Vladislav Morozov

Link to notes (new sections 11-14):
vladislav-morozov.github.io/econometrics...

Source repo: github.com/vladislav-mo...

My favorite result in this block:

Even with just 2 periods of data, you can identify average causal effects, even if people differ in infinitely many unobserved ways and the outcome function is completely unrestricted.

That's the power of panel data.

Beyond linearity:
What can we still learn when we don’t restrict functional form and allow arbitrarily rich unobserved heterogeneity?

This new section covers:
• A gentle intro
• Heterogeneity bias
• Average effects via panel data
• Stayers and why they matter
• Local polynomial regression

Just added a new section to my graduate lecture notes — on nonparametric models with unobserved heterogeneity.

It includes one of my favorite identification results in all of econometrics.

Why I Switched from Beamer to Quarto Reveal.js for My Presentations Why I switched from Beamer to Quarto Reveal.js for reproducible, maintainable, and portable slides in teaching, research, and data science.

Wrote a short post with details about why it happened and what I like.

vladislav-morozov.github.io/blog/web/qua...

I version-control everything with Git, sync and deploy via GitHub, and present directly from a browser.

It’s reproducible, portable, and just works.

Executable slides: code runs during render, outputs (plots, tables) are embedded automatically.

Simple syntax, responsive HTML, and interactive options too.

I’ve stopped using LaTeX Beamer for slides.

All my research and teaching presentations are now Quarto Reveal.js, and I feel very happy about it.

#EconSky #DataSky

Lecture notes here: (new sections are 7-10)

vladislav-morozov.github.io/econometrics...

Or

github.com/vladislav-mo...

The main idea: you can identify the full distribution of effects almost as easily as the average!

But these results aren’t widely used — maybe because the original treatment is pretty dense. I tried to make them more accessible via a clean special case.

Just uploaded the second big chunk of my lecture notes on linear models with heterogeneous coefficients! The notes for this topic are now complete.

This new section goes beyond average effects — to the variance and full distribution of heterogeneous coefficients.

Sorry, missed it! Maybe for some very tractable models?

Otherwise, only the usual characterization for misspecified likelihood: that you are estimating the parameter that minimizes the KL-divergence between the true model and the specified one

I usually find it hard to interpret those...

Why Simultaneous (Joint) Tests Instead of Adjusted Multiple Tests? Why simultaneous hypothesis tests are better — but not always — than adjusted multiple tests

Post link: vladislav-morozov.github.io/blog/statist...

Code link: github.com/vladislav-mo...

Turns out, the answer is only mostly right:

1. Yes, adjusted multiple testing can lead to a huge loss of power.

2. Surprisingly, in some cases, simultaneous testing actually performs worse (though only slightly).

Got the same question every time teaching testing in multivariate regression:

"Why a new tests for joint hypotheses? Why not multiple t-tests with adjustment?"

Usual answer: "because power" — always felt vague. I decided to check and wrote a post. (1/3)

#EconSky

Two-Way Fixed Effects Estimators with Heterogeneous Treatment Effects (September 2020) - Linear regressions with period and group fixed effects are widely used to estimate treatment effects. We show that they estimate weighted sums of the average treatment effects (ATE)...

Very true! Comes down to what you care about.

As an aside, if you drop linearity of the model, OLS — fixed effects models in this case — can give you "bad" weighted averages with potentially negative weights.
Then you really don't have a nice estimand.

www.aeaweb.org/articles?id=...

If a researcher
1. Knows that the effect is non-negative
2. Thinks that the within regression is targeting the ATE,

they will conclude that that there is no effect.

Even if M is very large and there are many people with β_i = M, so you would have a strong effect from intervening on x.

A simple example: suppose that you have two periods, one covariate x_{it}, and two types for β: some crazy big number M and 0.
1. Units with positive β do not change x.
2. Units with β=0 change x.

The estimand of the within regression is 0, regardless of the proportions of the types and M.

Good point!

It is a perfectly fine estimand under a linear model — a convex average of individual effects.

The problem is in (economic) practice: people often interpret that as the genuine ATE. Then one may draw wrong conclusions — this effect can have the opposite sign from the ATE.

Link: vladislav-morozov.github.io/econometrics...

I have learned a lot much from others openly sharing their specialized materials.

It's only fair to offer my epsilon as well and I hope these materials can serve someone.

Just uploaded the first block of my lecture notes on econometrics with unobserved heterogeneity! 📊

Introduction and a block on average effects in linear models with heterogeneous coefficients — why standard estimators fail and a robust approach.

Link below.

#econsky

Econometrica | Econometric Society Journal | Wiley Online Library Firms are more productive, on average, in larger cities. Two main explanations have been offered: firm selection (larger cities toughen competition, allowing only the most productive to survive) and ....

Example with productivity: onlinelibrary.wiley.com/doi/abs/10.3...

Example with worker skills:
academic.oup.com/restud/artic...

The Jochmans and Weidner paper above cites some more examples.

Inference on a Distribution from Noisy Draws We consider a situation where the distribution of a random variable is being estimated by the empirical distribution of noisy measurements of that variable. This is common practice in, for example, te...

I dunno if it's what you mean, but some other examples are:
1. Firm-level productivity (TFP)
2. Worker skills
3. Teacher value added.

You may care about their distribution, but you have to estimate all these (with noise).

A paper on working with such estimates:
arxiv.org/abs/1803.049...

Honestly? Everything just works. It’s fast, integrates with Zotero, and fits my workflow way better.

Still figuring out the best setup, but I'll document it when I find a winning approach.

Beamer slides? Slow and buggy.
Code integration? A hassle and no execution.
PDFs? Static and clunky.

I need something more flexible. So I switched:

➜ Quarto for structured notes & presentations.
➜ Obsidian for research, coding, project management, & language learning.

A humorous error message showing how I am giving up on LaTeX.

I think I’m done with LaTeX for anything except writing paper manuscripts.

I used to take all my notes in LaTeX — research papers, study notes, presentations, even language learning.

But it’s just too rigid, too slow, and too annoying for most of what I do.

#EconSky

Why Adding Fixed Effects May Increase Bias Why adding (more) fixed effects is not a silver bullet for the problem of unobserved heterogeneity and 3 things you can do about it.

Post: vladislav-morozov.github.io/blog/statist...

Code: github.com/vladislav-mo...

Adding fixed effects is supposed to reduce bias — but under realistic parameter heterogeneity, it can make bias worse

I wrote a post explaining how and why this can happen, with simulations and what you can do about it

(Video: results summary)

Links to post and Python code in replies

#EconSky

Researcher: "We let the data speak for itself."

Earlier that day: