Credibility Analysis for Automobile Cession Strategies
Sponsor: Premier Insurance
Advisor: Prof. Art. Heinricher
Student: Elizabeth Anne Hogan
In Massachusetts, every person is guaranteed automobile insurance at state-determined rates. Insurance companies cannot deny coverage, but can cede the policy to an agency called CAR. Insurance companies need good estimates for expected loss on a policy in order to make the best cession decision. The cession decision is difficult to make where data is sparse. This project describes two ways that a company can use loss data to obtain better predictions for in groups with sparse data.
Pricing a Waiver of Premium Upon Disability
Sponsor: John Hancock Mutual Life Insurance Co.
Advisor: Prof. Ann Wiedie
Students: Jovanna Rose Baptista, Larissa L. Gilbreath, Robert A. Jaeger
Development of approaches to price a waiver of premium upon disability rider based on provision terms set forth by John Hancock Insurance and available data. Approaches involved random variables; age at disablement, duration of disability, and age at death. A rider premium was calculated such that the random loss (a function of those random variables) had an expected value of zero. Through data collection and SAS programming, an expense-loaded rider premium was calculated as a percentage of base premium.
Statistical Consulting at BOSE
Sponsor: BOSE Corporation
Advisor: Prof. J. D. Petruccelli
Student: Jin (Justin) Tao Lin
This project was conducted in conjunction with a leading audio speaker manufacturer. During a three-month period, the author consulted on-site with the company, providing assistance on different projects relating to statistics and quality control. The author gained experience in data collection and analysis, designing experiments, and the application of statistical software.Maintained by email@example.com
Last modified: Jun 20, 2010, 09:03 EDT