IJSREG Trion Studio

No Publication Cost

Vol 4, No 1 :

openaccess

Mixed Effects Model for Ordered Categorical Data in Longitudinal Study with Skew Normal Random Effects
Azad Roshani , Suresh Kumar Sharma , Kanchan Jain
Abstract

The study of categorical data is one of the most crucial part of statistical analysis. Modeling for these data has been considered by many authors in terms of log linear, logit, probit and logistic models. Mixed effects models containing both fixed and random effects are useful in a variety topics in the physical, biological and social sciences. In present study, some considerations have been sought in parallel categorical data such as the relation between the past and presentwith some rigorous modeling techniques. The relation is usually depicted via random effects. Random effect distribution can control the correlation among variables in longitudinal study in an appropriate way. When the response variable is an ordinal random variable, random effect distribution is taken as multivariate normal distribution. According to Azzalini(1985) the skew normal distribution has better properties and it is more efficient. In the present paper, an attempt has been made to study mixed effects model wherein the random effects follow skew normaldistribution given by Azzalini (1985).The mixed model is considered for longitudinal ordered categorical data. A method for estimating the model parameters has been explored. The properties of the proposed model have been investigated in terms of validity and efficiency. Comparisons have also been made between fixed effect model and model with skew normal random effects. Simulation have been carried out for finding the estimates of the model parameters.
Full Text
PDF
References

Azzalini and A. Capitaino; Statistical applications of the multivariate skew-normal distribution. Journal of the Royal Statistical Society, Series B, 61, 579-602 (1999).
Azzalini and A. Dalla Valle; The multivariate skew-normal distribution. Biometrika, 83, 715-726 (1996).
Azzalini; A class of distributions which includes the normal ones. Scandinavian Journal of Statistics, 12, 171-178 (1985).
Biswas and K. Das; A Bayesian analysis of bivariate ordinal data: Wisconsin epidemiologic study of diabetic retinopathy revisited. Statistics in Medicine, 21, 549-559 (2002).
B. Liseo and N. Loperfido; A Bayesian interpretation of the multivariate skew-normal distribution. Statistics and Probability Letters, 61, 395-401 (2003).
E. T. Bradlow and A. M. Zaslavsky; A hierarchical latent variable model for ordinal data from a customer satisfaction survey with "no answer" responses. Journal of the American Statistical Association, 94, 43-52 (1999).
G. Gonz´alez-Farias, A. Dom´ınguez-Molina and A. K. Gupta; Additive properties of skew normal random vectors. Journal of Statistical Planning and Inference, 126, 521-534 (2004).
G. Verberkand E.Lesaffre; A linear mixed-effects model with heterogeneity in the random-effects population. Journal of the American Statistical Association, 91, 217-221 (1996).
H. Ishwaran and C. A. Gatsonis; A general class of hierarchical ordinal regression models with applications to correlated ROC analysis. The Canadian Journal of Statistics, 28, 731-750 (2000).
H. Ishwaran; Univariate mid multirater ordinal cumulative link regression with covariate specific cutpoints. The Canadian Journal of Statistics, 28, 715-730 (2000).
J. B. Lang; Bayesian ordinal and binary regression models with a parametric family of mixture links. Computational Statistics and Data Analysis, 31, 59-87 (1999).
J. C. Lee, T. I. Lin, K. J. Lee and Y. L. Hsu; Bayesian analysis of Box-Cox transformed linear mixed models with ARMA(p,q) dependence. Journal of Statistical Planning and Inference, 133, 435-451 (2005).
J. C. Pinheiro, C. H. Liu and Y. N. Wu; Efficient algorithms for robust estimation in linear mixed-effects models using the multivariate t distribution. Journal of Computational and Graphical Statistics, 10, 249–276 (2001).
M. K. Cowles, B. P. Carlin and J. E. Connett; (Bayesian tobit modeling of longitudinal ordinal clinical trial compliance data with nonignorablemissingness. Journal of the American Statistical Association, 91,86-98 (1996).
M. Tan, Y. S. Qu, E. Mascha and A. Schubert; A Bayesian hierarchical model for multilevel repeated ordinal data: analysis of oral practice examinations in a large anesthesiology training program. Statistics in Medicine, 18, 1983-1992 (1999).
M. Xie, D. G. Simpson and R. J. Carroll; Random effects in censored ordinal regression: Latent structure and Bayesian approach. Biometrics, 56, 376-383 (2000).
N.M. Laird and J. H. Ware; Random effects models for longitudinal data. Biometrics, 38, 963-974 (1982).
P. E. Rossi, Z. Gilula, and G. M. Allenby; (2001). Overcoming scaleusage heterogeneity: A Bayesian hierarchical approach. Journal of the American Statistical Association, 96, 20-31.
Q. Liu and D. A. Pierce; A note on Gauss-Hermite quadrature. Biometrika, 81, 624-29(1994).
R. B. Arellano-Valle and M. G. Genton; On fundamental skew distributions. Journal of Multivariate Analysis, 96, 93-116 (2005).
R. D. Gibbons and D.Hedeker; Application of random-effects probit regression models. Journal of Consulting and Clinical Psychology, 62, 285-296 (1994).
S. K. Sahu, D. K. Dey and M. D. Branco; A new class of multivariate skew distributions with application to Bayesian regression models. Canadian Journal of Statistics, 31, 129-150. 9 (2003).
T. I. Lin and J. C. Lee; On modelling data from degradation sample paths over time. Australian and New Zealand Journal of Statistics, 45, 257-270 (2003).
U. Chipman and M. Hamada; Bayesian analysis of ordered categorical data from industrial experiments. Technimetrics, 38, 1-10 (1996).

ISSN(P) 2350-0174

ISSN(O) 2456-2378

Journal Content
Browser