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


Reply
 
Thread Tools Search this Thread Display Modes
  #11  
Old 04-25-2018, 03:13 PM
behindthebag behindthebag is offline
Member
CAS
 
Join Date: Jul 2016
Favorite beer: Blue Moon (prefer single malt)
Posts: 40
Default

Quote:
Originally Posted by tometom View Post
I believe he's just saying you aggregate the tail factor over multiple years. so for example if your paid/incurred ultimates are like this:
1999: 10,000/11,000
2000: 10,000/12,000
2001: 10,000/10,000
you don't apply an adjustment of 1.1 to 1999, 1.2 to 2000 and 1.0 to 2001, you combine them together and adjust all years by 1.1.
Thought he meant that. We do that where I am. Wasn't sure though that it addressed the OP's original concern. True, it won't result in an exact match for the ultimates but overall you are definitely using the incurred to get the paid. (Not that that's so bad but seems redundant.)
Reply With Quote
  #12  
Old 04-25-2018, 03:38 PM
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: 62,738
Default

Quote:
Originally Posted by behindthebag View Post
Thought he meant that. We do that where I am. Wasn't sure though that it addressed the OP's original concern. True, it won't result in an exact match for the ultimates but overall you are definitely using the incurred to get the paid. (Not that that's so bad but seems redundant.)
The bolded has me confused . . .

Granted that using paid data to estimate ultimates might give you a different answer than using incurred data . . . but unless you're doing some sort of reserve adequacy analysis, I'm not sure what the bolded statement means.

Once an AY is fully mature, incurred = paid.
__________________
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
  #13  
Old 04-25-2018, 06:17 PM
Cloister Cloister is offline
Member
 
Join Date: Oct 2001
Posts: 2,499
Default

Quote:
Originally Posted by behindthebag View Post
Thought he meant that. We do that where I am. Wasn't sure though that it addressed the OP's original concern. True, it won't result in an exact match for the ultimates but overall you are definitely using the incurred to get the paid. (Not that that's so bad but seems redundant.)
Keep in mind the tail matching is being done on a set of older years. You're using the incurred to get the paid beyond a certain point -in my experience it's at least 10 years out, and often 15, 20 or more. It's saying that the incurred losses on old years tell us a lot about what we can expect overall paid losses to be beyond a certain point. But you're then using the actual paid development up to that point.

If you like, you can think of it as using paid development to estimate paid losses up to say 15 or 20 years out, and the incurred development and incurred/paid ratios to estimate paid development beyond that point. What often happens in my work is what I call the big/small problem for paid development. For old years, either you have some big claims still open with large case reserves (in which case late paid development will be large) or only small claims with little in case reserve (in which case late paid development will be small). The paid development method then ends up being terrible for projecting any individual old year (it's either way too high or way too low, unless you allow yourself to use different tails for different years which I can't say I've ever seen anyone do). But you can use that info to get a reasonable average tail factor, which is useful for projecting ultimate losses for more recent years (since for those, you have no way of knowing which will end up having late large open claims or now).
Reply With Quote
  #14  
Old 04-30-2018, 12:29 PM
PeppermintPatty's Avatar
PeppermintPatty PeppermintPatty is offline
Member
CAS
 
Join Date: Sep 2001
Posts: 38,496
Default

Quote:
Originally Posted by Vorian Atreides View Post
The bolded has me confused . . .

Granted that using paid data to estimate ultimates might give you a different answer than using incurred data . . . but unless you're doing some sort of reserve adequacy analysis, I'm not sure what the bolded statement means.

Once an AY is fully mature, incurred = paid.
I assume the AY isn't fully mature, or why do anything?
Reply With Quote
  #15  
Old 04-30-2018, 12:32 PM
PeppermintPatty's Avatar
PeppermintPatty PeppermintPatty is offline
Member
CAS
 
Join Date: Sep 2001
Posts: 38,496
Default

If I am working with data where I am confident the incurred at the end of my triangle is very close to "true ultimate", for example, if I'm looking at claim counts for personal auto, then I generally will match the paid to the incurred. If I'm looking at data where that's not the case, say, $loss for products liability, I generally like to pick each tail independently and see if the data tells me anything.
Reply With Quote
  #16  
Old 04-30-2018, 04:25 PM
yoyo's Avatar
yoyo yoyo is offline
Member
CAS
 
Join Date: Dec 2001
Posts: 22,217
Default

goal seek?

jk
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 02:50 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 0.36553 seconds with 11 queries