Photograph of Surajit Ray

Surajit Ray

University Gardens
University of Glasgow GLASGOW G12 8QQ

Phone:   0141 330 6238
Fax:       0141 330 4814
E-mail: Surajit.Ray at
Research Interests: My research interests are in the area of model selection, the theory and geometry of mixture models and functional data analysis. I am especially interested in challenges presented by "large magnitude", both in the dimension of data vectors and in the number of vector. Core areas of methodological research include multivariate mixtures, structural equations models, high-dimensional clustering and functional clustering. Key collaborative activities involve projects in immunology, modeling of climate ecosystem dynamics and medical image segmentation.

Recently Published and Working Papers
Kernels, degrees of freedom, and power properties of quadratic goodness of fit tests. with B.G. Lindsay and M. Markatou.
To appear in the Journal of American Statistical Association (2012)
Journal Page | PDF | Bibtex
Functional Factor Analysis For Periodic Remote Sensing Data with Chong Liu, Giles Hooker, and Mark Friedl.
Annals of Applied Statistics 2012, Vol 6, No 2
PDF | Supplement
A Comparison of Bayes Factor Approximation Methods Including Two New Methods with K. Bollen, J. Zavisca and Jeffrey J. Harden.
To appear in Sociological Methods & Research (2012)
On the upper bound of the number of modes of a multivariate normal mixture with Dan Ren
To appear in the Journal of Multivariate Analysis (2012)
Preprint | Journal Page
Improving Model Selection in Structural Equation Models with New Bayes Factor Approximations with K. Bollen, J. Zavisca and Jeffrey J. Harden.
Submitted to Sociological Methodology (2011)
Data processing and analysis for protein microarrays. David S Deluca, Ovidiu Marina, Guang Lan Zhang, Catherine J Wu and Vladimir Brusic.
Methods Mol Biol. (2011) 723:337-47. pmid 21370075
pdf | PubMed | Journal Page |
Evaluation of MHC class I peptide binding prediction servers: applications for vaccine research with Hong Huang Lin, Songsak Tongchusak, Ellis L. Reinherz and Vladimir Brusic.  
BMC Immunology 2008, 9:8
pdf | PubMed | Journal Page |
Model selection in High-Dimensions: A Quadratic-risk Based Approach with B.G. Lindsay
Journal of the Royal Statistical Society - Series B: 70(1) Page 95-118, February 2008
pdf | ps | arxiv | Journal Page |
Quadratic distances on probabilities: a unified foundation with B.G. Lindsay, M. Markatou, K. Yang, S.C. Chen.
Annals of Statistics 2008, Vol. 36, No. 2, page 983--1006
pdf | ps | Journal Page |
A Nonparametric Statistical Approach to Clustering via Mode Identification with Bruce G Lindsay and Jia Li
Journal of Machine Learning Research 8(Aug):1687--1723, 2007
pdf | Journal Page | Software
Statistics on Anatomic Objects Reflecting Inter-Object Relations with Ja-Yeon Jeong and Stephen M.Pizer
Proceedings of International Workshop on Mathematical Foundations of Computational Anatomy pp. 136-145, 2006
pdf | Poster |
Signaling Local Non-credibility in an Automatic Segmentation Pipeline with Joshua H. Levy, Robert E. Broadhurst, Edward L. Chaney and Stephen M. Pizer
Proceedings of the SPIE, Vol. 6512, 2007
pdf | Journal Page |

Something putside the box