Parameter Estimation for the Double Pareto Distribution

摘要: Problem statement: The double Pareto distribution appeared most often as model for variety of fields, including archaeology, biology, economics, environmental science, finance and physics. exhibits Paretian power-law behavior in both tails. family distributions has recently been proposed modeling growth rates such annual gross domestic product, stock prices, foreign currency exchange company sizes. In this study, I develop parameter estimates the that are easy to compute. compare performance maximum likelihood estimate with Bayesian method moments estimates. Approach: This study contracted likelihood, using Jeffrey’s prior extension information. comparisons made on these estimators respect Mean Squared Error (MSE) small, moderate large samples some values scale parameters simulation techniques. Results: It turns out result smaller MSE compared others all cases. Conclusion: Based results simulation, found be best MSE.