
177Frequency Modelling: Adjusting for Claim Count IBNR
years. Note that Method 1 (ignore last diagonal) and Method 4 (shift policy years) give the
closest results for all years.
13.3 Triangle-Free Method for IBNR Estimation
The main issue of the approach outlined in Section 13.2 is that aggregating claim counts
in a triangle throws away most of the information we have: by way of illustration, if we
have 1000 losses over 10 years, we will compress the information on the reporting delay
(which is made of 1000 different numbers) into a small triangle (which is made up of 55
different numbers). Bizarrely, increasing the number of losses (e.g. from ...