Account Share

 

Thread by @HeatherUrry: "Thread on making a difference. When I was a kid, I went on many camping trips with my mom and stepdad. One one such trip, we camped near san […]"

25 tweets
Thread on making a difference.

When I was a kid, I went on many camping trips with my mom and stepdad. One one such trip, we camped near sand dunes because my mom was writing a book called Seasons of the Wind. It's about plant life on sand dunes in the southwest United States.
I remember hiking in the sand, putting one foot in front of the other. Forward progress was surprisingly difficult. Step, sink, pull, repeat. And standing at the top of a dune was dizzying; they seemed to move, almost breathe.
Since 2011, I've felt a bit like I'm back on that dune, the sand shifting under my academic feet. Am I doing this right? What findings can we trust? What the hell is evidence anyway? Maybe I never really knew anything to begin with. Maybe this sand will pull me under.
But as I was running today with the sun shining and the sky serving blue, a slow bliss wended its way through my limbs. Just natural opioids doing their thing, I thought. Or, maybe that spot-on Discover Weekly playlist, courtesy of Spotify.
But I don't think it was either of those things. (Maybe it was, but this would be a short, unsatisfying thread if I left it at that so humor me.) No. It was a dawning realization: I can handle all that sand. Why?
1. I work with fantastic graduate students - every day, @laravu05 , @victoriafloerke , Gizem, and @jmperry06 inspire me to be a better advisor. How could it be otherwise when these smart people wake up every day and do science with me.
New ideas, new analytic techniques, new words on a new page of yet another proposal or preregistration. It's really hard and I don't always know what the hell we should do; nevertheless they persist. And we figure it out.
And now we know things that the world didn't know before - the weight of the evidence in the world shifted just a little bit because of them, and I get to be a part of that.
2. I teach a new graduate research practices course. I'm working with 8 smart people each on a path to their doctorates in fields like psychology, computer science, and occupational therapy.
I get to spend 2.5 hours a week with them to talk about things that matter to all of science. As little as a few years (and in some cases months!) ago, I didn't know much of what we're talking about. But we're doing it, learning together as we go.
We've had lively conversations about frequentist statistics, what a confidence interval REALLY means, the shape of a distribution of p values assuming true and false nulls with varying degrees of power.
We've talked about HARKing and p-hacking. We literally debated the relative merits of direct versus conceptual replications. They're working on proposals for a replication study (due tomorrow!) one of which we're going to run collaboratively.
We're going to preregister a plan that gives adequate power for our focal tests and write a reproducible manuscript in R Markdown. We're going to give constructive peer reviews and, damn it, we just might solve perverse incentives and publication bias while we're at it.
3. I teach undergraduate research methods. I'm working with ~100 bright minds twice a week in a lecture and I plan a 2.5 hour lab for them each week too.
They don't generally want to take this class - they do it because they have to. Every day I wake up wondering what I can do today that'll make it more likely they'll walk away thinking, "Hey, that was actually pretty useful and maybe even kinda cool."
So far this semester, they've grappled with association and causal claims, validity in all flavors (construct, internal, external, statistical), reliability, and measurement error. They know that X = T + e, where e can be random and/or systematic.
They know that headlines reporting research don't always get it right. They know about effect sizes and power and p-hacking. They know how to interpret a p value CORRECTLY. They know about random assignment and confounds.
They know that a single study does not a theory make. They know about the importance of replication. We've already conducted one direct replication experiment and we just got IRB approval to conduct a second. We're about to preregister and practice data collection procedures.
They know about using syntax to maximize computational reproducibility and they're damn well going to know about open materials, data, and code when we post ours.
4. I have the privilege of working with people I respect on projects that have great meaning to me outside of my lab and university. For example, I found 40+ collaborators from 16+ countries (!!) who want to study whether the pen is mightier than the keyboard with me.
I'm helping to make the Psychological Science Accelerator (@PsySciAcc) a living breathing global collaborative network. Working on the leadership team and writing both a manuscript and a grant with coauthors who inspire me has been so satisfying.
I've had the opportunity to contribute thoughts to a paper about the importance of representation, making sure we don't sacrifice insights about people from underrepresented groups for the sake of statistical rigor. I feel so lucky to have been asked to join this effort.
I had the pleasure of attending SIPS last year, where I joined a hackathon on diversity and inclusion. I've since been helping @johnpaulwilson and Yuichi Shoda carry forward the brilliant idea to hold an SPSP event to foster collaborations involving hard-to-reach populations.
I get to attend SIPS2018 in June, where I'll co-lead a hackathon on teaching replicable science and an unconference on peer review. I'm going to pour everything I'm learning in my own classes at Tufts into those experiences, and know I'll come away smarter and full of new ideas.
So, yeah. I'm standing on a dune, but the wind is quiet and the sand is holding me steady. When the season of the wind starts up again - it always does - maybe this time I'll remember: I'm strong and, damn it, that sand is beautiful.
Missing some Tweet in this thread?
You can try to force a refresh.
This content can be removed from Twitter at anytime, get a PDF archive by mail!
This is a Premium feature, you will be asked to pay $30.00/year
for a one year Premium membership with unlimited archiving.
Don't miss anything from @HeatherUrry,
subscribe and get alerts when a new unroll is available!
This is a Premium feature, you will be asked to pay $30.00/year
for a one year Premium membership with unlimited subscriptions/alert.
Did Thread Reader help you today?
Support me: I'm a solo developer! Read more about the story
Become a 💎 Premium member ($30.00/year) and get exclusive features!
Too expensive?
Make a small donation instead. Buy me a coffee ($5) or help for the server cost ($10):
Donate with 😘 Paypal or  Become a Patron 😍 on Patreon.com
Using crypto? You can help too!
Trending hashtags
Did Thread Reader help you today?
Support me: I'm a solo developer! Read more about the story
Become a 💎 Premium member ($30.00/year) and get exclusive features!
Too expensive?
Make a small donation instead. Buy me a coffee ($5) or help for the server cost ($10):
Donate with 😘 Paypal or  Become a Patron 😍 on Patreon.com
Using crypto? You can help too!