A.4. Mahler Flashcards
1
Q
Simplifications in baseball data compared to insurance data
A
- A constant set of risks (teams)
- The baseball loss data is readily available, accurate, and not subject to development
- Each risk (team) is of equal size; they each play roughly the same # of games each year
2
Q
Tests to determine if risk parameters are shifting over time
A
3
Q
6 methods to estimate X
A
4
Q
3 criteria to evaluate possible estimates
A
- Least squared error: Calculate the MSE of the prediction compared with the actual observed result. The Bühlmann/Bayesian credibility methods attempt to minize this criteria.
- Limited fluctuation: Also known as “Small chance of large errors”. Measure the probability that the observed result differs by more than a certain percent from the predicted result. The classical credibility method targets this criteria.
- Meyers/Dorweiler: Calculate the correlation between the ratio of actual to expected losses and the ratio of predicted losses to overall losses. This criteria confirms that there is no evidence that large predictions lead to large errors and small predictions lead to small errors.
