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
  #1  
Old 03-20-2019, 10:40 AM
TryingToFigure TryingToFigure is offline
CAS
 
Join Date: Aug 2018
College: CSU Grad
Posts: 6
Default Credibility Standard for Premium Trend

Hello Everyone

I've been trying to research a credibility standard for premium trend weighting between a state's experience and a proper compliment.

My goal is to do it by an exposure standard.

Mahler mentions an exposure credibility standard but it seems more of a pure premium trend calculation since you divide by frequency.

Jones mentions there is a possible standard but focuses more on the choice of compliment of credibility.

Has anyone run across any publications that talk about an exposure credibility standard for credibility weighting premium trend?

Could I just take 1082 and divide by freq of the state? But that's loss frequency standard.

Thanks for your time! Any helpful pointers would be appreciated.
Reply With Quote
  #2  
Old 03-20-2019, 10:46 AM
NormalDan's Avatar
NormalDan NormalDan is offline
Member
CAS
 
Join Date: Dec 2016
Location: NJ
Posts: 7,880
Default

Quote:
Originally Posted by TryingToFigure View Post
Hello Everyone

I've been trying to research a credibility standard for premium trend weighting between a state's experience and a proper compliment.

My goal is to do it by an exposure standard.

Mahler mentions an exposure credibility standard but it seems more of a pure premium trend calculation since you divide by frequency.

Jones mentions there is a possible standard but focuses more on the choice of compliment of credibility.

Has anyone run across any publications that talk about an exposure credibility standard for credibility weighting premium trend?

Could I just take 1082 and divide by freq of the state? But that's loss frequency standard.

Thanks for your time! Any helpful pointers would be appreciated.
What credibility standard do you use for the indication your premium trend is feeding into? Would be tempting to simply use that potentially exposure based method. Or as you suggest you can convert based on frequency assumptions.

Also, it's complement, in this context
Reply With Quote
  #3  
Old 03-20-2019, 10:54 AM
TryingToFigure TryingToFigure is offline
CAS
 
Join Date: Aug 2018
College: CSU Grad
Posts: 6
Default

Thanks!

If I can't find anything to counter I'll likely do that. Take the full credibility standard by counts and divide by frequency.

Also I'll likely match compliments. Example if pure premium compliment is CW then premium trend compliment will be CW.

There's surprisingly little literature on credibility for premium trend. All on loss trend.

Though the debate appears to rage harder for compliment for premium.
Reply With Quote
  #4  
Old 03-21-2019, 10:32 AM
Heywood J Heywood J is offline
Member
CAS
 
Join Date: Jun 2006
Posts: 4,093
Default

It seems to me that there isn't much need for a credibility procedure for premium trend. You need a credibility procedure for pure premium, since few policies have losses, and when they do happen, these losses are highly variable. On the other hand, every policy has premium, and the way it trends is going to be fairly predictable.
Reply With Quote
  #5  
Old 03-21-2019, 11:06 AM
MightySchoop's Avatar
MightySchoop MightySchoop is offline
Member
CAS AAA
 
Join Date: Aug 2009
Location: Insula Primalis
Posts: 7,134
Default

Quote:
Originally Posted by Heywood J View Post
It seems to me that there isn't much need for a credibility procedure for premium trend. You need a credibility procedure for pure premium, since few policies have losses, and when they do happen, these losses are highly variable. On the other hand, every policy has premium, and the way it trends is going to be fairly predictable.
This. Premium is not determined by a stochastic process, so you should not need a credibility procedure for it.

ETA: okay, premium can be determined by a stochastic process for retro-rated and other loss-sensitive policies.
__________________
Dare to believe you can survive
Reply With Quote
  #6  
Old 03-21-2019, 11:10 AM
Vorian Atreides's Avatar
Vorian Atreides Vorian Atreides is offline
Wiki/Note Contributor
CAS
 
Join Date: Apr 2005
Location: As far as 3 cups of sugar will take you
Studying for ACAS
College: Hard Knocks
Favorite beer: Most German dark lagers
Posts: 64,745
Default

One other thing about premium vs. pure premium: Once you write the policy, you know exactly how much premium you have (for nearly all lines of business), but the loss cost is still uncertain for quite some time.
__________________
I find your lack of faith disturbing

Why should I worry about dying? Itís not going to happen in my lifetime!


Freedom of speech is not a license to discourtesy

#BLACKMATTERLIVES
Reply With Quote
  #7  
Old 03-21-2019, 12:18 PM
TryingToFigure TryingToFigure is offline
CAS
 
Join Date: Aug 2018
College: CSU Grad
Posts: 6
Default

Thanks everyone for your replies.

To clarify the crediblity would be for the future component of the premium trend. For my line for historical just pick the 36 month smoothed and be done but there's some desire to see if we can't better represent the future.

Thanks again.
Reply With Quote
  #8  
Old 03-25-2019, 04:54 PM
tometom's Avatar
tometom tometom is offline
Member
CAS AAA
 
Join Date: May 2004
Favorite beer: Homebrew
Posts: 13,238
Default

I've done the divide by frequency assumption to get to an exposure basis. I've also converted to a premium value by taking an expected average severity per claim times claims for full credibility divided by PLR. This is more useful for lines where the exposure is harder to measure.
__________________
If I had some duct tape, I could fix that.
Reply With Quote
  #9  
Old 04-05-2019, 12:18 PM
DeepPurple's Avatar
DeepPurple DeepPurple is offline
Member
 
Join Date: Jun 2004
Posts: 4,294
Default

I don't immediately understand the need to do this at all. Your goal is to figure the loss ratio of experience periods at current rate level. Why would you weight the on-level factors with a complement? What difference is the RLAF for West Virginia when you are on-leveling Nevada loss ratios? No complement needed. You want to calculate what the trended developed historical loss ratios will give when compared to current rate levels IN NEVADA.
__________________
Come on. Let's go space truckin'. Come on!
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 11:24 AM.


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 0.41449 seconds with 11 queries