iiinova — where your digital self keeps evolving

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 20/10/2025

In our theory, we show how the estimator’s bias depends on product of imbalance across units, time and bias of the regression adjustment, so that effectively only one of these three needs to be small. This gives flexibility in the choice of unit, time weights and outcome model.

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 20/10/2025

This isn't surprising if it’s common that heterogeneity across units can be approximated with a few unobserved factors and the impact of each factor varies over time. This implies that we shouldn't assign the same weights to units far in time and we should accurately model interactive fixed effects.

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 20/10/2025

We find substantial heterogeneity in performance of common methods. TROP outperforms all competitors in 20 of 21 simulation designs. Empirically additive time and unit effects rarely capture all of the predictable patterns. Instead interactive latent factor structures often fit the data much better

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 20/10/2025

In contrast, TROP embeds all these estimators as special cases, while it learns which components of such estimators are most relevant to accurately predict the counterfactual. We evaluate TROP through a large set of simulation studies calibrated to match real-world applications.

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 20/10/2025

Why this matters: TROP learns the combination of time, unit weights and regression adjustments that most accurately predict the counterfactual as below. Common estimators of causal effects in panel data (DID/TWFE, SC, MC, SDID) rest on different assumptions, but all can fail in applications.

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 20/10/2025

TROP is “triply robust” – error is the product of the errors in the three components: imbalance betw/ treated and control periods, betw/ treated and control units and and misspecification of the regression adjustment (only one needs to perform well)

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 20/10/2025

TROP estimates causal effects in panel models by combining (i) a flexible outcome model (regularized low-rank factors + FE), (ii) unit weights, and (iii) time weights.

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 07/10/2025

New Paper Alert! Read the thread below for key takeaways from “Does Q&A Boost Engagement? Health Messaging Experiments in the United States and Ghana” by @erikakirgios.bsky.social @susanathey.bsky.social @angeladuckworth.bsky.social et al.

000

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 03/10/2025

During the @gsb.stanford.edu 100 Faculty Celebration of Scholarship @susanathey.bsky.social highlighted the GSB’s proud tradition of synergy between business and practice during her presentation. Listen to her thoughts and more in the podcast: stanford.io/3K8mcrz

stanford.io

A Century of Impact

In 1925, Herbert Hoover, a Stanford alum and future U.S. president, had an idea. “A graduate School of Business Administration is urgently needed upon the Pacific Coast,” he wrote.

000

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 24/09/2025

Earlier this month @susanathey.bsky.social joined Stanford University President Levin, @siepr.bsky.social Director @nealemahoney.bsky.social and other distinguished faculty to connect over cutting-edge research developments at Stanford Open Minds New York.

162

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 27/08/2025

Listen to Raj Chetty talk about how surrogate indices make it possible to make decisions more quickly using multiple short-term outcomes to predict long-term effects with @nber.org www.nber.org/research/vid...

161

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 22/08/2025

Check out @susanathey.bsky.social’s interview on how AI-powered after-the-fact quality checks boost driver performance at Uber—and what it means when AI can track compliance. Insights via @StanfordGSB. www.gsb.stanford.edu/insights/how...

gsb.stanford.edu

How Uber Steers Its Drivers Toward Better Performance

143

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 18/07/2025

“Governments will play a key role…in whether we actually develop the technology that will help lower-skilled workers become more productive by using AI to augment them with expertise that previously was difficult to acquire.”

132

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 15/07/2025

The talk will cover: ✔️How AI is altering industry dynamics & structures ✔️How these shifts will impact public services such as health and education ✔️How AI market concentration could tax the global economy ✔️Why govt policy will be crucial in shaping AI competition and innovation

000

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 15/07/2025

AI & digitisation are rapidly reshaping the way we work. Policymakers need to understand how, and what to do about it. Watch @Susan_Athey speak to G20 leaders about these issues tomorrow 16 July @ 13:30 CET. #G20SouthAfrica bit.ly/3GyMFgm or bit.ly/44PTXFP

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 30/06/2025

Beyond predictions, @keyonv.bsky.social also worked with @gsbsilab.bsky.social to show how these models can be used to make better estimations of important problems, such as the gender wage gap among men and women with the same career histories. Learn more here: bsky.app/profile/gsbs...

000

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 30/06/2025

If we know someone’s career history, how well can we predict which jobs they’ll have next? Read our profile of @keyonv.bsky.social to learn how ML models can be used to predict workers’ career trajectories & better understand labor markets. medium.com/@gsb_silab/k...

medium.com

Keyon Vafa: Predicting Workers’ Career Trajectories to Better Understand Labor Markets

If we know someone’s career history, how well can we predict which job they’ll have next?

192

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 30/06/2025

Analyzing representations tells us where history explains the gap. Ex: there are two kinds of managers: those who used to be engineers and those who didn’t. The first group gets paid more and has more males than the second. Models that don’t use history omit this distinction.

