Lightnews — Scholar-powered news

CJ Libassi @clibassi.bsky.social · 1d

Ultimately, we think these findings make a strong case for increased research & policy attention to understand which aspects of the transition may be most amenable to policy intervention. Lots more detail in the paper, hope you’ll give it a read! 10/10

CJ Libassi @clibassi.bsky.social · 1d

Our descriptive evidence is consistent w/ intuitive conclusion: low-SES grads appear disadvantaged in the first job transition, regardless of the broader economic context, and this has consequences for earnings gaps years later. 9/

1

CJ Libassi @clibassi.bsky.social · 1d

Overall, we find that diffs in first job transitions can explain *nearly two-thirds* of the year 5 residual earnings gap between high- and low-SES graduates (i.e., the gap that remains after controlling for other observable differences at graduation, including major, GPA, test scores, etc.) 8/

Horizontal bar chart showing how controlling for first job characteristics reduces earnings gaps between low- and high-socioeconomic status college graduates five years after graduation. Three horizontal bars extend leftward from zero, representing negative dollar amounts. The top gray bar shows an initial gap of $4,948 for observably similar graduates. The middle gray bar shows the gap reduced to $2,251 after controlling for first job salary, with a horizontal bracket and whiskers indicating a 55% reduction. The bottom blue bar shows the gap further reduced to $1,716 after controlling for all first job features, with a second horizontal bracket indicating a 65% reduction from the middle bar. Title states 'The Role of First Job Transitions in Explaining Earnings Gaps for Similar Low- vs. High-SES Grads, Five Years After Graduation.' Subtitle indicates data is from traditionally aged BA graduates from 2010-17 from a large urban public university system. X-axis shows dollar amounts from -$5,000 to $0.

1 1

CJ Libassi @clibassi.bsky.social · 1d

Interestingly, the SES gap in the first firm’s *average* pay is substantially bigger than the SES gap in grads’ own starting salaries (even in percentage terms). In other words, low-SES grads start out at firms where they may have less “room to grow” 7/

1

CJ Libassi @clibassi.bsky.social · 1d

Descriptively, low SES-grads are less likely to have already started working with their first post-college employer prior to graduation (34% vs. 40%), have lower starting salaries ($38K vs $43K) and work at lower-paying firms ($53K average vs $64K average) than high-SES grads 6/

1

CJ Libassi @clibassi.bsky.social · 1d

To describe first job transitions, we look at time to first job, starting salary, industry, industry-major match, firm size and average pay (and a few other things too) - these are all predictive of earnings at year five 5/

1

CJ Libassi @clibassi.bsky.social · 1d

We don’t examine these constraints directly, but begin by documenting large SES gaps in post-college earnings: even after controlling for a ton of other info on students’ background and grades, high-SES grads earn almost $5,000 (8%) more than similar low-SES grads five years post-grad 4/

1

CJ Libassi @clibassi.bsky.social · 1d

But what if some groups have persistently rockier transitions to the labor market, even in boom times? E.g. what if low-SES students struggle more to land a good first job, not b/c of their school, major, or grades, but b/c informational, financial, or structural constraints get in the way? 3/

1

CJ Libassi @clibassi.bsky.social · 1d

Context: While earnings bump for BAs remains strong, unemployment for recent grads has risen faster than other groups since 2022. Rigorous research shows economic conditions at graduation have long-run impacts, in part b/c it affects quality of grads’ first jobs 2/ www.newyorkfed.org/research/col...

The Labor Market for Recent College Graduates

Data on employment outcomes for new graduates and young workers.

www.newyorkfed.org

1

CJ Libassi @clibassi.bsky.social · 1d

🧵 New working paper! In joint work w/ @jscottclayton.bsky.social, Veronica Minaya, & Joshua Thomas, we use admin data from a large public univ system to examine earnings gaps for high- vs low-SES college grads 5 years out & the role of first jobs in explaining the gaps. 1/ www.nber.org/papers/w34366

Who Rides Out the Storm? The Immediate Post-College Transition and its Role in Socioeconomic Earnings Gaps

Founded in 1920, the NBER is a private, non-profit, non-partisan organization dedicated to conducting economic research and to disseminating research findings among academics, public policy makers, an...

www.nber.org

1 7 19

Reposted by CJ Libassi

Catherine Rampell @crampell.bsky.social · 14d

Whoa, White House withdraws Trump’s controversial nominee to lead BLS after ousting predecessor over jobs data
www.cnn.com/2025/09/30/p...

