A typical problem that insurance and financial companies face is obtaining an appropriate probability distribution to model the magnitude (severity) of losses when they deal with forecasting future losses using past or current insurance claims data. Modeling the probability distribution of the magnitude of losses is often beneficial not only because it provides quantitative estimation of the expected loss, but also because it illustrates the risk associated with it, and can be used in making future inferences regarding premium rates, reserves, and expected profits. In the application section of this thesis, previous hurricane loss data set for the years 1900-2005 is used to find the best fitting probability distribution for the magnitude of the losses. The objective of this thesis is to find an appropriate probability distribution for the hurricane damages in the United States between 1900 and 2005, and to examine how well the selected probability distribution fits the hurricane loss data, applying the technique of Monte Carlo simulation. In addition, a non-parametric kernel estimation approach is performed to provide a smoothed fit of the empirical distribution for the hurricane loss data, and then the confidence intervals for the estimated characteristics are constructed, using bootstrap resampling method. To end with, the bootstrap confidence intervals for both the parametric and nonparametric cases are compared to the true values of the main statistical characteristics to access which model approach performs better in terms of the evaluation of the main statistics.
|Commitee:||Kim, Sung Eun, Kim-Park, Yong Hee|
|School:||California State University, Long Beach|
|Department:||Mathematics and Statistics|
|School Location:||United States -- California|
|Source:||MAI 55/03M(E), Masters Abstracts International|
|Subjects:||American history, Statistics|
|Keywords:||Hurricane losses, Loss distribution, United States|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be