iiinova — where your digital self keeps evolving

Ethan McCormick @emccormick.bsky.social · 21/11/2024

I can't tell if this is compliment or insult Daniel

Ethan McCormick @emccormick.bsky.social · 21/11/2024

Without being anti-prereg (I'm not), I think this is exactly what people are worried about, no? The thesis/dissertation process takes a year+ and people feel like they don't want to do that for every paper. Poor incentive alignment perhaps?

100

Ethan McCormick @emccormick.bsky.social · 16/11/2024

Just logged back on, so would appreciate being added. Thx

110

Ethan McCormick @emccormick.bsky.social · 10/09/2024

10 hours of the full soundtrack of LotR

100

Ethan McCormick @emccormick.bsky.social · 12/12/2023

I mean honestly it would save me lots of time and worry haha

100

Ethan McCormick @emccormick.bsky.social · 12/12/2023

Level 5 is this (From a paper a colleague reviewed; N = 11 btw)

100

Ethan McCormick @emccormick.bsky.social · 12/12/2023

Shameless self promotion but if you want an automated way to generate the expansions for SEM growth models, github.com/E-M-McCormic...

110

Ethan McCormick @emccormick.bsky.social · 11/12/2023

I also lay out an approach for estimating any nonlinear function as a linearized SEM through the use of Taylor series expansions. And so you don't have to do the math, I did it for you! With automatic {lavaan} syntax generation using the {leni} package function leni_sem().

020

Ethan McCormick @emccormick.bsky.social · 11/12/2023

Which let's you do all sorts of cool things, like test whether boys really are developmentally delayed compared with girls. Or using a multiphase version, to model puberty or cortical thinning.

120

Ethan McCormick @emccormick.bsky.social · 11/12/2023

General approach is to define a set of transformations for a linear function to a corresponding set of nonlinear parameters that more closely match developmental features of interest. For instance, the timing of developmental transitions or the height of a quadratic peak. See a cubic example below.

100

Ethan McCormick @emccormick.bsky.social · 11/12/2023

New paper+package combination for linear estimation with nonlinear inference (LENI) - methods to obtain the results of a nonlinear model without the hassle of nonlinear estimation. Presented this at Flux this fall and really excited to see it out! osf.io/preprints/ps... github.com/E-M-McCormic...

1249

Ethan McCormick @emccormick.bsky.social · 06/12/2023

Agree with Ashley - they are a lot of fun. Lots of thoughts, so happy to message/email or chat/practice over zoom. Fingers crossed for you!

110

Ethan McCormick @emccormick.bsky.social · 06/12/2023

Exactly. And I need commitments around regular water delivery while I’m in meetings.

010

Ethan McCormick @emccormick.bsky.social · 05/12/2023

I now require 8 pubs minimum to consider an application - seems only fair because I have many myself now and I don’t want a trainee to slow me down, you know?

1100

Reposted by Ethan McCormick

rogier kievit @rogierk.bsky.social · 03/12/2023

PhD vacancy to work with my better half at Leiden University (note - Dutch required because of testing) www.universiteitleiden.nl/vacatures/20...

01012

Ethan McCormick @emccormick.bsky.social · 03/12/2023

Fair warning, maybe save it for a time you’re not already a bit emotionally stressed. Like not between tough paper revision and grant admin hell (not at all a specific example lol)

000

Ethan McCormick @emccormick.bsky.social · 03/12/2023

I just finally got around to reading A Little Life. Definitely needed a big hug after, but so good if you’ve not read it before

000

Ethan McCormick @emccormick.bsky.social · 03/12/2023

A great visual but might be nice to highlight for people that the (eyeballing it) within-person slopes can be partialed out so within subject variance isn’t inflated due to the trend. This of course generalized to other predictors but time trends are often treated with “special” consideration

120

Ethan McCormick @emccormick.bsky.social · 03/12/2023

Drop the reading list haha. I need more suggestions for the new year

000

Ethan McCormick @emccormick.bsky.social · 01/12/2023

Happy to chat over email e.m.mccormick@fsw.leidenuniv.nl if of interest

010

Ethan McCormick @emccormick.bsky.social · 01/12/2023

Are additional people being sought? Longitudinal methods is an area of interest for me and would like to see more of

110

Ethan McCormick @emccormick.bsky.social · 01/12/2023

Happy whamagedden to all who celebrate. I feel like the gays self-disqualify en masse with Mariah. People started posting her one minute after Oct 31

110

Ethan McCormick @emccormick.bsky.social · 01/12/2023

If you figure out how to do that, can I pay you an enormous sum (or at least a sum) to teach me??

010

Ethan McCormick @emccormick.bsky.social · 29/11/2023

Come on, we aren’t like that. We break it a fourth time and tell you that you should have learned better in grad school.

