2020 EC2 Program Now Posted

Looking great!

31th (EC)^2 Conference: High Dimensional Modeling in Time Series

December 11-12, 2020

Paris, France (Alas, virtually...)

Program, registration, etc. at http://ec2.essec.edu/

Classification Under Asymmetric Loss

I just read the stimulating new paper by Babii et al. on binary choice / classification w asymmetric loss, https://arxiv.org/abs/2010.08463.

It led me to recall some work of mine with Peter Christoffersen that may be related in interesting ways. The hyperlinked papers are below. We study optimal prediction under asy loss, focusing not only on how the amount of loss asymmetry drives the optimal bias (of course, as in Granger's seminal work), but also focusing on how heteroskedasticity​ (H), interacting with loss asymmetry, drives the optimal bias.  (The optimal bias increases as variance increases, and conversely.)  

We focus on time-series H, but of course cross section H is massively relevant as well, so I wonder how it would all work out in theory and practice in the Babii et al. cross-section classification environment.  Of course everyone talks about H destroying consistency in logit and related models, but that's deeper econometric consistency for marginal effects etc. I don't see why it would destroy consistency for the optimal prediction / classification, which is automatically induced by virtue of the estimation criterion as routinely exploited in the ML literature.

In any event the key recognition is that heteroskedasticity and asymmetric loss interact. Asymmetric loss of course influences the optimal prediction / classification, but it influences it more in regions (cross section) or periods (time series) where / when variance is high.

Christoffersen, P. and Diebold, F.X. (1997), "Optimal Prediction Under Asymmetric Loss," Econometric Theory, 13, 808-817.

Christoffersen, P.F. and Diebold, F.X. (1996), "Further Results on Forecasting and Model Selection Under Asymmetric Loss," Journal of Applied Econometrics, 11, 561-571.

(Somewhat) related earlier No Hesitations post:
https://fxdiebold.blogspot.com/search/label/Classification

Essie Maasoumi Econometric Theory Interview

Check it out here. So fine and so appropriate for Essie.

More generally, seeing the latest reminds me of the invaluable ET Interviews series. Piece-by-piece, thanks to the initiative of Peter Phillips at ET, it is assembling a history of modern econometric thought. May its future be as vibrant as its past!

See here for some background circa 2015.

Russian Holidays Predict Troll Activity 2015-2017

A fascinating new abstract. Timely too. 

Russian Holidays Predict Troll Activity 2015-2017 Douglas Almond, Xinming Du, and Alana Vogel #28035 Abstract: While international election interference is not new, Russia is credited with “industrializing” trolling on English-language social media platforms. In October 2018, Twitter retrospectively identified 2.9 million English-language tweets as covertly written by trolls from Russia's Internet Research Agency. Most active 2015-2017, these Russian trolls generally supported the Trump campaign (Senate Intelligence Committee, 2019) and researchers have traced how this content disseminated across Twitter. Here, we take a different tack and seek exogenous drivers of Russian troll activity. We find that trolling fell 35% on Russian holidays and to a lesser extent, when temperatures were cold in St. Petersburg. More recent trolls released by Twitter do not show any systematic relationship to holidays and temperature, although substantially fewer of these that have been made public to date. Our finding for the pre-2018 interference period may furnish a natural experiment for evaluati! ng the causal effect of Russian trolling on indirectly-affected outcomes and political behaviors — outcomes that are less traceable to troll content and potentially more important to policymakers than the direct dissemination activities previously studied. As a case in point, we describe suggestive evidence that Russian holidays impacted daily trading prices in 2016 election betting markets.

Econometrics / Machine Learning Interface

Check out this exciting new seminar series. Great initiative!

AMLEDS Seminar (Applied Machine Learning, Economics, and Data Science)

Serena Ng (Columbia University) will give the inaugural seminar. The discussion moderator is Michael McMahon (Oxford University).

Topic: "Methods for Analyzing Data with Missing Values and from New Sources"

13:00 EST time / 18:00 GMT time / 19:00 CET time, November 6, 2020. 

To register, and to learn more about AMLEDS, go to https://sites.google.com/view/amleds/home.

Factor Loadings and Network Connectedness

I have long been interested in using time-varying latent factor loadings for time-varying connectedness measurement. Patrick Gagliardini made great progress on time-varying loadings in his October 19 SoFiE talk, discussed by Seth Pruitt (recording etc, here).  

