Mathematical Modeling
Vol. 8 (2024), Issue 3, pg(s) 118-121

MATHEMATICAL MODELLING OF MEDICAL-BIOLOGICAL PROCESSES AND SYSTEMS

Bayesian vs. frequentist inference – an ophthalmic study on ocular perfusion pressure

  • 1 Faculty of Computer Science and Engineering, University Ss Cyril and Methodius Skopje, Republic of North Macedonia1
  • 2 Department of Ophthalmology, Medika Plus Polyclinic, Skopje, Republic of North Macedonia
  • 3 Department of Ophthalmology, City General Hospital “8th of September”, Skopje, Republic of North Macedonia

Abstract

This study investigates the application of Bayesian statistical methods for comparing ocular perfusion pressure (OPP) between glaucoma and non-glaucoma populations, contrasting it with traditional frequentist approaches. Using OPP measurements from two patient groups, we employ partially informed Bayesian models to test the hypothesis of no difference in means between the groups. We calculate Bayes factor using Savage-Dickey density ratio and offer insights in the hypothesis beyond p-values. The results highlight the advantages of the Bayesian approach, including its flexibility in incorporating prior information and interpreting evidence. We discuss the limitations and potential biases introduced by the choice of priors. This paper contributes to the understanding of Bayesian inference in ophthalmic research and emphasizes its potential for hypothesis testing in clinical studies.

Keywords

References

  1. J. P. A. Ioannidis. Why most published research findings are false. PLoS medicine. 2.8 (2005): e124
  2. А. Gelman, E. Loken. The garden of forking paths: Why multiple comparisons can be a problem, even when there is no “fishing expedition” or “p-hacking” and the research hypothesis was posited ahead of time. Department of Statistics, Columbia University 348.1-17 (2013): 3
  3. R. S. Nickerson, Null hypothesis significance testing: a review of an old and continuing controversy. Psychological methods. 5.2 (2000): 241.
  4. D. J. Benjamin et al. Redefine statistical significance. Nature human behavior. 2.1 (2018): 6-10
  5. Е. -Ј. Wagenmakers, A practical solution to the pervasive problems of p values. Psychonomic bulletin & review 14.5 (2007): 779-804
  6. J. Vandekerckhove, J. N. Rouder, J. K. Kruschke. Bayesian methods for advancing psychological science. Psychonomic Bulletin & Review .25 (2018): 1-4
  7. G. Cumming, The new statistics: Why and how. Psychological science 25.1 (2014): 7-29
  8. G. Dimitrova, A. Ljubic, B. Tojtovska, K. Tagasovska, U. Tomasevic. Pressure Related Ocular Parameters in Caucasian Patients with Primary Open-Angle Glaucoma. Journal of Ocular Diseases and Therapeutics. 9, (June 2021), 10–14
  9. K. E. Kim, S. Oh, S.U. Baek, et al. Ocular Perfusion Pressure and the Risk of Open-Angle Glaucoma: Systematic Review and Metaanalysis. Science Reports, 10, 10056 (2020)
  10. M. C. Leske, Ocular perfusion pressure and glaucoma: clinical trial and epidemiologic findings. Current opinion in ophthalmology. (March 2009) 20(2):73-8
  11. M. C. Leske et al. Risk factors for incident open-angle glaucoma: the Barbados Eye Studies. Ophthalmology. 115.1 (2008): 85-93
  12. E. J. Wagenmakers et al. Bayesian hypothesis testing for psychologists: A tutorial on the Savage–Dickey method. Cognitive psychology. 60.3 (2010): 158-189
  13. J. K. Kruschke, "Bayesian analysis reporting guidelines." Nature human behaviour 5.10 (2021): 1282-1291
  14. J. Van Doorn et al. The JASP guidelines for conducting and reporting a Bayesian analysis. Psychonomic Bulletin & Review. 28 (2021): 813-826
  15. A. Etz, Q.F. Gronau, F. Dablander et al. How to become a Bayesian in eight easy steps: An annotated reading list. Psychonomic bulletin & review 25, (2018): 219–234
  16. F.D. Schönbrodt, E.-J. Wagenmakers, M. Zehetleitner, M. Perugini, (2015). Sequential Hypothesis Testing With Bayes Factors: Efficiently Testing Mean Differences. Psychological Methods. 22.2 (2017): 322
  17. W. Zhengxiao, et al. A review of Bayesian hypothesis testing and its practical implementations. Entropy 24.2 (2022): 161
  18. R. van de Schoot, S. Depaoli, R. King, et al. Bayesian statistics and modelling. Nature Reviews Methods Primers 1, 1 (2021)

Article full text

Download PDF