Conversation

New blog post: Requiring high-powered studies from scientists with resource constraints daniellakens.blogspot.com/2019/08/requir

216

364

Replying to

Great post! Very relevant for students' thesis projects as well! By the way, what do you think about this paper? "Increasing the power of your study by increasing the effect size"

academic.oup.com

Increasing the Power of Your Study by Increasing the Effect Size

Abstract. As in other social sciences, published findings in consumer research tend to overestimate the size of the effect being investigated, due to both file

Darren Dahly, PhD oMG FFs JfC SMDH

Replying to

and

The title is hilarious - but the things in the paper all seem to be well understood ways to *reduce outcome variance* (reduce noise), so that a given effect size is easier to see.

Replying to

and

I never understood how the title went past peer-review (mind you this is a top journal if you are in consumer psych). Maybe the authors view effect size as something constructed

Replying to

and

There are billions of ways to operationalize a research question. Planning a study design and measurement so that effect is maximized and variance is minimizes increases effect size. This doesn't shock me.

12:44 PM · Aug 11, 2019Twitter for Android

Replying to

and

What if you believe there is a “true” effect size independent of researchers’ actions? How do we get to find it out if effect size depends on the design?