I want to relate time-varying latent factor loadings to the Diebold-Yilmaz connectedness measurement framework. Kelly et al. (2019) helps, showing how to empirically assess the correlation, if any, between time-varying factor loadings and time-varying DY network connectedness, by allowing loadings to depend on covariates like connectedness.

But what I really want is a "Rosetta Stone" giving a 1-1 translation between Patrick's "time-varying factor loadings" world and the DY "time varying network centrality" world. That's almost surely wishful thinking in general, but maybe under some (stringent) conditions?

PREDOC

Check out www.predoc.org.  It just launched.  Moving forward I think this will be a key clearinghouse for information for diverse undergrads seeking an economics "pre-doc" before potentially heading on for the Ph.D. Current members here, and growing daily, as are available predoc positions.

H. O. Stekler Research Program on Forecasting

November 5, 2020, 12:30 pm - 2 pm ET (Virtual): Launch event for the H. O. Stekler Research Program on Forecasting at George Washington University. Panelists will include Neil Ericsson, Fred Joutz, Prakash Loungani, and Tara Sinclair. Please email forecasting@gwu.edu to register (no cost) and receive a Zoom link to join the meeting online. 

60-Second Lecture

I hope you can join us...

60-Second Lectures | September 30, 2020

60-Second Lectures

Watch on Twitter and Facebook (@pennsas)

Wednesday, September 30, 2020 - Noon, Philadelphia time

Every spring and fall, Penn Arts & Sciences faculty take a minute to share their perspectives on a variety of topics. The theme for our talks this semester is “Social Institutions During Social Distancing.”

Social isolation, economic hardship, and questioning of our government and collective response to the pandemic has combined with reinvigorated demands for racial justice during these challenging times. These circumstances have led many of us to think more deeply about the glue that holds us together as a society. In this series we’ve asked faculty to share their observations on our social institutions, the role they play, and whether they’re working.

Faculty Speaker:
Entering the Pandemic: The Joint Progression of COVID-19 and Economic Growth in the U.S.
Francis Diebold, Paul F. and Warren Shafer Miller Professor Social Sciences and Professor of Economics, Finance, and Statistics

New Econometric Society Fellows

What a wonderful new crop for 2020.  Special congratulations to my Penn colleagues Dirk Krueger and Jesús Fernández-Villaverde!

September 22, 2020

www.econometricsociety.org

The Society is pleased to announce the election of 46 new Fellows of the Econometric Society. Manuel Amador, University of Minnesota Isaiah Andrews, Harvard University Raouf Boucekkine, Aix-Marseille Université Moshe Buchinsky, University of California, Los Angeles Aureo de Paula, University College London Melissa Dell, Harvard University Peter DeMarzo, Stanford University Habiba Djebbari, Aix-Marseille Université Matthias Doepke, Northwestern University Federico Echenique, California Institute of Technology Chris Edmond, University of Melbourne Joan María Esteban, Barcelona GSE Jesús Fernández-Villaverde, University of Pennsylvania Christopher J. Flinn, New York University Nicola Fuchs-Schündeln, Goethe University Frankfurt Alfred Galichon, New York University Paris Pierre-Olivier Gourinchas, University of California, Berkeley Kaddour Hadri, Queen’s University Belfast Marina Halac, Yale University Charles I. Jones, Stanford University Emir Kamenica, University of Chicago Greg Kaplan, University of Chicago Maxwell King, Monash University Dirk Krueger, University of Pennsylvania Gilat Levy, London School of Economics Francesca Molinari, Cornell University Massimo Morelli, Bocconi University Jessica Pan, National University of Singapore Alessandro Pavan, Northwestern University Thomas Philippon, New York University John K.H. Quah, Johns Hopkins University and National University of Singapore Imran Rasul, University College London Stephen J. Redding, Princeton University Ernesto Schargrodsky, Universidad Torcuato Di Tella Martin Schneider, Stanford University Carl Shapiro, University of California, Berkeley Margaret Slade, University of British Columbia Rodrigo Soares, Columbia University Chad Syverson, University of Chicago Adam Szeidl, Central European University Steve Tadelis, University of California, Berkeley Satoru Takahashi, National University of Singapore Fernando Vega-Redondo, Bocconi University Heidi Williams, Stanford University Steven R. Williams, University of Melbourne Muhamet Yildiz, Massachusetts Institute of Technology The Society is grateful for the work of its 2020 Fellows Nominating Committee (Liran Einav (Chair), Daron Acemoglu, Martin Cripps, Gabrielle Demange, Ignacio Lobato, Rosa Matzkin, and Hélène Rey) and for all the nominations initiated by its members.