iiinova — where your digital self keeps evolving

Vitor Possebom @vitorpossebom.bsky.social · 31/12/2023

Should I install Windows 11 instead of Windows S? It is a bit annoying that Windows S does not support many softwares, including Zoom…

100

Vitor Possebom @vitorpossebom.bsky.social · 03/12/2023

Thank you for the suggestion! It looks cool!

010

Vitor Possebom @vitorpossebom.bsky.social · 03/12/2023

I’m looking for podcast recommendations! Maybe something based on history, like Revolutions: open.spotify.com/show/05lvdf9T7… Or maybe something about economic policy? Like Americas Quarterly (open.spotify.com/show/5PCntXM9L ), but about the economy?

330

Reposted by Vitor Possebom

Pedro Sant’Anna @pedrosantanna.bsky.social · 27/11/2023

It is great seeing a new WP out in the wild! 👇👇👇

0112

Vitor Possebom @vitorpossebom.bsky.social · 27/11/2023

📉📈#Econsky, some of you may be interested in my new working paper about MTE with Duration Outcomes. @pedrosantanna.bsky.social and Santi are amazing co-authors.

080

Vitor Possebom @vitorpossebom.bsky.social · 27/11/2023

The paper also discusses other available methods in the literature, alternative assumptions, and decision-theoretical reasons to focus on time-to-recidivism as an outcome variable. Check the full paper here: arxiv.org/abs/2311.13969

arxiv.org

Was Javert right to be suspicious? Unpacking treatment effect...

This paper presents new econometric tools to unpack the treatment effect heterogeneity of punishing misdemeanor offenses on time-to-recidivism. We show how one can identify, estimate, and make...

000

Vitor Possebom @vitorpossebom.bsky.social · 27/11/2023

Our QMTE point estimates suggest that designing sentencing guidelines that encourage strict judges to become more lenient could lead to increasing time-to-recidivism.

100

Vitor Possebom @vitorpossebom.bsky.social · 27/11/2023

These point estimates suggest that defendants whom almost all judges would punish would take longer to recidivate, while defendants who would be punished only by tough judges would recidivate faster compared to situations where they would not be punished.

100

Vitor Possebom @vitorpossebom.bsky.social · 27/11/2023

All QMTE functions behave similarly. Although the level of the estimated QMTEs depends on the quantile, all functions are decreasing in the unobserved resistance to punishment.

100

Vitor Possebom @vitorpossebom.bsky.social · 27/11/2023

To have a deeper understanding of the time trade-offs associated with the effect of punishment on time-to-recidivism, we now focus on the QMTE. They use easy-to-interpret units (days before recidivism) and may work as good summary measures.

100

Vitor Possebom @vitorpossebom.bsky.social · 27/11/2023

This rich heterogeneity is relevant. If two researchers were to focus only on a specific but different time frame they may get different answers, highlighting that the practice of “binarizing” duration outcomes may come with caveats.

100

Vitor Possebom @vitorpossebom.bsky.social · 27/11/2023

But things change a lot in the long-run! The DMTEs are decreasing. This indicates that defendants whom almost all judges would punish would recidivate faster because of the punishment, while defendants who would be punished only by tough judges would take longer to recidivate.

100

Vitor Possebom @vitorpossebom.bsky.social · 27/11/2023

The DMTEs are increasing in the short-run. This behavior indicates that defendants whom almost all judges would punish are less likely to recidivate, while defendants who would be punished only by tough judges are more likely to recidivate.

100

Vitor Possebom @vitorpossebom.bsky.social · 27/11/2023

For inference, you can use the weighted bootstrap! Piece of cake! And we do show that everything is consistent and asymptotic normal! Now, it is time to estimate the effect of misdemeanor punishment on time-to-recidivism.

110

Vitor Possebom @vitorpossebom.bsky.social · 27/11/2023

We use a conditional local IV estimand to identify the distributional treatment responses. After that, we can get the DMTE and the QMTE. Our estimation procedure is a bit long, but super easy to implement! You only need to run a few logit models and take some averages!

120

Vitor Possebom @vitorpossebom.bsky.social · 27/11/2023

We do so by looking at the Distributional MTE and the Quantile MTE of time-to-recidivism, a continuous variable. We impose Random Assignment and Censoring. The last assumption imposes that the sentence date is independent of the defendant’s decision to commit another crime.

110

Vitor Possebom @vitorpossebom.bsky.social · 27/11/2023

To look at long-run recidivism, our Econometric tools need to appropriately address right-censoring. We also want to use the MTE to analyze heterogeneity with respect to the defendants’ punishment resistance. So we need to develop new tools combining MTE and duration outcomes!

