C
Constantinos Goutis
Researcher at University College London
Publications - 21
Citations - 968
Constantinos Goutis is an academic researcher from University College London. The author has contributed to research in topics: Confidence interval & Total least squares. The author has an hindex of 10, co-authored 21 publications receiving 909 citations. Previous affiliations of Constantinos Goutis include ENSAE ParisTech & Carlos III Health Institute.
Papers
More filters
Journal ArticleDOI
An overview of robust Bayesian analysis
James O. Berger,Elías Moreno,Luis R. Pericchi,M. Jesús Bayarri,José M. Bernardo,Juan Antonio Cano,Julián de la Horra,Jacinto Martín,David Rios-Insua,Bruno Betrò,Anirban DasGupta,Paul Gustafson,Larry Wasserman,Joseph B. Kadane,Cid Srinivasan,Michael Lavine,Anthony O'Hagan,Wolfgang Polasek,Christian P. Robert,Constantinos Goutis,Fabrizio Ruggeri,G. Salinetti,Siva Sivaganesan +22 more
TL;DR: An overview of the subject of robust Bayesian analysis is provided, one that is accessible to statisticians outside the field, and recent developments in the area are reviewed.
Journal ArticleDOI
Model choice in generalised linear models: A Bayesian approach via Kullback-Leibler projections
TL;DR: A general Bayesian method of comparing models based on the Kullback-Leibler distance between two families of models, one nested within the other, which can judge whether or not a more parsimonious model is appropriate.
Journal ArticleDOI
Partial least squares algorithm yields shrinkage estimators
TL;DR: In this article, the authors give a geometric proof that the estimates of a regression model derived by using partial least squares shrink the ordinary least squares estimates, based on a sequential construction algorithm of partial least square.
Journal ArticleDOI
Improved Invariant Confidence Intervals for a Normal Variance
TL;DR: In this paper, confidence intervals for the variance of a normal distribution with unknown mean are constructed which improve upon the usual shortest interval based on the sample variance alone, and the posterior probabilities of the intervals are examined numerically.
Journal ArticleDOI
Assessing Evidence in Multiple Hypotheses
TL;DR: In this paper, the authors formulate the problem of choosing between two hypotheses as a problem of constructing a data-dependent evidential measure for or against the null hypothesis, and examine multivariate evidential measures constructed as combinations of univariate ones.