Subharup Guha

University of Missouri, Columbia, Missouri, United States

Are you Subharup Guha?

Claim your profile

Publications (4)2.78 Total impact

  • Subharup Guha
    [Show abstract] [Hide abstract]
    ABSTRACT: Supplement to the paper of M. Kyung, J. Gill and G. Casella [ibid. 20, No. 3, 259–290 (2011; Zbl 1241.65007)].
    Statistical Methods and Applications 08/2011; 20:291-293. · 0.35 Impact Factor
  • Source
    Steven N. MacEachern, Subharup Guha
    [Show abstract] [Hide abstract]
    ABSTRACT: The independent additive errors linear model consists of a structure for the mean and a separate structure for the error distribution. The error structure may be parametric or it may be semiparametric. Under alternative values of the mean structure, the best fitting additive errors model has an error distribution which can be represented as the convolution of the actual error distribution and the marginal distribution of a misspecification term. The model misspecification term results from the covariates' distribution. Conditions are developed to distinguish when the semiparametric model yields sharper inference than the parametric model and vice versa. The main conditions concern the actual error distribution and the covariates' distribution. The theoretical results explain a paradoxical finding in semiparametric Bayesian modelling, where the posterior distribution under a semiparametric model is found to be more concentrated than is the posterior distribution under a corresponding parametric model. The paradox is illustrated on a set of allometric data. The Canadian Journal of Statistics 39: 165–180; 2011 ©2011 Statistical Society of CanadaLe modèle linéaire avec des erreurs additives et indépendantes consiste en une structure pour la moyenne et une structure séparée pour la distribution des erreurs. Cette dernière structure peut être paramétrique ou semi-paramétrique. Sous des valeurs alternatives de la structure sur la moyenne, le modèle pour les erreurs additives ayant le meilleur ajustement peut être écrit comme la convolution de la vraie distribution des erreurs et de la distribution marginale du terme représentant l'inexactitude du modèle. Celui-ci provient de la distribution des covariables. Des conditions, sous lesquelles un modèle semi-paramétrique conduit à une meilleure inférence que le modèle paramétrique, sont établies. Le cas contraire est aussi considéré. Les principales conditions concernent la vraie distribution des erreurs et celle des covariables. Les résultats théoriques expliquent le paradoxe trouvé avec la modélisation semi-paramétrique où la distribution a posteriori est plus concentrée sous un modèle semi-paramétrique que sous le modèle paramétrique correspondant. Le paradoxe est illustré à l'aide d'un jeu de données allométriques. La revue canadienne de statistique 39: 165–180; 2011 © 2011 Société statistique du Canada
    Canadian Journal of Statistics 02/2011; 39(1):165 - 180. · 0.59 Impact Factor
  • Source
    Subharup Guha, Steven N. MacEachern
    [Show abstract] [Hide abstract]
    ABSTRACT: Benchmark estimation is motivated by the goal of producing an approximation to a poste- rior distribution that is better than the empirical distribution function. This is accomplished by incorporating additional information into the construction of the approximation. We fo- cus here on generalized post-stratication , the most successful implementation of benchmark estimation in our experience. We develop generalized post-stratication for settings where the source of the simulation diers from the posterior which is to be approximated. This al- lows us to use the techniques in settings where it is advantageous to draw from a distribution dieren t than the posterior, whether this is for exploration of the data and/or model, for algorithmic simplicity, to improve convergence of the simulation or for improved estimation of selected features of the posterior. We develop an asymptotic (in simulation size) theory for the estimators, providing con- ditions under which central limit theorems hold. The central limit theorems apply both to an importance sampling context and to direct sampling from the posterior distribution. The asymptotic results, coupled with large sample (size of data) approximation results provide guidance on how to implement generalized post-stratication . The theoretical results also explain the gains associated with generalized post-stratication and the empirically observed robustness to cutpoints for the strata. We note that the results apply well beyond the setting of Markov chain Monte Carlo simulation.
    Journal of the American Statistical Association 02/2006; 101(September):1175-1184. · 1.83 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: While studying various features of the posterior distribution of a vector-valued parameter using an MCMC sample, a subsample is often all that is available for analysis. The goal of benchmark estimation is to use the best available information, i.e. the full MCMC sample, to improve future estimates made on the basis of the subsample. We discuss a simple approach to do this and provide a theoretical basis for the method. The methodology and beneflts of benchmark estimation are illustrated using a well-known example from the literature. We obtain as much as an 80% reduction in MSE with the technique based on a 1-in-10 subsample and show that greater beneflts accrue with the thinner subsamples that are often used in practice.
    Journal of Computational and Graphical Statistics. 01/2004; 13(3).

Publication Stats

3 Citations
2.78 Total Impact Points

Institutions

  • 2011
    • University of Missouri
      • Department of Statistics
      Columbia, Missouri, United States
  • 2004
    • The Ohio State University
      • Division of Biostatistics
      Columbus, Ohio, United States