Performance of the One-Sample Goodness-of-Fit P–P-Plot Length Test

Abstract

This article studies the performance of the one-sample goodness-of-fit test which is based on the length of the P–P-plot initially introduced in a similar context by Reschenhofer and Bomze (1991). The distributional properties of the length test are revised empirically via simulations. In the Monte Carlo power study that follows the length test is shown empirically to have high power under various alternatives considered relative to members of the Cramér–von Mises family of goodness-of-fit tests, and the Kolmogorov–Smirnov test.

Keywords:

• Cramér–von Mises family
• Goodness-of-fit tests
• Kolmogorov–Smirnov test
• P–P-plot
• Spacings

Mathematics Subject Classification:

• Primary 62G30
• Secondary 62E99