Actuarial Outpost
 
Go Back   Actuarial Outpost > Exams - Please Limit Discussion to Exam-Related Topics > CAS > CAS Exams > Exam 8 (old Part 9) - Advanced Ratemaking
FlashChat Actuarial Discussion Preliminary Exams CAS/SOA Exams Cyberchat Around the World Suggestions


Reply
 
Thread Tools Search this Thread Display Modes
  #361  
Old Today, 12:35 AM
AbedNadir's Avatar
AbedNadir AbedNadir is offline
Member
CAS SOA
 
Join Date: Mar 2014
Studying for FCAS
Posts: 2,563
Default

DoF is number of parameters minus 1 for the intercept
__________________
Reply With Quote
  #362  
Old Today, 12:38 AM
AbedNadir's Avatar
AbedNadir AbedNadir is offline
Member
CAS SOA
 
Join Date: Mar 2014
Studying for FCAS
Posts: 2,563
Default

the denominator of F-Test appears to include the intercept, k is the parameter number and the denominator is n-k, but the DoF in the model is k-1
__________________
Reply With Quote
  #363  
Old Today, 02:22 AM
CFF CFF is online now
Member
CAS
 
Join Date: Apr 2014
Studying for 789
Posts: 104
Default

Quote:
Originally Posted by AbedNadir View Post
the denominator of F-Test appears to include the intercept, k is the parameter number and the denominator is n-k, but the DoF in the model is k-1
Good point, that’s why I listed out both of those two instances in one of my prior posts and I tried to equate them, but can’t cuz DoF just changes depend on context I think.

So DoF for a GLM is all beta exclude intercept aka beta0.
In F test, DoF is #datapoint minus #parameter(ALL bets include beta0) in the comparison step.

If anyone has any more updates on this please do so. Thanks!

Last edited by CFF; Today at 05:37 AM..
Reply With Quote
  #364  
Old Today, 11:02 AM
DamSon's Avatar
DamSon DamSon is online now
Member
CAS
 
Join Date: Sep 2018
Location: NYC
Studying for 8
Favorite beer: Alcoholic
Posts: 180
Default

Quote:
Originally Posted by AbedNadir View Post
DoF is number of parameters minus 1 for the intercept
Quote:
Originally Posted by CFF View Post
Good point, that’s why I listed out both of those two instances in one of my prior posts and I tried to equate them, but can’t cuz DoF just changes depend on context I think.

So DoF for a GLM is all beta exclude intercept aka beta0.
In F test, DoF is #datapoint minus #parameter(ALL bets include beta0) in the comparison step.

If anyone has any more updates on this please do so. Thanks!
I'm pretty sure the DoF is just = # parameters. Again, there are probably different definitions depending on if you check actual statistics sources, but the GLM paper says it's equal to the # of parameters.

If you check some of the past exam S problems, they're pretty explicit about the intercept adding to the DoF. Spring 2016 Exam S Q35 is a good example, as in Model 1, Risk class should have 4 estimated parameters from 5 classes. One extra DoF is added for the intercept to get the 5 shown in the problem.
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 05:33 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 0.14229 seconds with 9 queries