A Comparison Study of Three Types of Parameter Estimation Methods on Weibull Model
| Autor: | Shu Guo, Ying Zhai, Xiaofeng Wang, Yang Liu, Xiaogang Zhu |
|---|---|
| Rok vydání: | 2020 |
| Předmět: | |
| Zdroj: | Advances in Intelligent Systems and Computing ISBN: 9783030539795 ATCI |
| Popis: | Estimation of the Weibull parameters is vital to reliability engineering. In engineering, the least squares regression of y (LS Y) is often used for Weibull distribution’s parameter estimation. LS Y only involves the error of the y coordinate but doesn’t involve the error of the x coordinate. Similarly, the least squares regression of x (LS X) only involves the error of x coordinate but doesn’t involve the error of y coordinate. Total least squares (TLS), however, involves both the error of x coordinate and y coordinate, therefore, TLS is introduced to estimate the parameters of the Weibull distribution in this paper. The comparison and selection among the estimators of the three parameter estimation methods is carried out using Monte Carlo simulations. The results demonstrate that we can directly choose LS X, when sample size n > 20. It is necessary to select the parameter estimation methods by comparing \( Q_{T} \) in TLS constrained criterion and \( Q_{x} \) in LS X constrained criterion, when sample size n < 20. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|