12 months indicated an interest in taking part...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics