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

Salary Surveys
Property & Casualty, Life, Health & Pension

Health Actuary Jobs
Insurance & Consulting jobs for Students, Associates & Fellows

Actuarial Recruitment
Visit DW Simpson's website for more info.
www.dwsimpson.com/about

Casualty Jobs
Property & Casualty jobs for Students, Associates & Fellows


Reply
 
Thread Tools Search this Thread Display Modes
  #1  
Old 02-01-2020, 02:11 PM
CaffeineJunky's Avatar
CaffeineJunky CaffeineJunky is offline
Member
CAS AAA
 
Join Date: Jun 2006
Location: Chicago Area
Studying for absolutely nothing!! :-)
College: Roosevelt University Alum
Favorite beer: Goose Island - Bourbon County Stout
Posts: 1,189
Default Literature of Optimal Severity Distributions by LOB

Is anyone aware of any papers or studies out there on optimal distributions to use for claim severity modeling? I am working at a small insurer with limited historical data, so Ideally I don't want to fit only to our data. In my limited research, I've seen the lognormal used quite a bit for WC, but what about the various liability lines? Any ideas or suggestions are much appreciated.
__________________
"A friend of mine has a trophy wife, but apparently it wasn't first place." - Steven Wright
Reply With Quote
  #2  
Old 02-01-2020, 07:29 PM
Colymbosathon ecplecticos's Avatar
Colymbosathon ecplecticos Colymbosathon ecplecticos is offline
Member
 
Join Date: Dec 2003
Posts: 6,225
Default

You used the word "optimal" in your question.

What are you trying to "optimize"?
__________________
"What do you mean I don't have the prerequisites for this class? I've failed it twice before!"


"I think that probably clarifies things pretty good by itself."

"I understand health care now especially very well."
Reply With Quote
  #3  
Old 02-02-2020, 05:11 PM
CaffeineJunky's Avatar
CaffeineJunky CaffeineJunky is offline
Member
CAS AAA
 
Join Date: Jun 2006
Location: Chicago Area
Studying for absolutely nothing!! :-)
College: Roosevelt University Alum
Favorite beer: Goose Island - Bourbon County Stout
Posts: 1,189
Default

Optimal is not the right word. Just looking for distributions that others have used that fit well to certain lines of business. Or any papers that have been written on this topic. Thanks.
__________________
"A friend of mine has a trophy wife, but apparently it wasn't first place." - Steven Wright
Reply With Quote
  #4  
Old 02-02-2020, 06:01 PM
Marcie's Avatar
Marcie Marcie is offline
Member
CAS
 
Join Date: Feb 2015
Posts: 10,598
Default

Have you tried the papers/texts on fitting loss distributions on the exam syllabus?
Reply With Quote
  #5  
Old 02-04-2020, 11:03 AM
v10 v10 is offline
Member
CAS
 
Join Date: Aug 2012
Posts: 61
Default

WC is an interesting case because in many cases the largest portion of the claim is the indemnity income which is formula driven and not stochastic. So while you could use a distribution to fit the aggregate losses for a given claim it may make sense to have a distribution modeling the expected length of the claim and use the known indemnity amount based on the claimant wages.

But in general the most common distributions we'll see underlying ILFs are:
Gamma
Lognormal
Pareto
mixtures of any of the above
Mixed exponential (ISO GL)

Slightly less common would be:
5 parameter truncated pareto
Weibull
Reply With Quote
  #6  
Old 02-07-2020, 09:54 AM
CaffeineJunky's Avatar
CaffeineJunky CaffeineJunky is offline
Member
CAS AAA
 
Join Date: Jun 2006
Location: Chicago Area
Studying for absolutely nothing!! :-)
College: Roosevelt University Alum
Favorite beer: Goose Island - Bourbon County Stout
Posts: 1,189
Default

Quote:
Originally Posted by v10 View Post
WC is an interesting case because in many cases the largest portion of the claim is the indemnity income which is formula driven and not stochastic. So while you could use a distribution to fit the aggregate losses for a given claim it may make sense to have a distribution modeling the expected length of the claim and use the known indemnity amount based on the claimant wages.

But in general the most common distributions we'll see underlying ILFs are:
Gamma
Lognormal
Pareto
mixtures of any of the above
Mixed exponential (ISO GL)

Slightly less common would be:
5 parameter truncated pareto
Weibull
Very helpful, thanks!
__________________
"A friend of mine has a trophy wife, but apparently it wasn't first place." - Steven Wright
Reply With Quote
Reply

Tags
distributions, liability, modeling, severity

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 03:58 PM.


Powered by vBulletin®
Copyright ©2000 - 2020, 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 0.18738 seconds with 9 queries