Hello, I have a few questions on April 2019's paper: Q6(ii): The distribution of the number of claims for an individual is given, and the second table gives the aggregate claim amount for a risk class. - In this case, using the Buhlmann-Straub model, we obtain the credibility estimator by weighting Beta (found using the given number of claims distribution) and the historical average claim amount per individual (from the tables given). - Wouldn't this make the estimator inconsistent somehow? Since Beta is based on the number of claims but the other part of the credibility weight is applied on the average claim amount. Q8(i): Liability claims development to ultimate a. Why do we need to use BF instead for 2017, when the ultimate loss ratio under chain ladder is 26%; comparable to 2016's ratio? b. It is mentioned in the solutions that there is an increasing trend for liability claims. However, aren't we essentially 'removing' that trend by imposing the 19% IELR on 2017 and 2018 claims using BF?
Hi JL24, For question 6 part ii, this has been covered in a few other posts on this forum (you can find other posts using the search function). In any case, you may find the following useful: https://www.acted.co.uk/forums/index.php?threads/april-2019-q6.18491/ I hope that helps. Aman ActEd Tutor
Hi, In response to your questions about question 8, the examiners stated that: Part (i) was generally well answered. The above solution is only one proposed solution, and the examiners recognised that many different solutions were possible depending on the assumptions/choices made by the candidates. Credit was given where candidates explained what they were doing and their explanations were reasonable. There was an expectation however that the uncertain development in the most recent year(s) and examining the trends should not be ignored. In response to your comment b), given there are only 3 data points, it has been deemed reasonable to use 19% as there are only 3 data points, which is too few points to justify to apply a trend. You may disagree, and as long as you do something that is reasonable, marks ought to be awarded. I hope that helps. Aman ActEd Tutor
You'll see in the Examiners' Report that many different solutions were possible for each of the years, depending on the assumptions you make. If you can explain your own method, assumptions and calculations here, then perhaps somebody can indicate whether you've taken a reasonable approach.
Hi, Regarding Q8, could someone please help me with the following: 1. why is chain ladder method inappropriate for most recent year? 2. in the solution, how has the ultimate claim-BF been calculated? 3. the examiner's report states other methods were acceptable, what alternatives could have been used? 4. Have the average loss ratios in the solution been determined by dividing by 4 as opposed to 5 years? if so, why? Thanks in advance
1. Most recent years are very undeveloped, and so little weight should be put on them as the experience to date is uncertain. 2. You may need to revisit Subject CM2 to see how BF methods work. Alternatively, have a go and post your calcs here and we can see what you might be doing differently to the examiners. 3. All sorts! There are probably as many reasonable approaches as there were candidates for the exam! As long as you reasonably justify the method you use, you would hopefully have scored. I think an understanding of SP7 material helps here too, because BF considerations are explored there in more detail.