170

Ethan McCormick @emccormick.bsky.social · 29/11/2023

Is there a submission portal for these requests? And do we get to help (I can definitely write at least one sentence in 90 days - or pitch title ideas)?

120

Ethan McCormick @emccormick.bsky.social · 29/11/2023

Looks great - looking forward to reading it!

010

Ethan McCormick @emccormick.bsky.social · 22/11/2023

If you live with yourself haha, Mplus does a similar thing and handles categorical data well

010

Ethan McCormick @emccormick.bsky.social · 18/11/2023

What a wonderful thing to come back from vacation to read! First publication at Psych Methods - feeling really proud of this one.

3161

Ethan McCormick @emccormick.bsky.social · 18/11/2023

Could also consider plausible values search.r-project.org/CRAN/refmans... as a halfway step and treat it like multiple imputation at the 2nd step

120

Ethan McCormick @emccormick.bsky.social · 08/11/2023

Have to include this in the next biosketch!

000

Ethan McCormick @emccormick.bsky.social · 01/11/2023

I feel like it’s different kinds of bad. Like Hellvetica is intentionally bad and no one would ever use it. I’ve sat through comic sans presentations…

000

Ethan McCormick @emccormick.bsky.social · 01/11/2023

Reviewers can’t critique my paper if they can’t stand to look at it. Thanks to @rogierk.bsky.social for the “inspiration”?

1101

Ethan McCormick @emccormick.bsky.social · 27/10/2023

Truly the most neglected subset of society - those with multiple optional dwellings.

010

Ethan McCormick @emccormick.bsky.social · 27/10/2023

“Well which one Beverley, the château in Bordeaux, or the cabin in Aspen??” 🎩🧐

150

Reposted by Ethan McCormick

Eric Layland, PhD 🏳️‍🌈 @ericlayland.bsky.social · 26/10/2023

I’m accepting a grad student to work in my lab on LGBTQ health and development research! Very excited to see the Queer Development Lab grow 🌈 Interested applicants can attend our virtual Open House on November 7 @ 6:30pmET.

cehd.udel.edu

Graduate Programs Virtual Open House – November 2023

Tuesday, November 7, 6:30 to 8:00 p.m. 6:30 to 7:30 p.m. General information for all participants; panel of current students 7:30 to 8:00 p.m. Breakout sessions by academic program Graduates of o...

035

Ethan McCormick @emccormick.bsky.social · 26/10/2023

100% - and other scientific disciplines do regularly historically. No one stopped using geometry just because epicycles were wrong for the orbits of planets. We should feel free to keep what works and bin what doesn't. Maybe it's just a slower process than we want because of inertia/ego/ect. :/

020

Ethan McCormick @emccormick.bsky.social · 26/10/2023

And just to be clear, methods work is NOT immune from this - lots of saddles in search of a horse, and models which probably don't/can't replicate due to overfitting, etc.

010

Ethan McCormick @emccormick.bsky.social · 26/10/2023

Like it's not fun or easy, but I feel like the marginal downside of throwing most things out as "received wisdom" and going down the list with a "is this true?" mindset wouldn't hurt the behavioral sciences in the long-run. Maybe the pages of PNAS/Nature would be emptier for a while but 🤷‍♂️

140

Ethan McCormick @emccormick.bsky.social · 26/10/2023

I guess it depends on whether it's more "I did it, so everyone else must have been too" or something as benign as "Methods/practices have improved over time". But either way, I feel like we can acknowledge that it's true without *accepting* it. Can't we throw things out and start over?

230

Ethan McCormick @emccormick.bsky.social · 26/10/2023

I thought it was like golf and I peaked in 2014 with an all-time low score.

010

Ethan McCormick @emccormick.bsky.social · 26/10/2023

Also, very 🏳️‍🌈, so fair warning.

040

Ethan McCormick @emccormick.bsky.social · 26/10/2023

Finally introducing myself, I'm an assistant professor of Methods and Stats at Leiden University, developing models for longitudinal/timeseries data. Some current projects include distal outcome prediction in growth models, time-varying covariate modes, and interpretable model reparameterizations.

1286

Ethan McCormick @emccormick.bsky.social · 21/10/2023

Straight to jail - clearly it’s “lin’” as pronounced in a deep southern US accent, like I was taught 🙈

010

Ethan McCormick @emccormick.bsky.social · 18/10/2023

Blocking out my whole calendar with this right now

000

Ethan McCormick @emccormick.bsky.social · 10/10/2023

Have a couple running around. Any particular features to the data you would find most useful?

100

Ethan McCormick @emccormick.bsky.social · 02/10/2023

There definitely is an economy of conversation in Dutch faculty meetings sometimes. Last week featured “That is a bad idea…moving on” 😂

040