Actuarial Outpost
 
Go Back   Actuarial Outpost > Actuarial Discussion Forum > Property - Casualty / General Insurance
FlashChat Actuarial Discussion Preliminary Exams CAS/SOA Exams Cyberchat Around the World Suggestions


Fill in a brief DW Simpson Registration Form
to be contacted when new jobs meet your criteria.


Reply
 
Thread Tools Search this Thread Display Modes
  #51  
Old 06-12-2019, 11:42 AM
bjc2142's Avatar
bjc2142 bjc2142 is offline
Member
CAS
 
Join Date: Aug 2014
Location: Boston
Studying for Python and DS
Favorite beer: Asahi Draft
Posts: 1,198
Default

Quote:
Originally Posted by Vorian Atreides View Post
Thanks for sharing that bjc. I've left you a comment as well.
Reply With Quote
  #52  
Old 07-10-2019, 11:11 AM
bjc2142's Avatar
bjc2142 bjc2142 is offline
Member
CAS
 
Join Date: Aug 2014
Location: Boston
Studying for Python and DS
Favorite beer: Asahi Draft
Posts: 1,198
Default

Quote:
Originally Posted by Actuarially Me View Post
Practitioners guide to GLMs (Warning: Clicking link will download PDF). Somehow this one slipped past me until yesterday. Another user on here suggested it and after a 30 second overview, it does better at explaining things that I have done above.
op, I think WTW removed the paper from their website or changed path. The same pdf is available from CAS website instead.
__________________
FCAS
Reply With Quote
  #53  
Old 08-12-2019, 11:54 AM
Actuarially Me Actuarially Me is offline
Member
CAS
 
Join Date: Jun 2013
Posts: 191
Default

Just read through GLMs w/ Examples in R as a potential textbook to use for a statistics minor at my old school. I really like the Springer series books (Intro Statistical Learning, Applied Predictive Modeling, and Elements of Statistical Modeling).

I'd definitely suggest it if you want to get more in depth into the mathematics behind GLMs. It covers the Tweedie distribution and the R code is still up to date (Applied Predictive Modeling is pretty outdated for the version I have). At 500 pages, I'll probably refer back to this instead of the CAS monographs.

My gf is taking Exam 8 and thinks it's easier to follow than the monograph. Even when it gets to the Linear Algebra, it's not that hard to parse though what's going on. Compared to Elements of Statistical Learning which is very dense.

Last edited by Actuarially Me; 08-12-2019 at 12:55 PM..
Reply With Quote
  #54  
Old 09-16-2019, 12:12 PM
J. Caesar J. Caesar is offline
Member
CAS
 
Join Date: Nov 2016
College: Virginia Tech
Posts: 45
Default

Thanks for writing this up. I love working in R and all things tidy, so naturally I'm frustrated that there doesn't seem to be a ton of options when it comes to elastic net regression in R.

glmnet is limited on the distributions you can select (e.g. no gamma), and HDtweedie doesn't seem to allow you to specify the link (instead enforcing the canonical link for a given $p$).

So how does one build an elastic net Gamma regression in R with a log link?
Reply With Quote
  #55  
Old 09-16-2019, 12:42 PM
bjc2142's Avatar
bjc2142 bjc2142 is offline
Member
CAS
 
Join Date: Aug 2014
Location: Boston
Studying for Python and DS
Favorite beer: Asahi Draft
Posts: 1,198
Default

Quote:
Originally Posted by J. Caesar View Post
Thanks for writing this up. I love working in R and all things tidy, so naturally I'm frustrated that there doesn't seem to be a ton of options when it comes to elastic net regression in R.

glmnet is limited on the distributions you can select (e.g. no gamma), and HDtweedie doesn't seem to allow you to specify the link (instead enforcing the canonical link for a given $p$).

So how does one build an elastic net Gamma regression in R with a log link?
I don't use R. Have you tried R H2O?
__________________
FCAS
Reply With Quote
Reply

Thread Tools Search this Thread
Search this Thread:

Advanced Search
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off


All times are GMT -4. The time now is 11:10 PM.


Powered by vBulletin®
Copyright ©2000 - 2019, Jelsoft Enterprises Ltd.
*PLEASE NOTE: Posts are not checked for accuracy, and do not
represent the views of the Actuarial Outpost or its sponsors.
Page generated in 0.15241 seconds with 11 queries