Dissertation > Excellent graduate degree dissertation topics show

Non-life actuarial study based on extreme value theory

Author: ZhaoZhiHong
Tutor: LiXingXu
School: Yunnan University of Finance
Course: Statistics
Keywords: Extreme Value Theory Generalized Pareto distribution Domain of attraction Inspection Value at Risk Expected loss pure premium
CLC: F840
Type: Master's thesis
Year: 2009
Downloads: 177
Quote: 1
Read: Download Dissertation

Abstract


In this paper, a detailed study of the traditional non-life actuarial method based on the main use of the good properties of the extreme value theory , that the the POT model in the extreme value theory only consider the distribution tail , instead of modeling the entire distribution , which avoid the distribution of the hypothetical problems , loss distribution modeling is very favorable . And extreme value theory can accurately describe the distribution tail quantiles , which helps the non- life insurance companies risk management . In addition, on this basis , the compound Poisson process and extreme value theory generalized Pareto model to study the problem of the non-life reinsurance . In general , the main purpose of this paper is to establish the entire non- life insurance actuarial framework based on extreme value theory , enabling the accurate portrayal of the loss distribution of the right tail of the distribution of the huge losses , and a non- life insurance actuarial basis . Extreme Value Theory strict generalized Pareto distribution in the modeling process , discusses the modeling process , including the thick tail diagnosis , extreme value distribution maximum domain of attraction of inspection, the optimal choice of the threshold , generalized Pa the rectories distribution parameter estimation and model fitting effect inspection , and discuss different threshold selection method and parameter estimation methods , including maximum likelihood estimation Hill semiparametric estimates , the moment estimation method and the use of non- parametric test methods to test the model . After completing the modeling , the problem of non - life insurance actuarial build generalized Pareto distribution basis , and take advantage of short-term the aggregation risk models and compound Poisson distribution to calculate risk -bit pure excess of loss reinsurance premiums .

Related Dissertations

  1. A Smoothing Method for Solving Model under WCVarR,O224
  2. Copula-EGARCH-Kernel Density Estimation Model and Its Application,O211.3
  3. Ecological Risk Assessment of Marine Gastropod Mollusks Population,X174
  4. Annual Contract Energy Decomposition for Hydropower Plants and Risk Control Study,F224;F426.91
  5. Our open-end fund market risk measurement,F224
  6. Transmission system cascading failure risk assessment,TM711
  7. Bank Operational Risk Measurement Approach System Realization,TP311.52
  8. Stock market risk measurement and correction,F832.51
  9. China Mortgage Pricing,F293.3;F224
  10. Global value chain governance strategy to upgrade the Chinese OEM manufacturers of,F279.2
  11. Based on GARCH Model Method of VAR in securities investment funds in the application and analysis,F830.91
  12. Heavy-tailed extreme value index estimation,O211.4
  13. Connection function (Copula) theory and its applications in financial risk,F224
  14. Copula function and high-end ES liquidity of commercial banks risk measure,F224
  15. Operational risk measure based on the the Bayes - copula method of commercial banks,F224
  16. A Study on Risk Spillover Effect of Copper Futures Between LME and SHFE,F713.35;F724.5
  17. Construction of Risk-oriented Internal Auditing Procedures,F239.45
  18. Extreme value statistics in the value-at-risk calculations,F830.9
  19. Financial Leasing Enterprise Risk Control and Analysis,F224
  20. The Measure of RMB Exchange Rate Risk Based on Extreme Value Theory and Dynamic Extreme Value Theory,F832.6
  21. The Application Research of CVaR on Commercial Bank’s Exchange Rate Risk Evaluation,F830.7

CLC: > Economic > Fiscal, monetary > Insurance > Insurance Theory
© 2012 www.DissertationTopic.Net  Mobile