{"id":1586,"date":"2017-08-14T08:55:02","date_gmt":"2017-08-14T02:55:02","guid":{"rendered":"https:\/\/dev.isrt.ac.bd\/?post_type=tribe_events&p=1586"},"modified":"2017-08-14T08:55:02","modified_gmt":"2017-08-14T02:55:02","slug":"seminar-on-sunday-may-27-2007","status":"publish","type":"tribe_events","link":"https:\/\/isrt.ac.bd\/event\/seminar-on-sunday-may-27-2007\/","title":{"rendered":"Seminar on Sunday, May 27, 2007"},"content":{"rendered":"
Seminar : Robust linear model selection based on Least Angle Regression<\/h1>\n
<\/div>\n
\n
May 26, 2007 – 1:59am<\/em><\/span><\/p>\n
\n\n
\n
Full Title:<\/strong><\/td>\n
Robust linear model selection based on Least Angle Regression<\/td>\n<\/tr>\n
\n
Speaker:<\/strong><\/td>\n
Jafar A Khan, PhD<\/td>\n<\/tr>\n
\n
<\/td>\n
Department of Statistics, Deltin 7 Aviator গেম টাকা ইনকাম of Deltin 7 bangladesh, Bangladesh<\/td>\n<\/tr>\n
\n
Date\/Time:<\/strong><\/td>\n
Sunday, May 27, 2007<\/span>,\u00a01200<\/td>\n<\/tr>\n
Abstract We consider the problem of building a linear prediction model when the number of candidate covariates is large and the dataset contains a fraction of outliers and other contaminations that are difficult to visualize and clean. We aim at predicting the future non-outlying cases. Therefore, we need methods that are robust and scalable at the same time.<\/p>\n
Our two-step model building procedure consists of\u00a0sequencing<\/em>\u00a0and\u00a0segmentation<\/em>. In\u00a0sequencing<\/em>, we order the covariates and the first m covariates form a reduced set for further consideration. The\u00a0segmentation<\/em>\u00a0step carefully examines subsets of the covariates in the reduced set to select the final prediction model.<\/p>\n
We need a suitable step–by–step algorithm to sequence the covariates. Since Forward Selection (FS) is aggressive, we focus on Least Angle Regression (LARS), a powerful algorithm recently proposed by Efron, Hastie, Johnstone and Tibshirani (2004). We review LARS, and explain one approach to its robustification.<\/p>\n<\/div>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"