## General location multivariate latent variable models for mixed correlated bounded continuous, ordinal, and nominal responses with non-ignorable missing data.(English)Zbl 07482760

Summary: Using a multivariate latent variable approach, this article proposes some new general models to analyze the correlated bounded continuous and categorical (nominal or/and ordinal) responses with and without non-ignorable missing values. First, we discuss regression methods for jointly analyzing continuous, nominal, and ordinal responses that we motivated by analyzing data from studies of toxicity development. Second, using the beta and Dirichlet distributions, we extend the models so that some bounded continuous responses are replaced for continuous responses. The joint distribution of the bounded continuous, nominal and ordinal variables is decomposed into a marginal multinomial distribution for the nominal variable and a conditional multivariate joint distribution for the bounded continuous and ordinal variables given the nominal variable. We estimate the regression parameters under the new general location models using the maximum-likelihood method. Sensitivity analysis is also performed to study the influence of small perturbations of the parameters of the missing mechanisms of the model on the maximal normal curvature. The proposed models are applied to two data sets: BMI, Steatosis and Osteoporosis data and Tehran household expenditure budgets.

### MSC:

 62J12 Generalized linear models (logistic models) 62J05 Linear regression; mixed models 62Pxx Applications of statistics

DirichletReg
Full Text:

### References:

 [1] Amiri, L.; Khazaei, M.; Ganjali, M., The grouped continuous model for multivariate ordered categorical variables and covariate adjustment, Adv. Data. Anal. Classif., 11, 593-609 (2017) · Zbl 1414.62205 [2] Anderson, J. A.; Pemberton, J. D., The grouped continuous model for multivariate ordered categorical variables and covariate adjustment, Biometrics, 41, 875-885 (1985) · Zbl 0615.62065 [3] Anholeto, T.; Sandoval, M. C.; Botter, D. A., Adjusted Pearson residuals in beta regression models, J. Stat. Comput. Simul., 84, 999-1014 (2014) · Zbl 1453.62028 [4] Barreto-Souza, W.; Simas, A. B., Improving estimation for beta regression models via em-algorithm and related diagnostic tools, J. Stat. Comput. Simul., 87, 2847-2867 (2017) · Zbl 07192098 [5] Belin, T.; Hu, M. Y.; Young, A. S.; Grusky, O., Performance of a general location model with an ignorable missing-data assumption in a multivariate mental health services study, Stat. Med., 18, 3123-3135 (1999) [6] Chen, S. X.; Tang, C. Y., Nonparametric regression with discrete covariate and missing values, Stat. Interface., 4, 463-474 (2011) · Zbl 1245.62036 [7] Cook, R. D., Assessment of local influence, J. R. Stat. Soc. Ser. B, 48, 133-169 (1986) · Zbl 0608.62041 [8] Cox, D. R., The analysis of multivariate binary data, J. Appl. Stat., 21, 113-126 (1972) [9] Cox, D. R.; Wermuth, N., Response models for mixed binary and quantities variables, Biometrika, 79, 441-461 (1992) · Zbl 0766.62042 [10] Cui, R.; Bucur, I. G.; Groot, P.; Heskes, T., A novel Bayesian approach for latent variable modeling from mixed data with missing values, Stat. Comput., 29, 1-17 (2019) · Zbl 07119307 [11] De Leon, A. R.; Carriere, K. C., The one-sample location hypothesis for mixed bivariate data, Comm. Statist. Theory Methods, 29, 2573-2581 (2000) · Zbl 0993.62014 [12] De Leon, A. R.; Carriere, K. C., General mixed data model: extension of general location and grouped continuous models, Can. J. Stat., 35, 533-548 (2007) · Zbl 1143.62323 [13] De Leon, A. R.; Chough, K. C., Analysis of Mixed Data: Methods and Applications (2013), CRC Press: CRC Press, New York [14] De Souza, D. F.; Da Silva Moura, F. A., Multivariate beta regression with application in small area estimation, J. Off. Stat., 32, 747-768 (2016) [15] Ferrari, S. L.P.; Cribari-Neto, F., Beta regression for modeling rates and proportions, J. Appl. Stat., 31, 799-815 (2004) · Zbl 1121.62367 [16] Ferrari, S. L.; Pinheiro, E. C., Improved likelihood inference in beta regression, J. Stat. Comput. Simul., 81, 431-443 (2011) · Zbl 1221.62101 [17] Heckman, J., Dummy endogenous variable in a simultaneous equation system, Econometrica, 6, 931-959 (1978) · Zbl 0382.62095 [18] Kieschnick, R.; McCullough, B. D., Regression analysis of variates observed on (0, 1): percentages, proportions and fractions, Stat. Modell., 3, 193-213 (2003) · Zbl 1070.62056 [19] Little, R. J.; Rubin, D., Statistical Analysis with Missing Data, 14 (2002), Wiley: Wiley, New york [20] Maier, M.J., DirichletReg: Dirichlet regression for compositional data in R, Research Report Series / Department of Statistics and Mathematics, 125. WU Vienna University of Economics and Business, Vienna, 2014. [21] Mirkamali, S. J.; Ganjali, M., A general location model with zero-inflated counts and skew normal outcomes, J. Appl. Stat., 44, 2716-2728 (2017) · Zbl 07282178 [22] Olkin, I.; Tate, R. F., Multivariate correlation models with mixed discrete and continuous variables, Ann. Math. Statist., 32, 743-453 (1961) · Zbl 0113.35101 [23] Paleti, R.; Bhat, C. R.; Pendyala, R. M., Integrated model of residential location, work location, vehicle ownership, and commute tour characteristics, Transp. Res. Rec., 2382, 162-172 (2013) [24] Pearson, K., Mathematical Contribution to the Theory of Evolution. Xiii. on the Theory of Contingency and Its Relation to Association and Normal Correlation (1904), Dulau and Co.: Dulau and Co., London [25] Peng, Y. H.; Little, R. J.A.; Raghunathan, T. E., An extended general location model for causal inferences from data subject to noncompliance and missing values, Biometrics, 60, 598-607 (2004) · Zbl 1274.62046 [26] Poon, W. Y.; Lee, S. Y., Maximum likelihood estimation of multivariate polyserial and polychoric correlation coefficients, Psychometrika, 52, 409-430 (1987) · Zbl 0627.62060 [27] Rubin, D. B., Inference and missing data, Biometrika, 63, 581-590 (1976) · Zbl 0344.62034 [28] Tabrizi, E.; Samani, E. B.; Ganjali, M., Analysis of mixed correlated bivariate zero-inflated count and (k,l)-inflated beta responses with application to social network datasets, Commun. Stat. Theory Methods, 48, 1651-1681 (2018) [29] Tabrizi, E.; Samani, E. B.; Ganjali, M., Joint modeling of mixed zero-inflated count and (k,l)-inflated beta longitudinal responses with nonignorable missing values for social network analysis, Multivariate Behavioral Research J Appl. Statistics (2020) [30] Tabrizi, E.; Samani, E. B.; Ganjali, M., A note on the identifiability of latent variable models for mixed longitudinal data, Stat. Probab. Lett (2020) · Zbl 1455.62102 [31] Wang, W., Identifiability of linear mixed effects models, Electron. J. Stat., 7, 244-263 (2013) · Zbl 1337.62182
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. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.