Joint models for longitudinal zero-inflated overdispersed binomial and normal responses. (English) Zbl 07761603
Summary: In this paper, we propose joint random effects models for longitudinal mixed overdispersion binomial and normal responses where the overdispersion binomial response is inflated in zero point. Also, we propose a new parametric distribution forms called as the Zero-Inflated LogLindley-Binomial distribution for overdispersed binomial response with extra zeros. A LogLindley-Binomial distribution is obtained by compounding LogLindley and Binomial distributions. The random effect approach is used to investigate both of the correlation between responses. A Monte Carlo EM algorithm is utilized to obtain the parametric estimation of the models parameters. The models are illustrated by simulation study. Finally, these models are applied to air quality data, obtained from an observational study on Tehran where the correlated responses are the overdispersed binomial with extra zeros of particulate matter and normal response of AQI. The simultaneous effects of some covariates on both responses are also investigates.
Keywords:
zero-inflated beta-binomial and normal joint model; zero-inflated LogLindley-binomial and normal joint model; random effects; the EM Algorithm; air quality dataReferences:
| [1] | Anderson, DA; Aitkin, M., Variance component models with binary response: interviewer variability, J. Roy. Stat. Soc. B, 47, 203-210 (1985) |
| [2] | Casella, G.; Berger, RL, Statistical Inference (2002), Pacific Grove: Duxbury Press, Pacific Grove · Zbl 0699.62001 |
| [3] | Deng, D.; Paul, SR, Score tests for zero-inflation and overdispersion in generalized linear models, Stat. Sin., 15, 2, 257-276 (2005) · Zbl 1059.62077 |
| [4] | Gilmour, AR; Anderson, RD; Rea, AL, The analysis of binomial data by a generalized linear mixed model, Biometrika, 72, 3, 593-599 (1985) · doi:10.1093/biomet/72.3.593 |
| [5] | Hall, DB, Zero-inflated Poisson and binomial regression with random effects: a case study, Biometrics, 56, 4, 1030-1039 (2000) · Zbl 1060.62535 · doi:10.1111/j.0006-341X.2000.01030.x |
| [6] | Hu, T.; Gallins, P.; Zhou, Y-H, A zero-inflated beta-binomial model for microbiome data analysis, Stat, 7, 1, e185 (2018) · Zbl 07851073 · doi:10.1002/sta4.185 |
| [7] | Kassahun, W.; Neyens, T.; Molenberghs, G.; Faes, C.; Verbeke, G., Modeling overdispersed longitudinal binary data using a combined beta and normal random-effects model, Archives of Public Health, 70, 1, 7 (2012) · Zbl 1457.62349 · doi:10.1186/0778-7367-70-7 |
| [8] | Kassahun, W.; Neyens, T.; Molenberghs, G.; Faes, CH; Verbeke, G., A joint model for hierarchical continuous and zero-inflated overdispersed count data, J. Stat. Comput. Simul, 85, 552-571 (2013) · Zbl 1457.62349 · doi:10.1080/00949655.2013.829058 |
| [9] | Kim, J.; Lee, JH, The validation of a beta-binomial model for overdispersed binomial data, Communications in Statistics - Simulation and Computation, 46, 2, 807-814 (2015) · Zbl 1362.62045 · doi:10.1080/03610918.2014.96009 |
| [10] | Lambert, D., Zero-inflated Poisson regression, with an application to defects in manufacturing, Technometrics, 34, 1-14 (1992) · Zbl 0850.62756 · doi:10.2307/1269547 |
| [11] | Molenberghs, G.; Verbeke, G.; Demtrio, C.; Vieira, A., A family of generalized linear models for repeated measures with normal and conjugate random effects, statistical science, 25, 3, 325-347 (2010) · Zbl 1329.62342 |
| [12] | Pearson, ES, Bayes’ theorem in the light of experimental sampling, Biometrika, 17, 3-4, 388-442 (1925) · JFM 51.0383.02 · doi:10.1093/biomet/17.3-4.388 |
| [13] | Skellam, JG, A probability distribution derived from the binomial distribution by regarding the probability of a success as variable between the sets of trials, Journal of the Royal Statistical Society Series B, 10, 257-261 (1948) · Zbl 0032.41903 |
| [14] | Varin, C.; Czado, C., A mixed autoregressive probit model for ordinal longitudinal data, Biostatistics, 11, 1, 127-138 (2010) · Zbl 1437.62640 · doi:10.1093/biostatistics/kxp042 |
| [15] | Wang, W., Identifiability of linear mixed effects models, Electron J. Stat, 7, 244-263 (2013) · Zbl 1337.62182 · doi:10.1214/13-EJS770 |
| [16] | Wu, H.; Zhang, Y.; Long, JD, Longitudinal beta-binomial modeling using GEE for overdispersed binomial data, Stat. Med., 36, 6, 1029-1040 (2017) · doi:10.1002/sim.7191 |
| [17] | Yang, S.; Harlow, LL; Puggioni, G.; Redding, CA, A Comparison of Different Methods of Zero-Inflated Data Analysis and an Application in Health Surveys, J. Mod. Appl. Stat. Methods, 16, 1, 518-543 (2017) · doi:10.22237/jmasm/1493598600 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
