A new goodness of fit test for uniform distribution with censored observations

TL;DR

This paper introduces a novel goodness of fit test for the uniform distribution that accounts for censored data, supported by theoretical analysis, simulations, and real data applications.

Contribution

It develops a new test based on fixed point characterization and extends it to handle right censored observations, with asymptotic properties analyzed.

Findings

Test performs well in finite samples

Incorporates censored data effectively

Validated with real data examples

Abstract

Using fixed point characterization, we develop a new goodness of fit test for uniform distribution. We also discuss how the right censored observations can be incorporated in the proposed test procedure. We study the asymptotic properties of the proposed test statistics. A Monte Carlo simulation is carried out to evaluate the finite sample performance of the tests. We illustrate the test procedures using real data sets.