Research
I currently focus on dynamic panel data models which allow for unobserved factors and network effects.
These models are relevant when the past affects the present, units influence each other (e.g. house prices in one city affect neighboring cities, what your friend does affects what you do etc.) and there are common unobserved shocks which affect everyone or a subset of the units.
Sample applications: house prices, unemployment, spread of behaviors on social networks, popularity of news topics and opinions in different regions of the country.
Double-Question Survey Measures for the Analysis of Financial Bubbles and Crashes
Joint work with Hashem Pesaran
Summary
We develop a novel type of survey indicator which can be used to measure and forecast financial bubbles and crashes. We show how the application of our indicator improves the out of sample forecast of house prices across US Metropolitan Statistical Areas when compared to traditionally used methods.
Academic Abstract
This article proposes a new double-question survey whereby an individual is presented with two sets of questions; one on beliefs about current asset values and another on price expectations. A theoretical asset pricing model with heterogeneous agents is advanced and the existence of a negative relationship between price expectations and asset valuations is established, and is then tested using survey results on equity, gold, and house prices. Leading indicators of bubbles and crashes are proposed and their potential value is illustrated in the context of a dynamic panel regression of realized house price changes across key Metropolitan Statistical Areas (MSAs) in the U.S. In an out-of-sample forecasting exercise, it is also shown that forecasts of house price changes (pooled across MSAs) that make use of bubble and crash indicators perform significantly better than a benchmark model that only uses lagged and expected house price changes. Supplementary materials for this article are available online.
Downloads
The manuscript and supplemental material (data, code, appendices) can be downloaded here.
Estimation of Peer Effects in Endogenous Social Networks: Control Function Approach
Joint work with Roger Moon
Summary
We propose a novel estimator of peer effects. Our estimator takes into account the fact that there may be unobserved characteristics which drive both link formation and behavior, which, if not taken into account, introduce bias into traditional types of peer effect estimators. We use a sieve semiparametric approach and establish asymptotics of the semiparametric estimator.
Academic Abstract
Estimation and Inference in Multivariate Spatiotemporal Models with Common Latent Factors
Joint work with Hashem Pesaran and Cynthia Fan Yang
Working paper
Summary
When analyzing processes which are correlated across space and time – such as house prices – it is important to take into account the fact that correlation might be induced by unobserved factors (common shocks) and “neighbor” effects (one unit affects another one). We propose a novel estimator which controls for both unobserved factors and spillover effects and apply it to forecasting house prices.
Academic Abstract
Coming soon
Downloads
Coming soon
Estimation and Inference for Spatial Models with Heterogeneous Coefficients in MATLAB, Python, R, and Stata
Joint work with Michele Aquaro, Federico Belotti and Giovanni Millo
Work in progress
The Informational Role of Housing Market Liquidity
Joint work with Michele Aquaro and Christian Badarinza
Work in progress
Spatial Equilibrium and Search Frictions – an Application to the New York Taxi Market
Working paper
Summary
Academic Abstract
This paper uses a dynamic spatial equilibrium model to analyze the effect of matching frictions and pricing policy on the spatial allocation of taxicabs and the aggregate number of taxi-passenger meetings. A spatial equilibrium model, in which meetings are frictionless but aggregate matching frictions can arise endogenously for certain parameter values, is calibrated using data on more than 45 million taxi rides in New York. It is shown how the set of equilibria changes for different pricing rules and different levels of aggregate market tightness, defined as the ratio of total supply to total demand. Finally, a novel data-driven algorithm for inferring unobserved demand from the data is proposed, and is applied to analyze how the relationship between demand and supply in a market with frictions compares to the frictionless equilibrium outcome.
Downloads
A Bayesian Comparison of Models of Network Formation
Working Paper