• If you are citizen of an European Union member nation, you may not use this service unless you are at least 16 years old.

  • Whenever you search in PBworks or on the Web, Dokkio Sidebar (from the makers of PBworks) will run the same search in your Drive, Dropbox, OneDrive, Gmail, Slack, and browsed web pages. Now you can find what you're looking for wherever it lives. Try Dokkio Sidebar for free.



Page history last edited by mike@mbowles.com 11 years ago

Reference for glmnet: http://www.stanford.edu/~hastie/Papers/glmnet.pdf


Here's R-code for in-class examples:

    A new version of the IRLS algo for logistic regression.  This version adds calculation of covariance matrix for betas.


     A new version of glmnet applied to zipcode data.  this version does training on all 10 digits and runs against the test set

          to calculate error rate on out of sample test-set.


     Some simple examples using spline functions as part of linear least squares fits. 


     Using glmnet to classify iris data


     Several different basis expansions in conjunction with glmnet to classify sonar data.


     SA heart study with 4 df spline basis expansion.


     Concrete strength predicting using various combinations of basis expansions


     Bone density smoother



Data Sets:

     Concrete Data;



Cross-validation plot for 10-digit handwritten zip code character recognition




Generalized Linear Models approximate the data with a curve similar to

     Linear Models which approximate the data with a straight line.


In this plot points are approximated with a line (using lm in r)

In this plot points are approximated with a curve (using glm in r)

      (the r code used to produce these plots)



Recorded Lectures:


Part 1: https://datamining.webex.com/datamining/ldr.php?AT=pb&SP=MC&rID=107734827&rKey=2ffe310143519e90


Part 2: https://datamining.webex.com/datamining/ldr.php?AT=pb&SP=MC&rID=107734837&rKey=8cbadda8ad08416f


Part 3: https://datamining.webex.com/datamining/ldr.php?AT=pb&SP=MC&rID=107734847&rKey=01ce38478bb66b06




Comments (0)

You don't have permission to comment on this page.