Sanjay Srivastava Profile picture
Personality, reputation, culture, identity, lifespan development, research methods, open science. https://t.co/8SzulCftJq he/him
Oct 21, 2022 7 tweets 2 min read
I suppose it’s as good a time as any to share this news. This fall I am winding down my lab, teaching my last class, and getting ready to leave my job as a tenured professor. At the end of this year I will be leaving the academic industry for that other one In January I start a new job as a senior behavioral scientist at Apple. I’ll be doing interdisciplinary research with engineers, designers, and others on ML and personalization. So - applied personality psychology and psychometrics, kinda sorta
Oct 20, 2022 4 tweets 1 min read
Something I have grown to appreciate recently is how distortions in the prestige market are linked to the trend in higher ed toward centralization of power with administrators and erosion of shared governance Administrators don’t want a system where you have to read somebody’s work in order to evaluate them professionally. That would cede power to department colleagues with subject matter expertise. They want to pull the strings themselves
May 5, 2022 16 tweets 4 min read
Interesting commentary by Gratton et al on brain-behavior correlations. Marek et al. discussed increasing sample size. Their second "path" is to change research designs, such as using within-Ss designs, recruiting populations with extreme variability (like lesions), etc. 1/ Something easy to overlook, though, is that changing the research design often changes the substantive research question. Consider this example of moving from a cross-sectional association to within-person change. This isn't just a change in design, it is a change in estimand 2/
Apr 24, 2022 4 tweets 1 min read
As the number of people discussing some matter of importance increases, the probability that somebody who agrees with you is a dick approaches 1 Corollary: Rapidly
Feb 8, 2022 6 tweets 2 min read
I wish I was more surprised. There is a loophole in FERPA that allows universities to access students' private therapy records for the purpose of defending themselves in court. There was a notorious case at my university involving this with a rape survivor oregonlive.com/education/2015… Oregon banned it after that incident came out. But AFAIK it is still permitted at a federal level oregonlive.com/education/2015…
Jul 22, 2021 12 tweets 2 min read
And now a thread of things that must be true in order to validly interpret a standard mediation analysis.

These are assumptions you must defend with outside knowledge. They are not tested as part of the analysis, and often they are not testable even in principle.

Here goes... 1. The effect of M on X is exactly zero
Jul 21, 2021 4 tweets 1 min read
If psychologists had to present and defend a DAG every time they did a mediation analysis, 10% of them would result in "sorry the effect we care about isn't identified" and the other 90% would be "sorry we don't understand this phenomenon well enough to draw a DAG" (Apparently today is "be salty about mediation" day in my brain)
Apr 7, 2021 10 tweets 3 min read
Hey psychology twitter. The journalist Jesse Singal is probably going to be showing up on your radar because he has a new book about social psychology. He has also written about trans people. I want to encourage you to read what trans people have said about that work There is a lot of stuff out there and it can feel a little overwhelming. Here is one place to start, a collection of links to critiques of a very influential 2018 Atlantic article he wrote patreon.com/posts/19542136
Jan 28, 2021 7 tweets 1 min read
NOT SWEENEY NOT SWEENEY TODD
Jan 27, 2021 6 tweets 2 min read
Is who you follow on Twitter correlated with your mental health? Using machine learning, we find that the high-degree accounts that people follow - celebrities, public figures, etc. - can predict anxiety, depression, post-traumatic stress, & anger (out-of-sample R = .2) Substantive upshot: A user's Twitter experience - what they see in their feed - is heavily affected by their decisions of who to follow. Those curation decisions, in the aggregate, are associated with mental health
Dec 17, 2020 15 tweets 4 min read
Were you taught that you cannot interpret a main effect in the presence of an interaction? That interactions "supersede" main effects? That you have to use hedging language like, "the effect of A depends on B"?

Then I've got a little provocation for you. Thread... Imagine the following study: People with depression are randomly assigned to get either drugs or psychotherapy. In addition, they are asked which they believe is more effective: half say drugs, half say therapy. Outcome is functioning after treatment (0-100). So it's a 2x2
Dec 10, 2020 4 tweets 1 min read
I’m sorry but Bounty is just begging to be memed
Jun 3, 2020 6 tweets 2 min read
Are you looking for places to make a(nother) round of donations? Were you not looking but now you're like, hunh, now that you mention it maybe I should? Here are 4 ideas Campaign Zero promotes "data-driven policy solutions" to end police violence joincampaignzero.org
Feb 24, 2020 7 tweets 2 min read
LEAKED! Episode titles and plot summaries from The Chair, Netflix's upcoming 6-part series about an academic department...

deadline.com/2020/02/sandra… HOLD THE FLOOR

A faculty meeting goes awry when one of the assistant professors calls out a senior male professor for repeating her ideas as if they're his own. A standoff ensues, only to be resolved when another senior male professor offers the same complaint but louder
May 9, 2019 9 tweets 2 min read
You guys. We just did a little demo in my research methods class to introduce them to p-values and statistical significance. And I'm super excited at how it went down The demo was simple. Students pair up. One student, the flipper, flips a coin. The other, the guesser, guesses the result. Flipper tells them right or wrong. Then they switch roles and do it again. Everybody reports their results on their iClicker
Mar 10, 2019 4 tweets 2 min read
This is your semi regular reminder that among players who have been admitted to the NBA, height has no association with basketball performance And that’s not even getting into the validity issues with the criterion variables
Dec 13, 2018 18 tweets 5 min read
Let's talk cross-lagged panel models! A short example/provocation, inspired by some discussion yesterday Say you have 2 things you're interested in, X and Y, each measured at 2 times. You want to know does X cause Y, Y cause X, or both? (or if you're shy about saying "cause" you say "lead to," "predict," "is a risk factor for," "Granger-cause," etc.).
Oct 3, 2018 18 tweets 5 min read
One of the issues @alexa_tullett, @siminevazire, and I talked about in this episode is a super important and kinda counterintuitive question (b/c superficially it feels unscientific): When should you believe research you do not understand? (thread) This question was posed really well by @NaomiOreskes, who pointed out that even scientists do not have the subject-matter and technical expertise to evaluate all of the science they consume and rely on ted.com/talks/naomi_or…
Sep 12, 2018 11 tweets 4 min read
Here is a list of things I wish Tom Bartlett (@tebartl) had done better in covering SIPS for this @chronicle article chronicle.com/article/I-Want… 1. Talked to more than one woman in SIPS. They are about half of the organization's members
Aug 27, 2018 13 tweets 3 min read
Coverage of the new multi-study replication project by @edyong209, who dives in to why the prediction market was so effective and what that means theatlantic.com/science/archiv… One important thing that the prediction market did is change the cost-benefit analysis for expressing hunches as behavior
Mar 3, 2018 47 tweets 7 min read
About to start - a symposium session on fresh* results from a multi-site ego depletion study #spsp2018

* Like apparently even the participating labs don’t know the results yet (?) Vohs will give background and approach. @BJSchmeichel will present results. @DavidFunder will discuss (@EJWagenmakers couldn't make it in person)