Pinned Tweet
What does a temporary expansion in food entitlements tell us about urban vulnerability? Our new paper (https://nitter.gq/t.co/Sk5Pob89JM) in @epw_in (w/ @bijoyhrid and @guatambhan80) highlights gaps in urban social protection with Delhi Govt's COVID-19 PDS E-coupon data. A 🧵1/n
Parushya retweeted
The single biggest argument about statistics: is probability frequentist or Bayesian?
It's neither, and I'll explain why.
Deep-dive explanation incoming:
Parushya retweeted
🙌🙌 Data on every district boundary change in India since 1951? Yes please!
Link in reply
Parushya retweeted
Already spoken to some v interesting applicants.
I'm taking a PhD student this year in political economy & comparative political behavior at @AhdUniv.
Top class faculty w good methodological & interdisciplinary training.
Deadline: Apr 13
Please reach out & see poster below!
I'm recruiting a PhD student in political economy & comparative political behavior at @AhdUniv (elections, political parties, federalism, welfare, or climate)
We believe in interdisciplinary work & offer great training in models of political economy & applied stats.
Pls apply!
Parushya retweeted
PhD applications at Ashoka Econ are now open. It’s a vibrant department with faculty working across multiple and varied research areas - come join us!
Parushya retweeted
1. Use the available data (no listwise deletion)
2. Do not use single imputation
3. For factor-level missingness exceeding 10%, use FIML, EM, & MI
4. For item-level missingness, one item is enough to represent a factor
5. When response rate < 30% conduct sensitivity analysis
In my studies I encounter item- and construct-level missing data. Handle item-level missingness (e.g., missing response in a 10-item survey) by imputing with the mean of available items. But use multiple imputation for construct-level (e.g., entire variable) missingness.
#phdchat
Parushya retweeted
The most important geospatial concept?
Spatial Autocorrelation.
It can make the difference between spurious and accurate results.
Here’s what you need to know about it:
Parushya retweeted
I LOVED learning R. I loved writing in Markdown even more. I now use R for all of my work and only use Stata to look at dta files.
I’ve also come to the conclusion that we are doing students a disservice by teaching Stata. I know that’s controversial, but it’s how I feel now.
Parushya retweeted
🚨 NEW PAPER: When low-income Americans get $1,000/month for 3 years, what happens to their political views & behavior?
The OpenResearch Unconditional income Study reveals surprising findings about the effects of income on politics... 🧵
Parushya retweeted
जिस आवाज़ से छठ की शुरूआत हुआ करती थी, वही आवाज़ छठ के शुरू होते ही ख़ामोश हो गई। शारदा सिन्हा जी अब हमारे बीच नहीं हैं। शारदा सिन्हा ने अपनी गायकी से ऐसी सामूहिकता का सृजन किया जिसे पहचानने के लिए ज़ोर-ज़ोर से चिल्लाना नहीं पड़ता है बल्कि चुपचाप अपने भीतर महसूस करना होता है। उनके गीत छठ का हिस्सा हैं। कहते हैं छठ में कुछ भी बाहरी परिवर्तन नहीं हुआ, जो पुराना है वही चला आ रहा है सिवाय शारदा सिन्हा के छठ गीतों के। क्या कोई छठ को शारदा सिन्ही की आवाज़ से अलग कर सकता है? इन्हीं दिनों लाउड स्पीकर बजने लगते हैं। खेत खलिहानों और नदी किनारे बने घाटों से आ रही उनकी आवाज़ गांव-घर बुलाने लग जाती है।शारदा सिन्हा की आवाज़ बिहार जैसे ग़रीब राज्य की सबसे बड़ी समृद्धी थी। आज बिहार थोड़ा ग़रीब हो गया। हम आपको अपनी यादों में रखेंगे। जब रोएँगे अपनों की याद में, आपको भी याद करेंगे। अलविदा शारदा जी।
Parushya retweeted
Few thinkers were as creative as Albert Hirschman, an economist by training who was broadly respected by the social science community. For an introduction to Hirschman, a point of entry are these works and Adelman’s wonderful biography.
Parushya retweeted
This new article by @sarahsunnbush & @melinaplatas makes a case that 𝘸𝘩𝘰 assigns scores in democracy ratings makes a difference for the way countries are evaluated. This is yet another reason to be very cautious about democracy indices.
Free download: journals.sagepub.com/doi/ful…
Parushya retweeted
Here’s something new by @AdamPrzeworski
It addresses different conceptions of democracy, whether there is a crisis of democracy, and how to defend democracy.
Free download: muse.jhu.edu/pub/1/article/9…
Parushya retweeted
A vote for democracy
In an election in which voters sought out alternate media & the Constitution re-entered mass politics, voters punished BJP for crossing a “red line”
Questions for the future of Indian democracy remain
Final piece in my series w @AiyarYamini (updated image)
Kahan se ho? Allahabad se! #ProudPoorvachali #electionresults
3
235
Parushya retweeted
In what is likely the peak of my scientific career, we created a new variable!
If you’ve ever struggled to quantify the different drivers of extreme humid heat, take a look at our new article on “stickiness” in @AMS_atmos 🧵1/9
journals.ametsoc.org/view/jo…
Parushya retweeted
I updated my post on equivalence tests using {marginaleffects} this morning.
If you want to make an argument *FOR* no effect, then you should be using an equivalence test.
carlislerainey.com/blog/2023…
Parushya retweeted
The most important geospatial concept?
The Modifiable Areal Unit Problem.
It can be the difference between reliable and deceptive results.
Here’s what you need to know about it:
“Andrew, you are skeptical of pretty much all causal claims. But wait, causality rules the world around us, right? Plenty have to be true.” | Statistical Modeling, Causal Inference, and Social Science statmodeling.stat.columbia.e…
1
157
Parushya retweeted
One of the many incredible things about Danny Kahneman: He was a joyful coauthor. Look at how many coauthors he had? His ideas often came from discussions. (When I was struggling to keep with the flood of ideas, all oral, he exclaimed, "Cass, you think by writing. I think by talking!")


































