One of the most difficult and important decisions in power analysis involves specifying
an effect size. Researchers frequently employ definitions of small, medium, and large
that were proposed by Jacob Cohen. These definitions are problematic for...
PsychBriefWhy we should no longer use Cohen's recommendations for effect sizes for power analyses: cell.com/trends/cogniti… Short and thought provoking article from Correll et al.
All psychology students are taught is levels of measurement: nominal, ordinal, interval, & ratio. But are they useful? Should we retire them?
PsychBriefNominal, ordinal, interval, and ratio. These levels of measurement are everywhere in psychology and are the foundation for many statistical analyses. But are they as essential as they are often presented? New blog post
In a classic 1978 Memory &Cognition article, Geoff Loftus explained why noncrossover interactions are removable. These removable interactions are tied to the scale of measurement for the dependent variable and therefore do not allow unambiguous ...
The direction of an association at the population-level may be reversed within the subgroups comprising that population—a striking observation called Simpson's paradox. When facing this pattern, psychologists often view it as anomalous. Here, ...
PsychBriefMost researchers believe Simpson's paradox (where the trend disappears or reverses when going from looking at the whole data set to subgroups or vice versa) is rare but the rate at which it's found and simulation studies say otherwise
It sucks you in before you can even think – that dramatic statistic that makes a point you're inclined to believe, with a bang. After that, no matter how many times it's shot down, it just keeps going... And so you have it: a zombie statistic....
A game about writing nice letters to real people. Write and receive encouraging letters in a cozy room. Trade stickers and listen to chill music. We're all in this together. Sometimes all you need are a few kind words.
PsychBriefMy friend brought this game to my attention and I think it's really cool: you post short comments about what's bothering you and the community sends you anonymous letters of support. And there's almost no negativity in the community. Plus chill music
PsychBriefI'm a huge fan of preregistration, so reading critical articles of it is very important. This short paper by Szollosi, Kellen, @djnavarro, Shiffrin, @IrisVanRooij, Van Zandt, & Donkin is well worth your time.
A common criticism of research is that it's under powered so the results should be treated with caution. But what does "under powered" actually mean?
PsychBriefWhen critiquing a study, it's common to say the study is "under powered". But what does that mean and does it further the discussion? I've written a short post examining this criticism and whether it is useful psychbrief.com/under-powered-… What are your thoughts?
1000+ courses from schools like Stanford and Yale - no application required. Build career skills in data science, computer science, business, and more.
PsychBriefNew free MOOC by @lakens on how to improve the questions you ask of your data is live! coursera.org/learn/improvin… the 1st was excellent and this looks just as good, if not better. I've recently started to appreciate importance of the questions you ask, so it's perfect timing
The 'paradox of choice' (where too many options can overwhelm and frustrate consumers) is a popular idea. But what is the empirical support for it?
PsychBriefThe 'Paradox of Choice' is often brought up as an explanation for the choices people make (too many options overwhelm us and we are then unhappy with our decision). But what is the empirical evidence for it? New post: psychbrief.com/choice-paradox/ What is your view on choice overload?
The Intensive Partnerships for Effective Teaching initiative enhanced how teachers are evaluated and improved teacher staffing policies but did not lead to gains in student achievement or graduation rates.
PsychBriefLarge-scale implementation of teacher observation designed to improve teaching effectiveness found no effect on student's achievement or graduation rates