110

Vitor Possebom @vitorpossebom.bsky.social · 27/11/2023

First, long-run recidivism matters in São Paulo, Brazil. A non-negligible share of recidivism events happens 6-8 years after the judge’s decision. So analyzing the effect of judges’ decision on long-run recidivism may matter when discussing sentencing guidelines.

110

Vitor Possebom @vitorpossebom.bsky.social · 27/11/2023

Misdemeanor punishment (fines) can have heterogeneous effects on recidivism depending on the defendants’ types and time horizon. We explore these sources of heterogeneity by looking at the marginal treatment effect of misdemeanor punishment on recidivism at many time horizons.

111

Vitor Possebom @vitorpossebom.bsky.social · 27/11/2023

🚨New Working Paper🚨 Was Javert right to be suspicious? Unpacking treatment effect heterogeneity of alternative sentences on time-to-recidivism in Brazil by Acerenza (scholar.google.com/citations?user…), Possebom and Sant’Anna (@pedrosantanna.bsky.social) Paper: arxiv.org/abs/2311.13969

2156

Reposted by Vitor Possebom

Michael Clemens @mclem.org · 14/11/2023

🚨 Call for Papers —Conference on the economics of migration in Latin America, Mar. 14–15 in Washington —Featuring top researchers @sandrarozo.bsky.social @dmckenzie.bsky.social @claireadida.bsky.social et al., run by HUMANS network of LACEA —With a keynote by me —Submissions due 🔜 December 15

2nd Call for Papers: Humans Lacea Network. Place and date: The conference will be held at the Headquarters of the World Bank in Washington DC on March 14 and 15, 2024. Keynote Speakers: Michael Clemens and Catalina Amuedo-Dorantes Panel with Expert Researchers: David McKenzie and Claire Adida Scientific Committee: Santiago Perez, Claire Adida, David McKenzie, Cynthia Van Der Werf, Ana Maria Ibafiez, Marcela Meléndez, Antonella Bandiera, and Sandra Rozo. The deadline for submitting complete papers is December 15, 2022. Full papers, in PDF format, should he submitted online via humanslacea@gmail.com. The authors of accepted papers will be notified by email on January 31st, 2023. There will be a dedicated discussant for each paper, as well as open floor discussion. Airfare and accommodations will be covered for up to one presenter of the selected papers. Founders of the network include Ana Maria Ibanez (Network head), Marcela Meléndez, Antonella Bandiera, and Sandra Rozo.

12525

Vitor Possebom @vitorpossebom.bsky.social · 09/11/2023

Sometimes, I think that journals do not know that many of its readers have eyesight problems... Elsevier's font size is so small and its line spacing is miniscule.

110

Vitor Possebom @vitorpossebom.bsky.social · 05/11/2023

QT with 10 of your favorite novels Ubirajara by Alencar Vidas Secas by Ramos Harry Potter and the Order of the Phoenix Assassin’s Apprentice by Hobb The Final Empire by Sanderson Percy Jackson and The Lightening Thief by Riordan I tried to focus on the novels that marked my life in some way.

000

Vitor Possebom @vitorpossebom.bsky.social · 05/11/2023

Following my theme of comparing academic and fictional writing, are there any similarities between economic papers and world building in fantasy? Are theory papers hard world building (LoTR)? Are empirical work more like soft world building (Narnia)? What about Econometrics?

010

Vitor Possebom @vitorpossebom.bsky.social · 04/11/2023

I like @peibich.bsky.social’s solution. I would also check the distribution of Z for men and women. If they differ, the weighted average of LATEs (I.e., your 2SLS) will be different, even if the underlying LATEs/MTE are the same.

130

Vitor Possebom @vitorpossebom.bsky.social · 03/11/2023

Probable Causation is an amazing podcast and this interview with Allison Stashko is awesome: open.spotify.com/episode/0rfq... They discuss the effect of newly elected prosecutors and police killings in the US. It is based on this paper: drive.google.com/file/d/1LwnA....

020

Reposted by Vitor Possebom

ᴅᴀɴɪᴇʟ ᴍɪʟʟɪᴍᴇᴛ ✡️☮️❤️ @dlmillimet.bsky.social · 03/11/2023

#EconSky 📉📈 Advances in Econometrics is putting together an issue on "Econometrics of Climate, Energy, and Green Transition" edited by Eric Hillebrand, Marina Friedrich, & @smueconomics.bsky.social's Tom Fomby. Paper submissions due Nov 30! Info at: tinyurl.com/py9n677y

097

Reposted by Vitor Possebom

John Mullahy @johnmullahy.bsky.social · 03/11/2023

If you're studying outcomes whose distributions resemble those in this picture then this new NBER working paper may be of interest. www.nber.org/papers/w31814

1122

Vitor Possebom @vitorpossebom.bsky.social · 02/11/2023

One of my pastimes is to watch videos about writing fiction. Many things that work when writing fiction also work when writing academic papers! I think this video on editing is quite useful: youtu.be/WLAmilJx3Us?.... E.g., accept that your manuscript will evolve a lot over time!

