Daniel Molitor

[Political Analysis @polanalysis]

Currently in FirstView: In “Adaptive Randomization in Conjoint Survey Experiments,” @jennahgosciak, @danieljmolitor, and @IanLundberg1 develop a response-adaptive design for conjoint experiments that summarizes the range of effects of one attribute as a function of all others.

[John B. Holbein @JohnHolbein1]

If you run conjoint experiments, you need to read this.

Most conjoints estimate average effects for each attribute.

But what if the effect of one attribute depends on the others?

This new paper introduces a data-adaptive conjoint design that hunts for heterogeneity:

Where does a focal attribute matter most (or least)—depending on context?

The authors show that U.S. adults weigh immigrants’ education very differently depending on background—sometimes it matters a lot, sometimes not at all.

I’ve only run a few conjoints, but I’ve always wondered:
Why don’t more designs try to surface this kind of interaction?

Very cool. Very important.

[@ashecon @ashecon]

Congratulations to 2024 Diversity Scholarship recipient @skeigold, @CornellBPP.

Learn more about the Diversity Scholarship here: https://t.co/KluujXsAzQ

Sponsored by @DalioDotOrg, @CedarsSinaiMed, @CommonwealthFnd and @Arnold_Ventures

[Daniel Molitor @danieljmolitor]

@nickchk Why are the formula and data arguments being wrapped in lm as opposed to being passed directly to model.matrix?

[Daniel Molitor @danieljmolitor]

Watching the #Vikings offense the past two weeks.

[Daniel Molitor @danieljmolitor]

Me bringing a new research idea to my advisor.

[Buitengebieden @buitengebieden]

Caption this..

[Daniel Molitor @danieljmolitor]

This is largely inspired by the callr package. I'm wondering, am I re-creating the wheel here? The closest I could find was this issue on the callr repo where they said this was out of scope for them: https://t.co/Ug9uM0BuxC.

[Daniel Molitor @danieljmolitor]

#rstats I just cranked out a (still quite rough-shod) package with the goal of executing R functions/code blocks in an R sub-process within a Docker container and returning the results to the main R process. https://t.co/AIopulAg3Q

[Cornell Bowers Computing and Information Science @Cornell_Bowers]

Daniel Molitor, a doctoral student in information science, studies how causal inference can be used to evaluate the impact of policies under the guidance of Ian Lundberg at @CornellInfoSci.

Read more in this @CornellGrad profile: https://t.co/sV7hURB9jq

[Daniel Molitor @danieljmolitor]

Another day in paradise. #MNTwins

[Daniel Molitor @danieljmolitor]

#MLB #WhiteSox

[Daniel Molitor @danieljmolitor]

#MNTwins offense showing up tonight like...

[Daniel Molitor @danieljmolitor]

Ed Donatell after today. #NYGvsMIN

[Daniel Molitor @danieljmolitor]

Average monthly Minnesota air pollution levels (PM2.5) in 2021. Wildfire smoke is no joke! Dots are PM2.5 monitors. #RStats

[Daniel Molitor @danieljmolitor]

#Vikings fans rn

[Daniel Molitor @danieljmolitor]

Recent projections of the #Mets Opening Day budget:

[Daniel Molitor @danieljmolitor]

#Vikings defense whenever they're asked to get a stop.

[Daniel Molitor @danieljmolitor]

@KleinschmidtJD

[Daniel Molitor @danieljmolitor]

@Braves

[Daniel Molitor @danieljmolitor]

Recently wrote up a quick function to configure #RStudio projects to automatically activate project-local #JuliaLang environments. Use a non-RStudio IDE for Julia? Couldn't be me...
Function code: https://t.co/AEwAt7HJmK
#RStats