PROBLEM 1: Parameter estimation of Generalized Pareto Distribution
• Maximum Likelihood estimate
• Harmonic method
——————————————————————–
Data and solution in MATLAB Environment
• Maximum Likelihood estimate
• Harmonic method
——————————————————————–
Data and solution in MATLAB Environment
Problem Datasets | # of Samples | |||
---|---|---|---|---|
Dataset1 | Matlab Code | Library | Solution | 1250 |
Dataset2 | Matlab Code | Library | Solution | 12500 |
PROBLEM 2: Estimation of Generalized Pareto Distribution for residuals of quantile regression
Minimize kb_err
——————————————————————–
kb_err = Koenker and Basset error function
Parameter estimation for residuals:
• Maximum Likelihood estimate
• Harmonic method
——————————————————————–
Data and solution in MATLAB Environment
Minimize kb_err
——————————————————————–
kb_err = Koenker and Basset error function
Parameter estimation for residuals:
• Maximum Likelihood estimate
• Harmonic method
——————————————————————–
Data and solution in MATLAB Environment
Problem Datasets | # of Variables | # of Samples | |||
---|---|---|---|---|---|
Dataset1 | Matlab Code | Library | Solution | 5 | 1264 |
Dataset2 | Matlab Code | Library | Solution | 1 | 5000 |
Dataset3 | Matlab Code | Library | Solution | 1 | 50000 |
PROBLEM 3: Estimation of Generalized Pareto Distribution for residuals of CVaR regression
Minimize cvar2_err (Minimizing CVaR (Superquantile) error)
——————————————————————–
cvar2_err = CVaR (Superquantile) error
Parameter estimation for residuals:
• Maximum Likelihood estimate
• Harmonic method
——————————————————————–
Data and solution in MATLAB Environment
Minimize cvar2_err (Minimizing CVaR (Superquantile) error)
——————————————————————–
cvar2_err = CVaR (Superquantile) error
Parameter estimation for residuals:
• Maximum Likelihood estimate
• Harmonic method
——————————————————————–
Data and solution in MATLAB Environment
Problem Datasets | # of Variables | # of Samples | |||
---|---|---|---|---|---|
Dataset1 | Matlab Code | Library | Solution | 5 | 1264 |
CASE STUDY SUMMARY
This case study solves the problem of parameter estimation for generalized Pareto distribution. Two approaches for parameter estimating are implemented. The first one is maximum likelihood estimate (see Kotz and all 2000). The second one is known as the estimate by harmonic method (see Golodnikov and all. 2019) and is based on the maximum entropy principle with the Renyi entropy and moment constraints. Estimates were evaluated for artificial samples with different length (Problem 1) and for residuals of quantile regression (Problem 2, Dataset2 and Dataset3). Quantile (Problem 2, Dataset 1) and CVaR regression (Problem 3) were evaluated for return distribution of the Fidelity Magellan Fund on the Russell Value Index (RUJ), RUSSELL 1000 VALUE INDEX (RLV), Russell 2000 Growth Index (RUO) and Russell 1000 Growth Index (RLG). Parameters of GPD were estimated according to the described above techniques.
References
• Golodnikov, A., Grechuk, B., Zabarankin, M., Uryasev, S. Method of Moments and Renyi Entropy Maximization.
• Kotz, S., and S. Nadarajah. Extreme Value Distributions: Theory and Applications. London: Imperial College Press, 2000.
• Golodnikov, A., Grechuk, B., Zabarankin, M., Uryasev, S. Method of Moments and Renyi Entropy Maximization.
• Kotz, S., and S. Nadarajah. Extreme Value Distributions: Theory and Applications. London: Imperial College Press, 2000.