173

Reposted by Vitor Possebom

Paul Hünermund @p-hunermund.com · 02/11/2023

🙌 Our paper on "Natural Experiments: Missed Opportunities for Causal Inference in Psychology" just got accepted in Advances in Methods and Practices in Psychological Science (AMPPS). Thanks to @mp-grosz.bsky.social, @dingdingpeng.the100.ci & a great coauthor team. Pre-print: osf.io/preprints/ps...

24915

Reposted by Vitor Possebom

Jaap Abbring @jaap.abbring.org · 02/11/2023

Richard Blundell inaugurated Tilburg U's new Koopmans seminar series with a brilliant talk on wage paths, human capital formation, and labor market inequality, against the broad background of the IFS Deaton Review of inequality ifs.org.uk/inequality/ www.tilburguniversity.edu/current/news...

0102

Vitor Possebom @vitorpossebom.bsky.social · 01/11/2023

And both papers have super cool discussions on multi-valued treatment models with instruments. Both papers explain why this problem is much harder than the binary treatment problem! And both propose different solutions to it. I am still digesting them. But I learned a lot from both papers! [end]

010

Vitor Possebom @vitorpossebom.bsky.social · 01/11/2023

So, increasing leniency in the conviction margin while decreasing it in the incarceration margin may benefit society and defendants. But take this policy conclusion with a gigantic grain of salt. Recidivism, conviction and incarceration are very complicated topics with multiple dimensions. +

100

Vitor Possebom @vitorpossebom.bsky.social · 01/11/2023

Both find that conviction has criminogenic effects while incarceration decreases recidivism (through incapacitation). Kamat, Norris and Pecenco uses data from Ohio, while Humphries, Ouss, Stavreva, Stevenson and van Dijk uses data from Virginia. +

100

Vitor Possebom @vitorpossebom.bsky.social · 01/11/2023

Both papers are impressive, making contributions to the empirical literature of crime economics and to the theoretical literature of causal inference. On the empirical front, they are able to identify the effect of conviction against dismissal and the effect of incarceration against conviction. +

100

Vitor Possebom @vitorpossebom.bsky.social · 01/11/2023

Econometrics Thread (#EconSky): "The Effect of Conviction and Incarceration on Recidivism" Today, I want to talk about two recent working papers: - Kamat, Norris and Pecenco (2023): bit.ly/3QjqdbX - Humphries, Ouss, Stavreva, Stevenson and van Dijk (2023): bit.ly/3Mrrdtp +

130

Vitor Possebom @vitorpossebom.bsky.social · 28/10/2023

I second her recommendation about standing desk and good chairs.

010

Vitor Possebom @vitorpossebom.bsky.social · 28/10/2023

Based on discussion here (bsky.app/profile/vito...) and on Twitter, I decided to buy the Windows Surface Go. It can annotate PDFs, but it can also edit tex files and run simpler code scripts.

150

Reposted by Vitor Possebom

Aaron Sojourner @aaronsojourner.org · 27/10/2023

Over the last year consumer prices rose 3.9% on average. Individual workers experienced an average 6.8% increase in hourly wage. Half experienced wage increases of 5.2% or greater. 25% of workers saw their wages fall by 0.3% or worse. 25% saw their wages rise by 15.9% or more.

082

Vitor Possebom @vitorpossebom.bsky.social · 27/10/2023

Portuguese uses the same word for gym and academia. But what I discovered to love about going to the gym is the exact opposite of academic life. At the gym, reward is immediate. You finish your series and you are happy that you completed a task. But academic life is all about delayed gratification.

140

Reposted by Vitor Possebom

Climent Quintana-Domeque @climent.bsky.social · 26/10/2023

New #openaccess article in the Oxford Bulletin of Economics & Statistics: "Foetal Exposure to Air Pollution and Students' Cognitive Performance: Evidence from Agricultural Fires in Brazil" (by Juliana Carneiro, Matthew A. Cole & Eric Strobl) doi.org/10.1111/obes...

042

Vitor Possebom @vitorpossebom.bsky.social · 25/10/2023

I see. You went for the Surface Pro. I am leaning toward the Surface Go. The heaviest thing I will need it to do is edit and compile tex documents. My current laptop is heavy, but it runs regressions in a fast way. Its only problem is that using it in a small plane seat is hard.

100

Vitor Possebom @vitorpossebom.bsky.social · 25/10/2023

May I ask one extra question? What is your processor? Pentium 6500Y or Core i3?

100

Vitor Possebom @vitorpossebom.bsky.social · 24/10/2023

Thank you for the detailed analysis!

020