Comorbidity of chronic diseases in the elderly: Patterns identified by a copula design for mixed responses

Joint modeling of multiple health related random variables is essential to develop an understanding for the public health consequences of an aging population. This is particularly true for patients suffering from multiple chronic diseases. The contribution is to introduce a novel model for multivariate data where some response variables are discrete and some are continuous. It is based on pair copula constructions (PCCs) and has two major advantages over existing methodology. First, expressing the joint dependence structure in terms of bivariate copulas leads to a computationally advantageous expression for the likelihood function. This makes maximum likelihood estimation feasible for large multidimensional data sets. Second, different and possibly asymmetric bivariate (conditional) marginal distributions are allowed which is necessary to accurately describe the limiting behavior of conditional distributions for mixed discrete and continuous responses. The advantages and the favorable predictive performance of the model are demonstrated using data from the Second Longitudinal Study of Aging (LSOA II).

[1]  Claudia Czado,et al.  Maximum likelihood estimation of mixed C-vines with application to exchange rates , 2012 .

[2]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[3]  M Elia,et al.  Obesity in the elderly. , 2001, Obesity research.

[4]  Mingyao Li,et al.  Joint Regression Analysis of Correlated Data Using Gaussian Copulas , 2009, Biometrics.

[5]  A. Frigessi,et al.  Pair-copula constructions of multiple dependence , 2009 .

[6]  T. Bedford,et al.  Vines: A new graphical model for dependent random variables , 2002 .

[7]  M. Sklar.  Fonctions de repartition a n dimensions et leurs marges , 1959 .

[8]  Peter D. Hoff.  Extending the rank likelihood for semiparametric copula estimation , 2006, math/0610413.

[9]  Aristidis K. Nikoloulopoulos,et al.  Tail dependence functions and vine copulas , 2010, J. Multivar. Anal..

[10]  R. Nelsen.  An Introduction to Copulas (Springer Series in Statistics) , 2006 .

[11]  Jared S. Murray,et al.  Bayesian Gaussian Copula Factor Models for Mixed Data , 2011, Journal of the American Statistical Association.

[12]  Claudia Czado,et al.  Selecting and estimating regular vine copulae and application to financial returns , 2012, Comput. Stat. Data Anal..

[13]  Aristidis K. Nikoloulopoulos.  On the estimation of normal copula discrete regression models using the continuous extension and simulated likelihood , 2013, 1304.0905.

[14]  Ulf Schepsmeier,et al.  Derivatives and Fisher information of bivariate copulas , 2014 .

[15]  H. Joe,et al.  The Estimation Method of Inference Functions for Margins for Multivariate Models , 1996 .

[16]  C. Czado,et al.  Truncated regular vines in high dimensions with application to financial data , 2012 .

[17]  Ana V Diez Roux,et al.  Socioeconomic gradients in chronic disease risk factors in middle-income countries: evidence of effect modification by urbanicity in Argentina. , 2011, American journal of public health.

[18]  Leon Flicker,et al.  Body Mass Index and Survival in Men and Women Aged 70 to 75 , 2010, Journal of the American Geriatrics Society.

[19]  C. Genest,et al.  A Primer on Copulas for Count Data , 2007, ASTIN Bulletin.

[20]  Johanna Nešlehová,et al.  On rank correlation measures for non-continuous random variables , 2007 .

[21]  Ninh T. Nguyen,et al.  Relationship Between Obesity and Diabetes in a US Adult Population: Findings from the National Health and Nutrition Examination Survey, 1999–2006 , 2010, Obesity surgery.

[22]  Peter J. Danaher,et al.  Modeling Multivariate Distributions Using Copulas: Applications in Marketing , 2011, Mark. Sci..

[23]  R. Prim.  Shortest connection networks and some generalizations , 1957 .

[24]  B. Penninx,et al.  Self-reports and general practitioner information on the presence of chronic diseases in community dwelling elderly. A study on the accuracy of patients' self-reports and on determinants of inaccuracy. , 1996, Journal of clinical epidemiology.

