Jorge Ruiz 44th Annual Meeting of the Statistical Society of Canada

Time: May 29 to June 1, 2016
Place: Brock University, St. Catharines

Jorge Ruiz, research assistant of the IRCCF, attended the 44th Annual Meeting of the Statistical Society of Canada at Brock University in St. Catharines, Ontario from Sunday May 29 to Wednesday June 1, 2016.

His team participated in the case study entitled “What Predicts Sustainability of Canadian Charities”. In this particular case, they explored different characteristics of charitable organizations in Canada using data mining algorithms – specifically Random Forest, Decision Trees, and Gradient Boosting.

The Annual Meeting covered different subjects: Biostatistics, Actuarial and Finance, Education and Data Mining, and there were separate sections for each subject.

The one-day workshop “Bridging the gap: Turning classical statistics experience directly into a working knowledge of survey data analysis” was given by Claude Girard from Data Analysis Resource Center (DARC). He showed how researchers use survey data assuming that the data is independent and identically distributed (i.i.d.). This assumption is not always correct and, for this reason, researchers have to be careful that their results are not invalidated.

During the session “Quantile regression and extreme value analysis”, the researchers showed models that forecasted extremes for flooding, the development of non-parametric tools of extreme conditional quantiles and theory about weighted quantile regression.

The conference given by Sir David Spiegelhater from Cambridge University entitled “The Ups and (many) Downs of trying to be a ‘Public Statistician’” was really interesting. During this conference, Sir David showed how the media spread the information “statistic” without analyzing the meaning of the information.

In the session “Advanced Statistical and Machine learning techniques for high-dimensional data analysis”, researchers showed the latest models in selective inference, post model inferences, and variable selection.

More information available at

Photo by Peter Macdonald / CC BY-NC 2.0