Hello! Welcome to my website! Thank you for visiting.
Note: Please look for information regarding my publications, presentations and software under the tab marked Publications.
I am a statistician, a data analyst if you will, specializing in the data analysis aspects of bioinformatics.
Currently, I am Senior Director and Janssen Fellow in Nonclinical Biostatistics at Janssen Research & Development, where I head up a talented team of biostatisticians who provide high quality statistical expertise to scientists and bioinformaticians engaged in drug discovery and translational research.
Quite a few years ago, I received my Ph.D. in Statistics from Princeton University with Professor John W. Tukey as advisor (check out Wikipedia's entry on Tukey for a "bit" about him - and to see why "bit" is in quotes). After graduation, I joined the statistics faculty at the University of New Mexico before moving on to industry.
I received my undergraduate training in Sri Lanka at the University of Colombo, from where I graduated with a B.Sc. (First Class Honours) in Mathematics & Statistics.
I grew up in Colombo, Sri Lanka. All my early schooling was at St Thomas' College, Mt Lavinia, Sri Lanka ("The School by the Sea").
"The best thing about being a statistician is that you get to play in everyone's backyard." -- John W Tukey
"Exploratory data analysis is detective work." -- John W Tukey
"Far better an approximate answer to the right question than an exact answer to the wrong question." -- John W Tukey
In general, I am interested in the application of statistics to more or less any problem that can be formulated quantitatively. Since data rarely behave as nicely as they are supposed to, I have found exploratory data analysis (EDA) techniques, robust and resistant statistical methods, and resampling and rerandomization procedures to be far more useful than generally advertised. And part of the fun is developing a new approach when a canned approach is not readily available or appropriate.
In particular, I am interested in the exploration, mining, and analysis of large multivariate (and mega-variate) data sets that have emerged due to the modern hi-tech revolution and the feasibility of large-scale data collection. Such data arise quite naturally in genomics experiments such as those that utilize DNA microarray technology, in proteomics experiments such as those that utilize mass spectrometry, and in structure-activity relationship studies.