Transformation Approaches for the Construction of Weibull Prediction Interval

• Main Authors: YANG, Zhenlin, SEE, Stanley P., XIE, Min
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2003
• Subjects: Box-Cox transformation; Coverage probability; Kullback-Leibler information; Prediction interval; Weibull distribution; Econometrics
• Online Access: https://ink.library.smu.edu.sg/soe_research/196; https://ink.library.smu.edu.sg/context/soe_research/article/1195/viewcontent/Transformation_Weibull_prediction_2003.pdf
• Institution: Singapore Management University

Two methods of transforming the Weibull data to near normality, namely the Box-Cox method and Kullback-Leibler (KL) information method, are discussed and contrasted. A simple prediction interval (PI) based on the better KL information method is proposed. The asymptotic property of this interval is established. Its small sample behavior is investigated using Monte Carlo simulation. Simulation results show that this simple interval is close to the existing complicated PI where the percentage points of the reference distribution have to be either simulated or approximated.