A new multivariate zero‐adjusted Poisson model with applications to biomedicine

Recently, although advances were made on modeling multivariate count data, existing models really has several limitations: (i) The multivariate Poisson log-normal model (Aitchison and Ho, ) cannot be used to fit multivariate count data with excess zero-vectors; (ii) The multivariate zero-inflated Poisson (ZIP) distribution (Li et al., 1999) cannot be used to model zero-truncated/deflated count data and it is difficult to apply to high-dimensional cases; (iii) The Type I multivariate zero-adjusted Poisson (ZAP) distribution (Tian et al., 2017) could only model multivariate count data with a special correlation structure for random components that are all positive or negative. In this paper, we first introduce a new multivariate ZAP distribution, based on a multivariate Poisson distribution, which allows the correlations between components with a more flexible dependency structure, that is some of the correlation coefficients could be positive while others could be negative. We then develop its important distributional properties, and provide efficient statistical inference methods for multivariate ZAP model with or without covariates. Two real data examples in biomedicine are used to illustrate the proposed methods.

[1]  J. Aitchison,et al.  The multivariate Poisson-log normal distribution , 1989 .

[2]  Dianliang Deng,et al.  Score tests for zero inflation in generalized linear models , 2000 .

[3]  Felix Famoye,et al.  Zero-Inflated Generalized Poisson Regression Model with an Application to Domestic Violence Data , 2021, Journal of Data Science.

[4]  C. Radhakrishna Rao,et al.  Some small sample tests of significance for a Poisson distribution , 1956 .

[5]  S. K. Katti,et al.  Fitting of Certain Contagious Distributions to Some Available Data by the Maximum Likelihood Method , 1965 .

[6]  Shiferaw Gurmu,et al.  Semi-Parametric Estimation of Hurdle Regression Models with an Application to Medicaid Utilization , 1997 .

[7]  D. Karlis.  An EM algorithm for multivariate Poisson distribution and related models , 2003 .

[8]  T. B. d’Uva,et al.  Latent class models for utilisation of health care. , 2006, Health economics.

[9]  Alan Agresti,et al.  Random effect models for repeated measures of zero-inflated count data , 2005 .

[10]  D. Karlis,et al.  Bivariate Poisson and Diagonal Inflated Bivariate Poisson Regression Models in R , 2005 .

[11]  Ram C. Dahiya,et al.  Estimation in a truncated bivariate poisson distribution , 1977 .

[12]  Daniel B. Hall,et al.  Marginal models for zero inflated clustered data , 2004 .

[13]  Shiferaw Gurmu,et al.  Tests for Detecting Overdispersion in the Positive Poisson Regression Model , 1991 .

[14]  H. Hartley.  Maximum Likelihood Estimation from Incomplete Data , 1958 .

[15]  Yuehua Cui,et al.  Zero-inflated generalized Poisson regression mixture model for mapping quantitative trait loci underlying count trait with many zeros. , 2009, Journal of theoretical biology.

[16]  X L Meng,et al.  The EM algorithm and medical studies: a historical linik , 1997, Statistical methods in medical research.

[17]  J. Hinde,et al.  A Score Test for Testing a Zero‐Inflated Poisson Regression Model Against Zero‐Inflated Negative Binomial Alternatives , 2001, Biometrics.

[18]  Richard T. Carson,et al.  Models for truncated counts , 1991 .

[19]  R Shanmugam,et al.  An intervened Poisson distribution and its medical application. , 1985, Biometrics.

[20]  Atanu Biswas,et al.  A Bayesian analysis of zero-inflated generalized Poisson model , 2003, Comput. Stat. Data Anal..

[21]  P. Deb,et al.  Demand for Medical Care by the Elderly: A Finite Mixture Approach , 1997 .

[22]  P. R. Rider,et al.  Truncated Binomial and Negative Binomial Distributions , 1955 .

[23]  Yin Liu,et al.  Type I multivariate zero-inflated Poisson distribution with applications , 2015, Comput. Stat. Data Anal..

[24]  Lijuan Wang,et al.  IRT–ZIP Modeling for Multivariate Zero-Inflated Count Data , 2010 .

