The zero inflated models are usually used in modeling

\r\ncount data with excess zeros where the existence of the excess zeros

\r\ncould be structural zeros or zeros which occur by chance. These type

\r\nof data are commonly found in various disciplines such as finance,

\r\ninsurance, biomedical, econometrical, ecology, and health sciences

\r\nwhich involve sex and health dental epidemiology. The most popular

\r\nzero inflated models used by many researchers are zero inflated

\r\nPoisson and zero inflated negative binomial models. In addition, zero

\r\ninflated generalized Poisson and zero inflated double Poisson models

\r\nare also discussed and found in some literature. Recently zero

\r\ninflated inverse trinomial model and zero inflated strict arcsine

\r\nmodels are advocated and proven to serve as alternative models in

\r\nmodeling overdispersed count data caused by excessive zeros and

\r\nunobserved heterogeneity. The purpose of this paper is to review

\r\nsome related literature and provide a variety of examples from

\r\ndifferent disciplines in the application of zero inflated models.

\r\nDifferent model selection methods used in model comparison are

\r\ndiscussed.<\/p>\r\n","references":"

[1] M. Ridout, C. G. B. Demetrio, and J. Hinde, \u201cModels for count with\r\nmany zeros\u201d, in: Invited Paper Presented at the 19th International\r\nBiometric Conference, CapeTown, South Africa, 1998, 178.\r\n[2] A. C. Cameron and P. K. Trivedi, \u201cRegression analysis of count data\u201d.\r\nCambridge University Press. 1998\r\n[3] A. C. Cameron and P. K. Trivedi, \u201cMicroenometrics: Methods and\r\nApplications\u201d. Cambridge University Press. 2005\r\n[4] D. Lambert, \u201cZero-inflated Poisson regression, with an application to\r\nrandom defects in manufacturing\u201d. Technometrics, 34, 1992, 1-14\r\n[5] L. Tom, M. Beatrijs, and D.S. Olivia, \u201cThe analysis of zero-inflated\r\ncount data: Beyond zero-inflated Poisson regression\u201d, British Journal of\r\nMathematical and Statistical Psychology, 65, 163-180.\r\n[6] Y. Xia, M. Dianne, J. Ma, C. Feng, C. Wendy, and X. Tu, \u201cModeling\r\ncount outcomes from HIV risk reduction interventions: A comparison of\r\ncompeting statistical models for count responses\u201d, AIDS Research and\r\nTreatment, Vol. 2012, 1-11.\r\n[7] B. M. Golam Kibria, \u201c Applicaations of some discrete regression models\r\nfor count data\u201d, Pakistan Journal of Statistics and Operation research,\r\nVol11 No. 1, 2006, 1-16.\r\n[8] A. Bilgic, W. J. Florkowski, and C. Akbay, \u201cDemand for cigarettes in\r\nTurkey: an application of count data models\u201d, Empir, 39, 2010, 733-765.\r\n[9] A. Khan, S. Ullah, and J. Nitz, J. (2011). \u201cStatistical modelling of falls\r\ncount data with excess zeros. Journal of the International society for\r\nChild and Adolescent Injury Prevention (Inj Prev)\u201d, 17(4), 2011, 266-\r\n270.\r\n[10] S. Ullah, C. F. Finch, and L. Day, \u201cStatistical modelling for falls count\r\ndata\u201d. Accident Analysis and Prevention (Accid Anal Prev), 42(2),\r\n2010, 384-392.\r\n[11] K. K. W. Yau and K. C. H. Yip, \u201cOn modeling claim frequency data in\r\ngeneral insurance with extra zeros\u201d. Insurance: Mathematics and\r\nEconomics Vol. 36, Issue 2, 2005, 153-163.\r\n[12] A. H. Lee, M. R. Stevenson, K. Wang, and K. K. W. Yau, \u201cModelling\r\nyoung driver motor vehicle crashes: data with extra zeros\u201d, Accident\r\nAnalysis Prevention, 34, 2002, 515-521.\r\n[13] M. L. Dalrymple, I. L. Hudson, and R. P. K. Ford, \u201cFinite mixture, zeroinflated\r\nPoisson and hurdle models with application to SIDS\u201d,\r\nComputational Statistics & Data Analysis, 41, 2003, 491-504\r\n[14] A. C. Mehmet, \u201cZero-inflated regression models for modeling the effect\r\nof air pollutants on hospital admissions\u201d, Polish Journal of Environment\r\nStudies, Vol. 21, No. 3, 2012, 565-568.