[25]  R. Nelsen.  An Introduction to Copulas , 1998 .

[26]  C. Genest,et al.  A semiparametric estimation procedure of dependence parameters in multivariate families of distributions , 1995 .

[27]  B. Wu,et al.  Copula‐based regression models for a bivariate mixed discrete and continuous outcome , 2011, Statistics in medicine.

[28]  M. Smith,et al.  Estimation of Copula Models With Discrete Margins via Bayesian Data Augmentation , 2011 .

[29]  R B D'Agostino,et al.  Can sustained weight loss in overweight individuals reduce the risk of diabetes mellitus? , 2000, Epidemiology.

[30]  Sylvain Arlot,et al.  A survey of cross-validation procedures for model selection , 2009, 0907.4728.

[31]  Dimitris Karlis,et al.  Finite normal mixture copulas for multivariate discrete data modeling , 2009 .

[32]  Serena Tonstad,et al.  Does Excess Body Fat Maintained After the Seventh Decade Decrease Life Expectancy? , 2011, Journal of the American Geriatrics Society.

[33]  M. Carvalho,et al.  Alternatives in modeling of body mass index as a continuous response variable and relevance of residual analysis. , 2008, Cadernos de saude publica.

[34]  Diane B. Wilson,et al.  The Association Between Body Mass Index and Arthritis Among US Adults: CDC’s Surveillance Case Definition , 2009, Preventing chronic disease.

[35]  C. Czado,et al.  Bayesian model selection for D‐vine pair‐copula constructions , 2011 .

[36]  Claudia Czado,et al.  Pair Copula Constructions for Multivariate Discrete Data , 2012 .

[37]  Margaret Shih,et al.  Physical activity in men and women with arthritis National Health Interview Survey, 2002. , 2006, American journal of preventive medicine.

[38]  A. Raftery,et al.  Strictly Proper Scoring Rules, Prediction, and Estimation , 2007 .

[39]  H. Akaike.  A new look at the statistical model identification , 1974 .

[40]  M. Pitt,et al.  Efficient Bayesian inference for Gaussian copula regression models , 2006 .

[41]  A. Dobra,et al.  Copula Gaussian graphical models and their application to modeling functional disability data , 2011, 1108.1680.

[42]  Eike Christian Brechmann,et al.  Selection of Vine Copulas , 2013 .

[43]  Jialiang Li,et al.  Two-dimensional toxic dose and multivariate logistic regression, with application to decompression sickness. , 2011, Biostatistics.

[44]  Hongzhe Li,et al.  A Gaussian copula approach for the analysis of secondary phenotypes in case-control genetic association studies. , 2012, Biostatistics.

[45]  Dimitris Karlis,et al.  Modeling Multivariate Count Data Using Copulas , 2009, Commun. Stat. Simul. Comput..

[46]  C. Varin,et al.  Gaussian Copula Marginal Regression , 2012 .

[47]  Claudia Czado,et al.  Simplified pair copula constructions - Limitations and extensions , 2013, J. Multivar. Anal..

[48]  Roger M. Cooke,et al.  Probability Density Decomposition for Conditionally Dependent Random Variables Modeled by Vines , 2001, Annals of Mathematics and Artificial Intelligence.

[49]  C. Czado,et al.  Modeling Longitudinal Data Using a Pair-Copula Decomposition of Serial Dependence , 2010 .

[50]  J. Curb,et al.  Association of body mass index with blood pressure in elderly Japanese American men. The Honolulu Heart Program. , 1997, Hypertension.

[51]  Ulf Schepsmeier,et al.  Estimating standard errors in regular vine copula models , 2013, Comput. Stat..

[52]  Changyu Shen,et al.  A copula model for repeated measurements with non‐ignorable non‐monotone missing outcome , 2006, Statistics in medicine.

[53]  H. Joe.  Multivariate models and dependence concepts , 1998 .

[54]  P. Green.  Iteratively reweighted least squares for maximum likelihood estimation , 1984 .