Mack and Bootstrap Reserve Risk Calculations

[LostTriangles]

I'm quite new to R and have had some trouble pulling Mack and Bootstrap reserve risk information from R.

1. Using the pre-defined RAA incurred triangle, how do I get the "Total.Process Risk" and "Total.ParameterRisk" shown on page 35 of the package pdf https://cran.r-project.org/web/packages/ChainLadder/ChainLadder.pdf? I must be missing simple command somewhere but I'm only able to see total Mack S.E by year upon calling "MackChainLadder(RAA)".

I understand Total Mack S.E ^2 = (Process Risk^2) + (Paramater Risk^2) but I'd like to see the individual breakout.

Additionally, the Mack S.E's and Ultimates sometimes show up in abbreviated format (2.03e+06) rather than something like 2028950. Is there any way to re-format the Mack summary?

1. Similar question, but for the Bootstrap method included in the package. Rather than producing a mean simulated IBNR by accident year, is it possible to input reserves by AY and show Mean Reserve / Mean Std Dev on the summary screen?

Thanks in advance.

[fabioconcina]

Hi, I'll answer to the first question. What you are seeing calling MackChainLadder(RAA) is only a summary of the results of the model. You can use

attributes(MackChainLadder(RAA)) to display all the attributes of the MackChainLadder object:

$names [1] "call" "Triangle" [3] "FullTriangle" "Models" [5] "f" "f.se" [7] "F.se" "sigma" [9] "Mack.ProcessRisk" "Mack.ParameterRisk" [11] "Mack.S.E" "weights" [13] "alpha" "Total.Mack.S.E" [15] "Total.ProcessRisk" "Total.ParameterRisk" [17] "tail"

$class [1] "MackChainLadder" "TriangleModel" [3] "list"

To access the single elements you can use MackChainLadder(RAA)$Total.ProcessRisk and MackChainLadder(RAA)$Total.ParameterRisk.

For the exponential notation issue I would call options(scipen = 999) to disable scientific notation.

2016-07-03 21:49 GMT+02:00 LostTriangles notifications@github.com:

I'm quite new to R and have had some trouble pulling Mack and Bootstrap reserve risk information from R.

1. Using the pre-defined RAA incurred triangle, how do I get the "Total.Process Risk" and "Total.ParameterRisk" shown on page 35 of the package pdf https://cran.r-project.org/web/packages/ChainLadder/ChainLadder.pdf? I must be missing simple command somewhere but I'm only able to see total Mack S.E by year upon calling "MackChainLadder(RAA)".

I understand Total Mack S.E ^2 = (Process Risk^2) + (Paramater Risk^2) but I'd like to see the individual breakout.

Additionally, the Mack S.E's and Ultimates sometimes show up in abbreviated format (2.03e+06) rather than something like 2028950. Is there any way to re-format the Mack summary?

1. Similar question, but for the Bootstrap method included in the package. Rather than producing a mean simulated IBNR by accident year, is it possible to input reserves by AY and show Mean Reserve / Mean Std Dev on the summary screen?

Thanks in advance.

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/mages/ChainLadder/issues/9, or mute the thread https://github.com/notifications/unsubscribe/AML4BijCdtBK8xNexz_kMmhFOwm33VMjks5qSBJQgaJpZM4JD7z7 .

[LostTriangles]

Thank you Fabio, your advice worked! Unfortunately I'm still a bit stuck on the bootstrap portion.

BootChainLadder(RAA) Gives a Mean Ultimate, Mean IBNR, and IBNR SE, but no Ultimate SE.

Even without inputting Paid Information into R, if I could somehow retrieve Ultimate S.E from the BootChainLadder function by AY, I could simply do the rest of the calculations in excel. Unfortunately, I don't see one of the BootChainLadder attributes which call upon the value of Ultimate S.E.

[mages]

The ultimate SE is the same as the IBNR SE, if I am not mistaken.

The difference between the ultimate and IBNR (or better reserve in this context) is a known quantity with no variance.

On 4 Jul 2016, at 14:00, LostTriangles notifications@github.com wrote:

Thank you Fabio, your advice worked! Unfortunately I'm still a bit stuck on the bootstrap portion.

BootChainLadder(RAA) Gives a Mean Ultimate, Mean IBNR, and IBNR SE, but no Ultimate SE.

Even without inputting Paid Information into R, if I could somehow retrieve Ultimate S.E from the BootChainLadder function by AY, I could simply do the rest of the calculations in excel. Unfortunately, I don't see one of the BootChainLadder attributes which call upon the value of Ultimate S.E.

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or mute the thread.

[LostTriangles]

mages, you're absolutely right. I feel quite silly given that I was going to use Ultimate SE as my Reserve SE, which again is only different by a fixed amount but didn't see the same in the incurred case.