Statistical analysis of noncommensurate multiple outcomes.

Many studies collect multiple outcomes to characterize treatment effectiveness or evaluate risk factors. These outcomes tend to be correlated because they are measuring related quantities in the same individuals, but the common approach used by researchers is to ignore this correlation and analyze each outcome separately. There may be advantages to consider the simultaneous analysis of the outcomes using multivariate methods. Although the joint analysis of outcomes measured in the same scale (commensurate outcomes) can be undertaken with standard statistical methods, outcomes measured in different scales (noncommensurate outcomes), such as mixed binary and continuous outcomes, present more difficult challenges. In this article, we contrast some statistical approaches to analyze noncommensurate multiple outcomes. We discuss the advantages of a multivariate method for the analysis of noncommensurate outcomes, including situations of missing data. A real data example from a clinical trial, comparing bare-metal with sirolimus-eluting stents, is used to illustrate the differences between the statistical approaches.

[1]  Markus Neuhäuser,et al.  How to deal with multiple endpoints in clinical trials , 2006, Fundamental & clinical pharmacology.

[2]  S. Zeger,et al.  Longitudinal data analysis using generalized linear models , 1986 .

[3]  Karen Bandeen-Roche,et al.  Residual Diagnostics for Growth Mixture Models , 2005 .

[4]  P J Catalano,et al.  Bivariate modelling of clustered continuous and ordered categorical outcomes. , 1997, Statistics in medicine.

[5]  Ann A. O'Connell,et al.  Longitudinal Data Analysis , 2013 .

[6]  Nick Freemantle,et al.  Composite outcomes in randomized trials: greater precision but with greater uncertainty? , 2003, JAMA.

[7]  Yulei He,et al.  Missing data analysis using multiple imputation: getting to the heart of the matter. , 2010, Circulation. Cardiovascular quality and outcomes.

[8]  R. D'Agostino,et al.  Multiple Endpoints, Multivariate Global Tests , 2005 .

[9]  N L Geller,et al.  Use of a global test for multiple outcomes in stroke trials with application to the National Institute of Neurological Disorders and Stroke t-PA Stroke Trial. , 1996, Stroke.

[10]  F B Hu,et al.  Comparison of population-averaged and subject-specific approaches for analyzing repeated binary outcomes. , 1998, American journal of epidemiology.

[11]  D. Altman,et al.  Multiple significance tests: the Bonferroni method , 1995, BMJ.

[12]  J. LaFountain.  Inc. , 2013, American Art.

[13]  S. Normand,et al.  Correlated bivariate continuous and binary outcomes: Issues and applications , 2009, Statistics in medicine.

[14]  N M Laird,et al.  Regression models for mixed discrete and continuous responses with potentially missing values. , 1997, Biometrics.

[15]  Armando Teixeira-Pinto,et al.  MISSING DATA IN REGRESSION MODELS FOR NON-COMMENSURATE MULTIPLE OUTCOMES. , 2011, Revstat statistical journal.

[16]  Geert Molenberghs.  Repeated Measures , 2011, International Encyclopedia of Statistical Science.

[17]  Jeffrey W Moses,et al.  Sirolimus-eluting stents versus standard stents in patients with stenosis in a native coronary artery. , 2003, The New England journal of medicine.

[18]  A. Zellner,et al.  Further Properties of Efficient Estimators for Seemingly Unrelated Regression Equations , 1962 .

[19]  Garrett M. Fitzmaurice,et al.  A Primer in Longitudinal Data Analysis , 2008, Circulation.

[20]  Charles L. Brown,et al.  Analysis of 1-Year Clinical Outcomes in the SIRIUS Trial: A Randomized Trial of a Sirolimus-Eluting Stent Versus a Standard Stent in Patients at High Risk for Coronary Restenosis , 2004, Circulation.