\r\n[15] R. Winkelmann, Econometric Analysis of Count Data. Springe Verlag,\r\nBerlin, Heidelberg, 2008.\r\n[16] R. Winkelmann, \u201cHealth care reform and the number of doctor visits \u2013\r\nAn econometric analysis,\u201d Journal of Applied Econometrics 19, 2004,\r\n455-472\r\n[17] K. K. W. Yau, K. Wang, and A. H.and Lee, \u201cZero-inflated negative\r\nbinomial mixed regression Modeling of overdispersed count data with\r\nextra zeros\u201d. Biometrical Journal, 45, 4, 2003, 437-452.\r\n[18] S. Gurmu and P. K. Trivedi, \u201cExcess zeros in count models for\r\nrecreational trips\u201d, Journal of Business and Economic Statistics, 14,\r\n1996, 469-477.\r\n[19] D. B. Hall, \u201cZero inflated Poisson and binomial with random effects: a\r\ncase study,\u201d Biometrics, 56, 2000, 1030-1039\r\n[20] D. Bohning, E. Dietz, P. Schlattman, L. Mendonca and U. Kirchner,\r\n\u201cThe zero-inflated Poisson model and the decayed, missing and filled\r\nteeth index in dental epidemiology\u201d. Journal of the Royal Statistical\r\nSociety, Series A, 1999, 162-209\r\n[21] P. J. W. Carrivick, A. H. Lee, and K. K. W. Yau, \u201cZero inflated Poisson\r\nmodeling to evaluate occupational safety interventions\u201d, Safety Science,\r\n41, 2002, 53-63.\r\n[22] A. H. Welsh, R. B. cunningham, C. F. Donnelly and D. B. Lindenmayer,\r\n\u201cModelling the abundance of rare species: statistical models for counts\r\nwith extra zeros\u201d, Ecolog Modell, 88, 1996, 297-308.\r\n[23] F. Famoye and P. S. Karan, \u201c Zero-Inflated Generalized Poisson\r\nRegression Model with an Application to Domestic Violence Data,\u201d J of\r\nData Science 4, 2006, 117-130.\r\n[24] Z. Yang, J. W. Hardin, and C. L. Addy, \u201cScore test for Zero inflation in\r\noverdispersed count data\u201d, Cummunication in Statistics \u2013 Theory and\r\nMethods, 39, 2010, 2008-2030.\r\n[25] C. Czado, V. Erhardt, A. Min, and S. Wagner, \u201c Zero-inflated\r\ngeneralized Poisson models with regression effects on the mean,\r\ndispersion and zero-inflation level applied to patent outsourcing rates\u201d,\r\nStatiscal Modelling, 7, 2, 2007, 125-153.\r\n[26] P. L. Gupta, R. C. Gupta, and R. C. Tripathi, Score test for zero inflated\r\ngeneralized model\u201d, Communication in Statistics \u2013 Theory and Methods,\r\nVol.33, No.1, 2004, 47-64.\r\n[27] Y. N. Phang, \u201cStatistical inference for a family of discrete distribution\r\nwith cubic variance functions\u201d, Unpublished PhD thesis, University\r\nMalaya, Malaysia, 2007\r\n[28] Y. N. Phang, and E. R. Loh. Proceedings: IASC 2008: Joint Meeting of\r\n4th World Conference of the IASC and 6th Conference of the IASC and\r\n6th conference of the Asian Regional Section of the IASC on\r\nComputational Statistic and Data Analysis, Yokohama, Japan, 2008\r\n[29] N. Jasakul, and P. H. John, \u201c Score tests for extra-zero models in zeroinflated\r\nnegative binomial models\u201d, Communications in Statistics-\r\nSimulation and Computation, 38, 2009, 92-108.\r\n[30] H. Akaike, \u201cA new look at the statistical model identification\u201d. IEEE\r\nTransaction on Automatic Control, 19(6), 1974, 716-724.\r\n[31] G. Schwarz, \u201cEstimating the dimensions of a model\u201d, Annals of\r\nStatistics, 6, 1978, 461-464\r\n[32] Q. H. Vuong, \u201cLikelihood ratio tests for model selection and non-nested\r\nhypotheses\u201d, Econometrica, 57, 1989, 307-333.\r\n[33] J. Neyman, and E. S. Pearson, \u201cOn the use and interpretation of certain\r\ntest criteria for purposes of statistical inference\u201d, Biometrika, 20, 1928,\r\n175-240.\r\n[34] G. Sileshi, \u201cSelecting the right statistical model for analysis of insect\r\ncount data by using information theoretic measures\u2019, Bulletin of\r\nEntomological Research, 96, 2006, 479-488.<\/p>\r\n","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 80, 2013"}