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 30/06/2025

We use these methods to estimate wage gaps adjusted for full job history, following the literature on gender wage gaps. History explains a substantial fraction of the remaining wage gap when compared to simpler methods. But there’s still a lot that history can’t account for.

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 30/06/2025

This result motivates new fine-tuning strategies. We consider 3 strategies similar to methods from the causal estimation literature. E.g. optimize representations to predict the *difference* in male-female wages instead of individual wages. All perform well on synthetic data.

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 30/06/2025

Two extremes: A representation that's just the identity function meets condition (1) trivially but not (2). A representation that uses a very simple summary of history (e.g. # of years worked) should meet (2) but fails (1)

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 30/06/2025

New result: Fast + consistent estimates are possible even if a representation drops info Two main fine-tuning conditions: 1. Representation only drops info that isn't correlated w/ both wage & gender 2. Representation is simple enough that it’s easy to model wage & gender from it

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 30/06/2025

Intuition: If working in job X at some point has a small effect on wages, but men are much likelier to have worked in job X than women, it may be omitted by a model optimized to predict wage.

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 30/06/2025

Foundation models are usually fine-tuned to make predictions (like wages). But representations fine-tuned this way can induce omitted variable bias: the gap adjusted for full history can be different from the gap adjusted for the representation of job history.

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 30/06/2025

We use CAREER, a foundation model of job histories. It’s pretrained on resumes but its representations can be fine-tuned on the smaller datasets used to estimate wage gaps.

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 30/06/2025

But this discards information that’s relevant to the wage gap. In contrast, foundation models learn *representations*: lower-dimensional variables that summarize information.

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 30/06/2025

Consider estimating the wage gap explained by differences in job history. Job history is high-dimensional since there are many possible sequences of jobs. So most economic models describe histories using hand-selected summary stats (e.g., # of years worked).

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 30/06/2025

Decompositions can inform policy: a large explained gender wage gap can suggest differences in choices or opportunities earlier in a worker’s career, while an unexplained gap may arise due to differences in factors such as skill, care responsibilities, or bargaining.

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 30/06/2025

Ex.: estimating the gender wage gap between men & women with the same job histories. A large literature decomposes wage gaps into two parts: the part “explained” by gender gaps in observed characteristics (e.g. education, experience), and the part that’s “unexplained.”

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 30/06/2025

Foundation models make great predictions. How should we use them for estimation problems in social science? New PNAS paper @susanathey.bsky.social & @keyonv.bsky.social & @Blei Lab: Bad news: Good predictions ≠ good estimates. Good news: Good estimates possible by fine-tuning models differently 🧵

183

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 22/05/2025

Takeaway 2: Our experiment isolates the effect for the least employable learners from credibly and systematically informing employers about online credentials. The positive finding helps build a case that such credentials may be good investments for workers seeking to transition jobs

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 22/05/2025

Takeaway 1: Online learning platforms and professional networking sites (e.g., LinkedIn) can boost job outcomes with simple features. Even light nudges to encourage skill signaling (like sharing a certificate) can improve employment prospects

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 22/05/2025

Who benefited most? The boost was greatest for learners with the lowest initial job prospects

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 22/05/2025

Nor were the gains simply from sprucing up profiles. Treated learners’ LinkedIn pages weren’t more complete or active than the control group’s. This suggests it was the certificate signal itself – not a general profile update – that made the difference

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 22/05/2025

We checked that this isn’t just a fluke of LinkedIn activity. The results held even after excluding any “new” jobs that started within 4 months of the intervention (to ensure we only count jobs found after the credential was shared)

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 22/05/2025

And it paid off: nudged learners were ~6% more likely to land a new job within a year than the control group. They were also ~9% more likely to have a job in the same field as their certificate

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 22/05/2025

To dive deeper, we looked closer at the subsample of ~40K learners who were LinkedIn users before the experiment. They were 17% more likely to add their certificate to LinkedIn if they received the treatment. Their profiles also saw more views, signaling higher interest from potential employers

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 22/05/2025

After learners earned a certificate, we randomly assigned a subset to the treatment group who got a prompt to easily add their new credential to LinkedIn. The nudge worked. Treated learners added credentials to their LinkedIn accounts, and these certificates received visits from LinkedIn

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 22/05/2025

We ran a global, randomized trial with ~800,000 Coursera learners who had earned certificates, and who either came from a developing country or had no college degree. Do they get more jobs if they link to their (verified) Coursera certificate on LinkedIn?

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 22/05/2025

Online course certificates (from MOOCs) are booming (40M+ learners in 2024). But do these credentials actually help people get jobs? Our team investigated this in a new study by @susanathey.bsky.social & Emil Palikot 👇.

187

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 22/05/2025

100

Golub Capital Social Impact Lab @gsbsilab.bsky.social · 22/05/2025

100