Actuarial Outpost
 
Go Back   Actuarial Outpost > Exams - Please Limit Discussion to Exam-Related Topics > SoA/CAS Preliminary Exams > Short-Term Actuarial Math
FlashChat Actuarial Discussion Preliminary Exams CAS/SOA Exams Cyberchat Around the World Suggestions


Not looking for a job? Tell us about your ideal job,
and we'll only contact you when it opens up.
https://www.dwsimpson.com/register


Short-Term Actuarial Math Old Exam C Forum

Reply
 
Thread Tools Search this Thread Display Modes
  #551  
Old 06-04-2016, 03:47 PM
LoLActuary LoLActuary is offline
Member
SOA
 
Join Date: Aug 2014
Studying for ERM
Posts: 391
Default

I've read a lot of varying opinions on this exam. Some people say doing problems wont work and you have to know the material like the back of your hand. Some other people say they just did a ton of practice exams and ended up passing with flying colors. I'm hoping enough practice problems from different sources will help me enough. I'm getting nervous...
__________________
ASA

FSA Exams: LP | LFV | ERM
FSA Modules: Reg & Tax | ERM | Financial Econ | DMAC
Reply With Quote
  #552  
Old 06-04-2016, 05:19 PM
el jefe el jefe is offline
Member
SOA
 
Join Date: Aug 2014
Studying for C
Posts: 78
Default

Name:  Screen Shot 2016-06-04 at 1.12.15 PM.jpg
Views: 569
Size:  21.3 KB

Name:  Screen Shot 2016-06-04 at 1.12.38 PM.jpg
Views: 577
Size:  23.3 KB

Isn't there a way to do this problem with a gamma(exponential)-poisson conjugate prior? I got 9.96 using the conjugate prior, which resulted in a different letter answer
__________________
FM P MFE C MLC
VEE
Mods
Reply With Quote
  #553  
Old 06-04-2016, 09:02 PM
Doctuary Doctuary is offline
Member
CAS
 
Join Date: Sep 2014
Studying for C/4
Favorite beer: Holy Water
Posts: 259
Default

how important is Bayesian estimation and credibility? I have not touch that section yet...
__________________
Exams: P FM MFE C S
Online Courses: 1 2

Work hard, Study harder, Play the hardest
Reply With Quote
  #554  
Old 06-04-2016, 11:05 PM
el jefe el jefe is offline
Member
SOA
 
Join Date: Aug 2014
Studying for C
Posts: 78
Default

Quote:
Originally Posted by Doctuary View Post
how important is Bayesian estimation and credibility? I have not touch that section yet...
very. according to syllabus it is the heaviest tested topic
__________________
FM P MFE C MLC
VEE
Mods
Reply With Quote
  #555  
Old 06-05-2016, 10:37 AM
abeaupre's Avatar
abeaupre abeaupre is offline
Member
SOA
 
Join Date: Mar 2015
College: Université Laval
Posts: 312
Default

I still need to learn semi-parametric Bayesian credibility, conjugate priors and do as many practice exams as possible. Next couple of weeks are going to be pretty intense.

Good luck all!
Reply With Quote
  #556  
Old 06-05-2016, 01:12 PM
Doctuary Doctuary is offline
Member
CAS
 
Join Date: Sep 2014
Studying for C/4
Favorite beer: Holy Water
Posts: 259
Default

Quote:
Originally Posted by abeaupre View Post
I still need to learn semi-parametric Bayesian credibility, conjugate priors and do as many practice exams as possible. Next couple of weeks are going to be pretty intense.

Good luck all!
I'm in the same boat!
__________________
Exams: P FM MFE C S
Online Courses: 1 2

Work hard, Study harder, Play the hardest
Reply With Quote
  #557  
Old 06-05-2016, 02:30 PM
Completely Absorbed Completely Absorbed is offline
Member
CAS
 
Join Date: Apr 2015
Location: Nibbana
Studying for ever and ever, Amen.
College: Rutgers University
Posts: 544
Default

lol just watched TIA's 'before you do the sample exams' strategy guide, and Dave said something like "...you don't go out drinking the night before the exam, that's something you do after the exam"
__________________
Quote:
Originally Posted by Abelian Grape View Post
*fist pumping intensifies*
Reply With Quote
  #558  
Old 06-05-2016, 03:24 PM
Jim Daniel's Avatar
Jim Daniel Jim Daniel is offline
Member
SOA
 
Join Date: Jan 2002
Location: Davis, CA
College: Wabash College B.A. 1962, Stanford Ph.D. 1965
Posts: 2,688
Default

Quote:
Originally Posted by el jefe View Post
Attachment 35833

Attachment 35834

Isn't there a way to do this problem with a gamma(exponential)-poisson conjugate prior? I got 9.96 using the conjugate prior, which resulted in a different letter answer
Not really.

I suspect what you mean is that you noticed that the prior distribution is a 40/60 mixture of two Gamma random variables. It does indeed turn out that the posterior distribution will be SOME mixture of Gamma random variables, namely of the two Gamma distributions that would be the posterior distributions that would result solely from each of the Gamma distributions in the mixed prior. But this final mixture isn't the same as the original 40/60---in order for it to be so, the posterior distribution would have to result from a linear computation in the density function, and that fails to be true because of the division in the computation.
__________________
Jim Daniel
Jim Daniel's Actuarial Seminars
www.actuarialseminars.com
jimdaniel@actuarialseminars.com
Reply With Quote
  #559  
Old 06-06-2016, 02:11 PM
zenkei18 zenkei18 is offline
Member
Non-Actuary
 
Join Date: Jan 2014
College: Angelo State University
Posts: 698
Default

Holy crudsticks am I getting destroyed by practice exams, lol.

EDIT: This test is going to own my soul so hard.
__________________
P FM MFE C MLC

Last edited by zenkei18; 06-06-2016 at 04:22 PM..
Reply With Quote
  #560  
Old 06-06-2016, 04:28 PM
hjacjswo hjacjswo is offline
Member
 
Join Date: Dec 2009
College: About to be a super senior
Posts: 1,430
Default

So, when we are dealing with bayesian credibility with normal/normal prior conjugate, and we have lognormal as the model distribution, we keep the model variance the same and just LN the sample losses, correct? So basically, when we have a lognormal distribution instead of normal in this type of problems, only portion that i have to change is the sample mean.
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 02:10 PM.


Powered by vBulletin®
Copyright ©2000 - 2018, 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 0.44725 seconds with 10 queries