# Nonparametric Effect Size estimation, Likelihood Methods, and Meta Analysis

**URL:** <https://discourse.datamethods.org/t/nonparametric-effect-size-estimation-likelihood-methods-and-meta-analysis/1525>\
**Category:** meta-analysis\
**Created:** [March 27, 2019, 1:06pm UTC](https://discourse.datamethods.org/t/nonparametric-effect-size-estimation-likelihood-methods-and-meta-analysis/1525 "2019-03-27T13:06:34Z")\
**Posts on this page:** 1\
**Showing post:** 9

<div class="post-metadata">

**Author:** ![R\_cubed](https://discourse.datamethods.org/user_avatar/discourse.datamethods.org/r_cubed/32/1518_2.png) [@R\_cubed](https://discourse.datamethods.org/u/R_cubed)\
**Post date:** [October 13, 2019, 5:02pm UTC](https://discourse.datamethods.org/t/nonparametric-effect-size-estimation-likelihood-methods-and-meta-analysis/1525/9 "2019-10-13T17:02:31Z")

</div>

The aggregation of effect sizes on anything other than interval and ratio scaled variables is much more complicated than I initially anticipated. You would not know this from most of the readily available texts on meta-analysis, as far as I can tell.

This discussion hinted at the problems:

> [@Does data-based variable reduction lead to confounding?](https://discourse.datamethods.org/t/does-data-based-variable-reduction-lead-to-confounding/2405):
>
> Sander Greenland and colleagues do a good job explaining how the standardization of predictors leads to confounded estimates of both correlational and causal effects: because standardization depends on the eccentricities of the training data. I wonder if, for similar reasons, data reduction methods (e.g., principal components regression) have the same issue and why.

Relevant article by Stephen Senn on Effect size measurements, particularly non-parametric ones.

Stephen Senn (2011) [U is for Unease: Reasons for Mistrusting Overlap Measures for Reporting Clinical Trials](https://amstat.tandfonline.com/doi/abs/10.1198/sbr.2010.10024)

Stehpen Senn (2000) [The Many Modes of Meta](https://journals.sagepub.com/doi/abs/10.1177/009286150003400222)

Some issues related to standardized effect:  
Peter Cummings MD, MPH (2004) [Meta-analysis Based on Standardized Effects Is Unreliable](https://jamanetwork.com/journals/jamapediatrics/article-abstract/485720)

Peter Cummings MD, MPH (2011) [Arguments for and Against Standardized Mean Differences (Effect Sizes)](https://jamanetwork.com/journals/jamapediatrics/article-abstract/1107539?resultClick=1)

Milo A Puhan, Irene Soesilo, Gordon H Guyatt & Holger J Schünemann (2006) [Combining scores from different patient reported outcome measures in meta-analyses: when is it justified?](https://hqlo.biomedcentral.com/articles/10.1186/1477-7525-4-94)

---

_[View the full topic](https://discourse.datamethods.org/t/nonparametric-effect-size-estimation-likelihood-methods-and-meta-analysis/1525)._