Affiliation:
1. Southwestern University of Finance and Economics
2. Guilin University of Electronic Technology
Abstract
Abstract
Since measurement errors are inevitable in practice, and they are not considered in the existing process performance index, we propose an estimation method of process performance index for two-parameter exponential distribution with measurement errors. In this paper, the relationship between the unobservable actual value and measurement value is considered as an additive measurement error model. The maximum likelihood estimation method is considered to obtain the unknown parameters. In addition, we also use the Bootstrap method to construct confidence intervals of process performance index. The performance of the proposed estimation is investigated in terms of bias, mean square error (MSE) and average interval length. Simulation results show that the proposed estimator outperforms the estimates that do not account for measurement error. Finally, an example of the mileage data of the military personnel carrier is given to illustrate the implementation of the proposed estimation method.
Publisher
Research Square Platform LLC
Reference15 articles.
1. Montgomery, D.C. Introduction to Statistical Quality Control, (New York: John Wiley & Sons 1985).
2. Kane, V.E. Process Capability Indices, J Qual Technol, 18, 41–52 (1986)
3. Lawless, J.F. Statistical Models and Methods for Lifetime Data, (New York: John Wiley & Sons 1982).
4. Normalization of the origin-shifted exponential distribution for control chart construction;Kao SC;J Appl Stat,2010
5. The reliability assessment of the electromagnetic valve of high-speed electric multiple units braking system based on two-parameter exponential distribution;Yang J;Adv Mech Eng,2016