White House withdraws Trump’s controversial nominee to lead BLS after ousting predecessor over jobs data | CNN Politics

The White House has sent paperwork to the Senate to withdraw the nomination of E.J. Antoni as head of the Bureau of Labor Statistics, three sources told CNN.

www.cnn.com

23 110 550

CJ Libassi @clibassi.bsky.social · 19d

How about this? drive.google.com/file/d/1QdMA...

Unarchiver was able to get it to extract for me.

drive.google.com

CJ Libassi @clibassi.bsky.social · 19d

Blast! I may have it on an old external hard drive - I can check later tonight

1

CJ Libassi @clibassi.bsky.social · 19d

Does the file at this link work for you? web.archive.org/web/20210213...

web.archive.org

1

Reposted by CJ Libassi

Ben Zipperer @benzipperer.org · Aug 27

one amazing feature here is simply loading the entire dataset would probably freeze your laptop!

instead you can run this regression quickly and not worry about memory problems, thanks to the magic of duckdb and dbreg

Grant McDermott @gmcd.bsky.social · Aug 25

To borrow another example, taken from the `dbreg` README: github.com/grantmcdermo...

Here I am running a fixed-effects regression on 180 million(!) row parquet dataset... and it completes **< 2 seconds**... on my laptop 🤯

This is powered by @duckdb.org under the hood.

#rstats #econsky

Running dbreg::dbreg() on a full year of NYC taxi data... and it takes less than 2 seconds.

dbreg(
tip_amount ~ fare_amount + passenger_count | month + vendor_name,
path = "read_parquet('nyc-taxi/**/*.parquet')", ## path to hive-partitioned dataset
vcov = "hc1"
)
#> [dbreg] Estimating compression ratio...
#> [dbreg] Data has 178,544,324 rows and 24 unique FE groups.
#> [dbreg] Using strategy: compress
#> [dbreg] Executing compress strategy SQL
#>
#> Compressed OLS estimation, Dep. Var.: tip_amount
#> Observations.: 178,544,324 (original) | 70,782 (compressed)
#> Standard Errors: Heteroskedasticity-robust
#> Estimate Std. Error t value Pr(>|t|)
#> fare_amount 0.106744 0.000068 1564.742 < 2.2e-16 ***
#> passenger_count -0.029086 0.000106 -273.866 < 2.2e-16 ***
#> ---
#> Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

1 5 24

CJ Libassi @clibassi.bsky.social · Aug 20

Anyone know if anyone is doing any formal benchmarking of LLM performance on Stata tasks? www.statalist.org/forums/forum...

Anyone running benchmarks across LLMs for Stata skill? - Statalist

Curious if anyone has already tried comparing how well different LLMs perform on Stata coding tasks—not just casually, but using formal benchmarks. I’m

www.statalist.org

CJ Libassi @clibassi.bsky.social · Aug 18

Certainly not arguing the status quo (where all sorts of award letter shenanigans can and do occur) is optimal, but just as a matter of calculation, how would you calculate the value of IDR, PSLF, borrower protections such as hardship forbearances, in school deferments, closed school discharge, etc.

1 1

CJ Libassi @clibassi.bsky.social · Aug 16

Thanks for all you do for this package!

1

Reposted by CJ Libassi

Alex @s3alfisc.bsky.social · Aug 16

Vis method for decomposition now merged to main, feedback welcome!

2 1 6

CJ Libassi @clibassi.bsky.social · Aug 12

Also could it handle “negative” contributions (variables that increase the coefficient) in a way that is visually intuitive?

1

CJ Libassi @clibassi.bsky.social · Aug 12

This looks great!! Think it would scale well to many covariates?

1 1

CJ Libassi @clibassi.bsky.social · Aug 12

Man, when @dieworkwear.bsky.social weighs in on EJ Antoni's outfits, it may shake the earth.

1

Reposted by CJ Libassi

Erika McEntarfer @erikamcentarfer.bsky.social · Aug 2

It has been the honor of my life to serve as Commissioner of BLS alongside the many dedicated civil servants tasked with measuring a vast and dynamic economy. It is vital and important work and I thank them for their service to this nation.

1.2K 4.4K 22K

Reposted by CJ Libassi

COPAFS @copafs.bsky.social · Aug 2

AEA Statement on Dismissal of BLS Comm.

"The independence of the federal statistical agencies is essential to the proper functioning of a modern economy. Accurate, timely, and impartial statistics are the foundation upon which households, businesses, and policymakers make critical decisions."

3 110 200

CJ Libassi @clibassi.bsky.social · Jul 31

Thanks for maintaining it! Was very grateful to see that it was part of pyfixest.

1