Anderson-Darling and Watson tests for the geometric distribution with estimated probability of success
2024

New Tests for the Geometric Distribution

Sample size: 1032 publication 10 minutes Evidence: moderate

Author Information

Author(s): Coronel-Brizio Héctor Francisco, Hernández-Montoya Alejandro Raúl, Rodríguez-Achach Manuel Enrique, Tapia-McClung Horacio, Trinidad-Segovia Juan Evangelista

Primary Institution: Instituto de Investigaciones en Inteligencia Artificial, Universidad Veracruzana, Xalapa, Veracruz, México

Hypothesis

Can the Anderson-Darling and Watson tests be adapted for discrete models, specifically the geometric distribution?

Conclusion

The study successfully develops new goodness-of-fit tests for the geometric distribution, demonstrating their applicability in financial data analysis.

Supporting Evidence

  • The tests developed provide a robust statistical framework for discrete distributions.
  • Extensive tables of asymptotic critical values for the tests are included.
  • The methodology is demonstrated through a financial case study involving major stock indices.

Takeaway

This study created new ways to check if data fits a specific pattern called the geometric distribution, which is useful for understanding trends in financial markets.

Methodology

The study adapts the Anderson-Darling and Watson tests for discrete distributions and applies them to financial time series data.

Limitations

The assumption of a constant probability of success over time may oversimplify the dynamic nature of financial markets.

Statistical Information

Confidence Interval

[0.490, 0.534]

Digital Object Identifier (DOI)

10.1371/journal.pone.0315855

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication