Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Appearance settings
Discussion options

I'm working on a project involving both premium and loss triangles. For the premium triangles, I'm using the TrendConstant method. In that case, the development field represents the trending date - but it's a bit imprecise because I can have a case where I develop premium to a different date than I trend/onlevel it to. I don't know if there's been any thought on providing options to split those? I am also new to chainladder so may not know if that distinction is already available, or if this really isn't the intended use of the package.

Thanks!

You must be logged in to vote

Replies: 2 comments

Comment options

Hi @slisajacobson welcome!

Do you already have a sample code snippet that you can share? Or give an example using the sample data?

You must be logged in to vote
0 replies
Comment options

I don't have a particular snippet - apologies. And was not describing it very accurately.

I should be more specific that I'm looking at premium on-level and development. If I use the ParallelogramOLF method to on-level premium it will do so to the development I specify when I construct the triangle.

There is a case where I want to develop the premium to a different date (using DevelopmentConstant, which also uses the development specified in the triangle). I think of the on-level and development dates as being on two different axes for the triangle. This may be outside the intended scope, but was curious if anyone has looked at best ways to handle that? Right now I'm just overwriting the development date and then storing the on-level date when I write the triangle back to a table.

There could be an analogous question on loss trend vs development, where TrendConstant will use the development date as the valuation date, and one might want to have a different development date for loss development (i.e., on development age and not valuation date?)

This is not a problem at all with chainladder because it is doing what it says it is doing, but I was curious if/how others have handled?

Thanks! It's a great package.

You must be logged in to vote
0 replies
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
2 participants
Morty Proxy This is a proxified and sanitized view of the page, visit original site.