Predictive Insights AI · Book
Contents
  1. Introduction
  2. Ch 0 · DataFest
  3. 1.1 Data exploration
  4. 1.2 Intro to modeling
  5. 1.3 GLMs
  6. 1.4 GLMs for classification
  7. 1.5 Classification metrics
  8. 1.6 More GLM topics
  9. 1.7 Variable selection
  10. 1.8 Tree-based models
  11. 1.9 Unsupervised learning
  12. Ch 2 · Cybersecurity
  13. 3.1 Health costs case study
  14. 3.2 Apartment applicants
  15. 3.3 Titanic case study
  16. Ch 4 · Tools
  17. Ch 5 · Seven mistakes
  18. Ch 6 · Entrepreneurship
  19. Wrap-up
  20. Appendix
  21. References
  22. PA R Study Manual

Predictive Analytics & Risk Modeling: For Insurance and Actuarial Science

Chapter 1.7: GLM Variable Selection: Stepwise, Ridge, Lasso and Elastic Net

Full edition

Stepwise selection, penalized regression with ridge, lasso and elastic net, with worked R examples.

This chapter is in the full direct PDF edition. The free online sample covers the Introduction, Chapter 0 and References.

Direct sales open soon. Check back shortly.

Full direct PDF edition: $14.99, sold by the author via X Money only.

Buy the PDF for $14.99 via X Money

Pay via X Money with the note EBOOK-A plus your email, and Sam emails the PDF within 24 hours. Questions: ExamPATutor@gmail.com. How buying direct works

Free companion material for this chapter:

Datasets and R setup for this chapter

Install the packages used in this chapter (free, from CRAN):

install.packages(c("tidyverse", "ExamPAData", "caret", "glmnet", "ISLR", "MASS"))

Hitters: ISLR package: GPL-2 (CRAN). Source: https://cran.r-project.org/package=ISLR

install.packages("ISLR")
library(ISLR)
data(Hitters)

health_insurance: ExamPAData package: MIT license (CRAN). Package docs describe it as practice-exam health claims data. A similar public 1,338-row ‘Medical Cost Personal Datasets’ file is on Kaggle under ODbL / Database Contents License. Source: https://cran.r-project.org/package=ExamPAData

install.packages("ExamPAData")
library(ExamPAData)
data(health_insurance)

Sources and further reading

More from the author: predictiveinsightsai.com