Goodness-of-fit test for exponentiality based on spacings for general progressive Type-II censored data

Area of Science:

• Statistics
• Probability Theory
• Reliability Engineering

Background:

• Assessing the suitability of the exponential model is crucial in statistical analysis.
• Existing tests for exponentiality may have limitations with censored data.
• General progressive Type-II censoring is a common scenario in reliability and survival analysis.

Purpose of the Study:

• To propose a novel test statistic for the exponential distribution using general progressive Type-II censored samples.
• To investigate the null distribution and power properties of the new test statistic.
• To compare the performance of the proposed test with normal approximations via simulation.

Main Methods:

• Development of a new test statistic based on spacings for exponentiality.
• Derivation of the null distribution and approximation using the standard normal distribution.
• Simulation studies comparing Monte Carlo results with normal approximations under various alternatives and hazard functions.

Main Results:

• The proposed test statistic's null distribution can be approximated by the standard normal distribution.
• Power comparison reveals the test performs better with Monte Carlo simulations for increasing hazard functions.
• Normal approximation results are relatively better for other types of hazard functions.

Conclusions:

• The new spacing-based test offers a viable method for testing exponentiality with general progressive Type-II censored data.
• The choice between Monte Carlo simulation and normal approximation for power evaluation depends on the underlying hazard function.
• The study provides valuable insights for reliability and survival data analysis.