[25]  Claudia Czado,et al.  Testing for zero-modification in count regression models. , 2010 .

[26]  Olivier Thas,et al.  Goodness of fit for the zero-truncated Poisson distribution , 2007 .

[27]  Violetta E. Piperigou,et al.  On truncated bivariate discrete distributions: A unified treatment , 2003 .

[28]  Diane Lambert,et al.  Zero-inflacted Poisson regression, with an application to defects in manufacturing , 1992 .

[29]  Antonello Maruotti,et al.  A dynamic hurdle model for zeroinflated panel count data , 2013 .

[30]  Norman L. Johnson,et al.  The Truncated Poisson , 1952 .

[31]  Antonello Maruotti,et al.  A finite mixture model for multivariate counts under endogenous selectivity , 2011, Stat. Comput..

[32]  Marco Alfò,et al.  Variance component models for longitudinal count data with baseline information: epilepsy data revisited , 2006, Stat. Comput..

[33]  Andy H. Lee,et al.  Multi-level zero-inflated Poisson regression modelling of correlated count data with excess zeros , 2006, Statistical methods in medical research.

[34]  P. R. Rider,et al.  Truncated Poisson Distributions , 1953 .

[35]  Y. Cheung,et al.  Zero‐inflated models for regression analysis of count data: a study of growth and development , 2002, Statistics in medicine.

[36]  A. Cohen,et al.  Estimating the Parameter in a Conditional Poisson Distribution , 1960 .

[37]  Ch. A. Charalambides.  Minimum variance unbiased estimation for the zero class truncated bivariate poisson and logarithmic series distributions , 1984 .

[38]  J. O. Irwin,et al.  138. Note: On the Estimation of the Mean of a Poisson Distribution from a Sample with the Zero Class Missing , 1959 .

[39]  Chin-Shang Li.  Score Tests for Semiparametric Zero-inflated Poisson Models , 2012 .

[40]  Antonello Maruotti,et al.  Two‐part regression models for longitudinal zero‐inflated count data , 2010 .

[41]  Byoung Cheol Jung,et al.  Score Tests for Testing Independence in the Zero-Truncated Bivariate Poisson Models , 2007 .

[42]  Dankmar Böhning,et al.  The zero‐inflated Poisson model and the decayed, missing and filled teeth index in dental epidemiology , 1999 .

[43]  Feng-Chang Xie,et al.  Score tests for zero-inflated generalized Poisson mixed regression models , 2009, Comput. Stat. Data Anal..

[44]  K. Yau,et al.  Zero‐Inflated Negative Binomial Mixed Regression Modeling of Over‐Dispersed Count Data with Extra Zeros , 2003 .

[45]  M. A. Hamdan.  Estimation in the Truncated Bivariate Poisson Distribution , 1972 .

[46]  J. T. Campbell,et al.  The Poisson Correlation Function , 1934 .

[47]  P. G. Moore,et al.  THE ESTIMATION OF THE POISSON PARAMETER FROM A TRUNCATED DISTRIBUTION , 1952 .

[48]  A James O'Malley,et al.  A Bayesian model for repeated measures zero-inflated count data with application to outpatient psychiatric service use , 2010, Statistical modelling.

[49]  A. W. Kepm.  Weighted discrepancies and maximum likelihood estimation for discrete distributions , 1986 .

[50]  D. J. Finney,et al.  The truncated binomial distribution. , 1949, Annals of eugenics.

[51]  J. Mullahy.  Specification and testing of some modified count data models , 1986 .

[52]  Antonello Maruotti,et al.  On Baseline Conditions for Zero-Inflated Longitudinal Count Data , 2014, Commun. Stat. Simul. Comput..

[53]  D. Hall.  Zero‐Inflated Poisson and Binomial Regression with Random Effects: A Case Study , 2000, Biometrics.

[54]  S. R. Deshmukh,et al.  BIVARIATE DISTRIBUTION WITH TRUNCATED POISSON MARGINAL DISTRIBUTIONS , 2002 .

[55]  Marco Alfò,et al.  Semiparametric Mixture Models for Multivariate Count Data, with Application , 2004 .

[56]  D. J. Finney,et al.  An Example of the Truncated Poisson Distribution , 1955 .