Discover and read the best of Twitter Threads about #MeasurementSchmeasurement
Most recents (3)
1/n This project is finally updated! We argue that generative modeling can improve the quality of inference on behavioral data, and we use simulations and empirical data from the Stroop, Flanker, Posner Cueing, Delay Discounting Task, and IAT to show it.
2/n Recently, many papers have been published showing that traditional analyses lead to poor reliability for behavioral measures. We argue that there are both theoretical and statistical issues with traditional methods (e.g., mean contrasts) that are improved by generative models
3/n We then give an example of how background knowledge can be used to inform generative models of person-specific behavior. Our example uses lognormal and shifted lognormal models, the parameters of which make specific predictions about the shape of a person's response times:
"Common task-fMRI measures are not currently suitable for brain biomarker discovery or for individual-differences research" bc they are highly unreliable (by @max12elliott).
Good to learn after 20+ years of empirical work...
#MeasurementSchmeasurement
journals.sagepub.com/doi/10.1177/09…
Good to learn after 20+ years of empirical work...
#MeasurementSchmeasurement
journals.sagepub.com/doi/10.1177/09…
Here an interesting piece feat. among others @russpoldrack, with a list of ways forward. I would add to the list "draw inferences proportional to the evidence", which this field hasn't been particularly good at (but is not alone in that of course).
today.duke.edu/2020/06/studie…
today.duke.edu/2020/06/studie…
And here some nice ways forward by @ajshackman; couldn't agree more with sentiments like "There is a clear need for new funding mechanisms to support psychometric research and paradigm development".
To help me get back into some sort of routine, I’m going to restart my #paperperday challenge and finish when normal life resumes. Yes, your timeline with be spammed with papers focusing on psychology, cognitive neuroscience, reproducible, and transparent research, again!
#1 Seven Steps Toward Transparency and Replicability in Psychological Science psyarxiv.com/32uz6/ by @dstephenlindsay
“these are...disciplines, practices, even aspirations...I’m still working on them myself...most of us would do better science if we worked on these“
“these are...disciplines, practices, even aspirations...I’m still working on them myself...most of us would do better science if we worked on these“
#2 Why Are Self-Report and Behavioral Measures Weakly Correlated? By @dangjunhua @KMKing_Psych @minzlicht
“These tasks tend to have low reliability, making them unsuitable for psychiatric diagnoses of individuals”
#measurementschmeasurement
doi.org/10.1016/j.tics…
“These tasks tend to have low reliability, making them unsuitable for psychiatric diagnoses of individuals”
#measurementschmeasurement
doi.org/10.1016/j.tics…
