Two questions about Stuart Klugman's loss distribution review

Stuart Klugman ( stuart.klugman@drake.edu )
Mon, 17 Aug 1998 12:24:15 -0400

Question 1 asked about Example 26 on pages 15-16. The question should =
have more clearly stated that minimum *modified* chi-square estimation was =
to be used. Then replacing the expected count with the observed count is =
acceptable.

Question 2 asked about the solution to Exercise 28. There is an error in =
the solution. The final term in the likelihood, exp(-15625c), appears 7 =
times and so the log-likelihood should have as its final term +7(15625)c =
=3D -109375c. Also note that the final term should have a plus sign. The =
mle is c-hat =3D .00002817.

The solution also includes the estimate for the distribution of W, the =
actual payments.

---------------------------------------------------------------------------=
---------------------
Stuart Klugman, FSA
Principal Financial Group Professor of Actuarial Science
Drake University
2507 University Avenue
Des Moines, IA 50311 USA
ph: 515-271-4097
e-mail: Stuart.Klugman@drake.edu