Affiliation:
Brunel University London
Contact:
Email: vasilis.sarafidis [the usual symbol] brunel.ac.uk
Research Field:
Econometric Theory and Practice, Panel Data Analysis, Spatial Models and Networks
What's new?
July 2025: Our paper on "Estimating Spatial Dynamic Panel Data Models with Unobserved Common Factors in Stata" is now available online. We introduce the spxtivdfreg package in Stata, which implements a general instrumental variables (IV) approach for estimating dynamic spatial panel data models with unobserved common factors or interactive effects, when the number of both cross-sectional and time series observations is large. The spxtivdfreg package allows for both homogeneous and heterogeneous slope coefficients. In addition, the spxtivdfreg package allows estimation of short-run and long-run direct and indirect effects.
June 2025: New research on "Heterogeneous Exposures to Systematic and Idiosyncratic Risk across Crypto Assets: A Divide-and-Conquer Approach". We analyse realized return behavior across a broad set of crypto assets by estimating heterogeneous exposures to idiosyncratic and systematic risk. A key challenge arises from the latent nature of broader economy-wide risk sources: macro-financial proxies are unavailable at high-frequencies, while the abundance of low-frequency candidates offers limited guidance on empirical relevance. To address this, we develop a novel two-stage ``divide-and-conquer'' approach. Details are available at the link provided.
June 2025: The program is now available for the upcoming conference on "Social and Sustainable Finance: Bridging Methods, Policy and Practice" taking place at Brunel University London on June 23–24, 2025. We look forward to welcoming participants to two days of engaging presentations and discussions, featuring keynote addresses by George Kapetanios and Steven Ongena! To view the program, click here.
May 2025: New research on "Residual Income Valuation and Stock Returns: Evidence from a Value-to-Price Investment Strategy". We hypothesize that sorting portfolios by the V/P ratio yields excess returns by capturing persistently undervalued firms. In the US market, high V/P portfolios outperform low V/P ones over one- to three-year horizons. The V/P ratio predicts future returns even after controlling for standard risk factors. Profitability and investment improve the explanatory power of the Fama-French model, particularly for stocks with V/P near 1, but fail to account fully for excess returns in years two and three, especially among high V/P stocks. These high V/P portfolios identify firms significantly mispriced relative to future investment and profitability growth.
February 2025: New research on "IV Estimation of Heterogeneous Spatial Dynamic Panel Models with Interactive Effects". The paper develops a Mean Group Instrumental Variables (MGIV) estimator for spatial dynamic panel data models with interactive effects, under large N and T asymptotics. Unlike existing approaches that typically impose slope-parameter homogeneity, MGIV accommodates cross-sectional heterogeneity in slope coefficients. The proposed estimator is linear, making it computationally efficient and robust. Furthermore, it avoids the incidental parameters problem, enabling asymptotically valid inferences without requiring bias correction.