Richard Lockhart, Professor
Department of Statistics and Actuarial Science
Phone: (778) 782 3264  Messages: (778) 782 3803  Fax: (778) 782 4368
Office: K 10561  Email: lockhart (at) sfu (dot) ca

Cambridge Minicourse, Lent, 2017
Course Notes, 8 Mar
Inference for High Dimensional Regression
Lecture Slides 
Big Data Workshop at SFU
PIMS page
Statistical Inference for Large Scale Data
Program, abstracts 
Big Data Workshop at UBC
PIMS page
Big Data in Environmental Science
Program, abstracts 
Statistics Canada
The Daily 
United States Census Bureau
Data 
UK Statistics
StatsUserNet 
Putnam solutions
1985 1986 1987 1988 1989 
The Statistical Society of Canada
Home 
Physics and Statistics at BIRS
July 2010 Workshop 
My old home page
I used to have a simpler page 
SFU sites
My department
My university
High Dimensional Inference
Lately I have had the privilege of working with Jon Taylor, Ryan Tibshirani, and Rob Tibshirani on inference for LASSO and LARS. They are experts; I am a joyrider. Too many coauthors to put pictures at left. Instead: Stanford.
Methodology in Goodness of Fit
I do goodness of fit, developing testing methods and associated large sample theory largely with Michael Stephens, Federico O'Reilly, Alberto Contreras Cristan, and a number of former students. Ted Anderson is at left.
Directional data
I have written a number of papers on directional data with Michael Stephens and Peter Guttorp. With Michael I wrote about goodnessoffit for the von~Mises distribution and worked with a student on von~Mises mixtures. With Peter I worked on direction finding for downed aircraft. That paper does Bayesian analysis of the problem of finding and object on the basis of bearings taken with von~Mises distributed errors. It also considers ``outlier'' detection in a directional context. Michael's PhD supervisor, Geoff Watson, is pictured at left.
Large Sample Theory
I like to work on large sample theory with what I think of as clean, simple conditions. Peter Guttorp and I did this sort of thing in work on inference in irregularly sampled random walks. That work was motivated by a paper I wrote applying the local central limit theorem to prove that on an explosive trajectory of a BienayméGaltonWatson only the mean, variance and perhaps one other arithmetic parameter admit consistent estimates. Then Peter and I worked on the large sample behaviour of quadratic forms in uniform order statistics. That grew out of work on QQ plots some of which I did with Graham McLaren. Recently I proved a conditional limit theorem for empirical distribution functionl tests. At left is Sir Francis Galton.
Applied papers
I have a paper with Peter Guttorp about finding downed aircraft, work with Chandanie Perera on thermoluminescence dating, early work with (or really for  I was a summer student at the time having just finished my BSc) Jim Zidek on traffic loading on the Lion's Gate Bridge.