English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Journal Article

A straightforward and valid correction to Nathoo et al.'s Bayesian within-subject credible interval

MPS-Authors
/persons/resource/persons291015

Lindner,  Christoph
Max Planck Institute of Psychiatry, Max Planck Society;

External Resource
No external resources are shared
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)
There are no public fulltexts stored in PuRe
Supplementary Material (public)
There is no public supplementary material available
Citation

Zitzmann, S., Lindner, C., & Hecht, M. (2024). A straightforward and valid correction to Nathoo et al.'s Bayesian within-subject credible interval. JOURNAL OF MATHEMATICAL PSYCHOLOGY, 122: 102873. doi:10.1016/j.jmp.2024.102873.


Cite as: https://hdl.handle.net/21.11116/0000-000F-A940-A
Abstract
The APA encourages authors to thoroughly report their results, including confidence intervals. However, considerable debate exists regarding the computation of confidence intervals in within-subject designs. Nathoo et al.'s (2018) recently proposed a Bayesian within-subject credible interval, which has faced criticism for not accounting for the uncertainty associated with estimating subject-specific effects. In this article, we show how Nathoo et al.'s within-subject credible interval can be easily corrected by utilizing the theory of degrees of freedom. This correction obviates the necessity for estimates of subject-specific effects that offer shrinkage. Instead, it involves a straightforward adjustment in degrees of freedom in both the interaction mean squares and the t-distribution used to compute the interval. Therefore, our proposed interval, being easily computable through a simple formula, eliminates the need for fully Bayesian approaches. It accurately represents uncertainty and offers the interpretational benefit of Bayesian intervals.