Probability of direction
 | This article, Probability of direction, has recently been created via the Articles for creation process. Please check to see if the reviewer has accidentally left this template after accepting the draft and take appropriate action as necessary.
Reviewer tools: Inform author |
| This article, Probability of direction, has recently been created via the Articles for creation process. Please check to see if the reviewer has accidentally left this template after accepting the draft and take appropriate action as necessary.
Reviewer tools: Inform author |
In Bayesian statistics, the Probability of Direction (pd) is a measure of effect existence representing the certainty with which an effect is positive or negative.[1] This index is numerically similar to the frequentist p-value.[2][3]
Definition
It is mathematically defined as the proportion of the posterior distribution that is of the median's sign. It typically varies between 50% and 100%.[4]
History
The original formulation of this index and its usage in Bayesian statistics can be found in the psycho software documentation under the appellation Maximum Probability of Effect (MPE).[5][6] Similar formulations have also been described in the context of bootstrapped parameters interpretation.[citation needed]
Properties
The probability of direction is typically independent of the statistical model, as it is solely based on the posterior distribution and does not require any additional information from the data or the model. Contrary to indices related to the Region of Practical Interest (ROPE), it is robust to the scale of both the response variable and the predictors. However, similarly to its frequentist counterpart - the p-value, this index is not able to quantify evidence in favor of the null hypothesis.[2][7] Advantages and limitations of the probability of direction have been studied by comparing it to other indices including the Bayes Factor or Bayesian Equivalence test.[2][8][4][9]
Relationship with p-value
The probability of direction has a direct correspondence with the frequentist one-sided p-value through the formula and to the two-sided p-value through the formula . Thus, a two-sided p-value of respectively .1, .05, .01 and .001 would correspond approximately to a pd of 95%, 97.5%, 99.5% and 99.95%.[10] The proximity between the pd and the p-value is in line with the interpretation of the former as an index of effect existence, as it follows the original definition of the p-value.[11][12]
Interpretation
The bayestestR package for R suggests the following rule of thumb guidelines:[13]
style="text-align: left; margin-left: auto; margin-right: auto; border: none;"| pd | p-value equivalence | Interpretation |
|---|---|---|
| Uncertain | ||
| Possibly existing | ||
| Likely existing | ||
| Probably existing | ||
| Certainly existing |
See also
References
- ^ Makowski, Dominique; Ben-Shachar, Mattan; Lüdecke, Daniel (13 August 2019). "bayestestR: Describing Effects and their Uncertainty, Existence and Significance within the Bayesian Framework". Journal of Open Source Software. 4 (40): 1541. doi:10.21105/joss.01541.
- ^ a b c Makowski, Dominique; Ben-Shachar, Mattan S.; Chen, S. H. Annabel; Lüdecke, Daniel (10 December 2019). "Indices of Effect Existence and Significance in the Bayesian Framework". Frontiers in Psychology. 10: 2767. doi:10.3389/fpsyg.2019.02767.
{{cite journal}}: CS1 maint: unflagged free DOI (link) - ^ Heiss, Andrew. "Bayesian statistics resources". Georgia State University - Bayesian statistics course. Retrieved 7 December 2021.
- ^ a b Kelter, Riko (December 2020). "Analysis of Bayesian posterior significance and effect size indices for the two-sample t-test to support reproducible medical research". BMC Medical Research Methodology. 20 (1): 88. doi:10.1186/s12874-020-00968-2.
{{cite journal}}: CS1 maint: unflagged free DOI (link) - ^ Makowski, Dominique (5 February 2018). "The psycho Package: an Efficient and Publishing-Oriented Workflow for Psychological Science". The Journal of Open Source Software. 3 (22): 470. doi:10.21105/joss.00470.
- ^ Makowski, Dominique. "psycho - The Bayesian Framework". cran.r-hub.io. Retrieved 26 November 2021.
- ^ Kelter, Riko (28 September 2021). "How to Choose between Different Bayesian Posterior Indices for Hypothesis Testing in Practice". Multivariate Behavioral Research: 1–29. doi:10.1080/00273171.2021.1967716.
- ^ Baig, Sabeeh A (22 October 2021). "Bayesian Inference: Parameter Estimation for Inference in Small Samples". Nicotine & Tobacco Research: ntab221. doi:10.1093/ntr/ntab221.
- ^ Kelter, Riko (2021). "Bayesian and frequentist testing for differences between two groups with parametric and nonparametric two-sample tests". WIREs Computational Statistics. 13 (6): e1523. doi:https://doi.org/10.1002/wics.1523.
{{cite journal}}: Check|doi=value (help); External link in|doi= - ^ "BayestestR - Probability of Direction". https://easystats.github.io/bayestestR. Retrieved 26 November 2021.
{{cite web}}: External link in|website= - ^ Fisher, R. A. (1925). Statistical methods for research workers (11th ed. rev.). Edinburgh: Oliver and Boyd.
- ^ Cohen, Jacob (1994). "The earth is round (p < .05)". American Psychologist. 49 (12): 997–1003. doi:10.1037/0003-066X.49.12.997.
- ^ "Bayesian Reporting Guidelines". https://easystats.github.io/bayestestR. Retrieved 26 November 2021.
{{cite web}}: External link in|website=
External links
- bayestestR — an R package for computing Bayesian indices