Abstract | ||
---|---|---|
We develop a dynamic Bayesian beta model for modeling and forecasting single time series of rates or proportions. This work is related to a class of dynamic generalized linear models (DGLMs), although, for convenience, we use non-conjugate priors. The proposed methodology is based on approximate analysis relying on Bayesian linear estimation, nonlinear system of equations solution and Gaussian quadrature. Intentionally we avoid MCMC strategy, keeping the desired sequential nature of the Bayesian analysis. Applications to both real and simulated data are provided. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1016/j.csda.2010.12.011 | Computational Statistics & Data Analysis |
Keywords | Field | DocType |
generalized linear models,dynamic bayesian beta model,logistic–normal distribution,bayesian analysis,bayesian linear estimation,non-conjugate prior,dynamic models,nonlinear system,beta distribution,gaussian quadrature,mcmc strategy,dynamic generalized linear model,equations solution,approximate analysis,general linear model,conjugate prior,time series,normal distribution | Econometrics,Variable-order Bayesian network,Linear system,Bayesian average,Bayesian linear regression,Bayesian statistics,Statistics,Prior probability,Mathematics,Dynamic Bayesian network,Bayesian probability | Journal |
Volume | Issue | ISSN |
55 | 6 | Computational Statistics and Data Analysis |
Citations | PageRank | References |
3 | 0.74 | 1 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
C. Q. da-Silva | 1 | 4 | 1.69 |
H. S. Migon | 2 | 3 | 0.74 |
L. T. Correia | 3 | 3 | 0.74 |