Lectures on Advanced Regression Methods

Time: 14:00 đến 17:00 ngày 24/07/2017, 09:00 đến 12:00 ngày 25/07/2017, 14:00 đến 17:00 ngày 26/07/2017, 09:00 đến 12:00 ngày 27/07/2017, 14:00 đến 17:00 ngày 28/07/2017,

Venue/Location: C2-714, VIASM

Purpose: Data scientists have at their disposal many regression techniques in predictive modeling. If the most well known is the (Gaussian) linear regression, other methods of regression can be performed: Ridge, Lasso and ElasticNet Regression, MARS, GAM, trees, SVR. . . Lectures will be accompanied by tutorials and computer lab works with R software.

Speaker: Vincent Lefieux, RTE Paris, France.

Content:

Schedule.

ctrinhJul2017.jpg

Program.

• Reminders on linear regression (including choice of predictive variables).

• Ridge, Lasso and ElasticNet Regression.

• Multivariate Adaptive Regression Splines (MARS).

• Generalized Additive Model (GAM).

• Regression trees and random forests.

• Support Vector Machine Regression (SVR).

Language. English.

Prerequisites.

• Probability.

• Linear Models.

• Inferential Statistics.

• Basic concepts of R software.

References.

• Breiman, L. (1996). Bagging predictors. Machine Learning, 24:123-140.

• Breiman, L. (2001). Random forests. Machine Learning, 45:5-32.

• Breiman, L., Friedman, J., Stone, C. J., and Olshen, R. (1984). Classification And Regression Trees. Taylor & Francis.

• Hastie, T. and Tibshirani, R. (1990). Generalized additive models. CRC. Chapman & Hall.

• Hastie, T., Tibshirani, R., and Friedman, J. (2009). The elements of statistical learning. Data Mining, inference, and prediction. Springer Series in Statistics. Springer, 2 edition.

• Wood, S. (2006). Generalized additive models: an introduction with R. CRC. Chapman & Hall.