Publications
-
Yu Bai, M. Marcellino, and G. Kapetanios. Mean group instrumental variable estimation of time-varying large heterogeneous panels with endogenous regressors. Econometrics and Statistics, forthcoming.
[link]
Abstract: The large heterogeneous panel data models are extended to the setting where the heterogenous coefficients are changing over time and the regressors are endogenous.
Kernel-based non-parametric time-varying parameter instrumental variable mean group (TVP-IV-MG) estimator is proposed for the time-varying cross-sectional mean coefficients.
The uniform consistency is shown and the pointwise asymptotic normality of the proposed estimator is derived. A data-driven bandwidth selection procedure is also proposed.
The finite sample performance of the proposed estimator is investigated through a Monte Carlo study and an empirical application on multi-country Phillips curve with time-varying parameters.
-
Yu Bai, A. Carriero, T. E. Clark, and M. Marcellino. Macroeconomic forecasting in a multi-country context. Journal of Applied Econometrics, 37(6), 1230-1255, 2022.
[link]
Abstract: In this paper, we propose a hierarchical shrinkage approach for multi-country VAR models. In implementation, we consider three different scale mixtures Normals priors and provide new theoretical results.
Empirically, we examine how model specifications and prior choices affect the forecasting performance for GDP growth, inflation, and a short-term interest rate for the G7 economies.
We find that hierarchical shrinkage, particularly as implemented with the Horseshoe prior, is very useful in forecasting inflation. It also has the best density forecast performance for output growth and the interest rate.
Multi-country models generally improve on the forecast accuracy of single-country models.
-
Yu Bai, S. Zhou, and Z. Fan. A Monte Carlo comparison of GMM and QMLE estimators for short dynamic panel data models with spatial errors. Journal of Statistical Computation and Simulation 88 (2), 376-409, 2018.
[link]
Pre-PhD work.
Working Papers
-
Yu Bai. Optimal forecasting under parameter instability. (2023, JMP)
[PDF] [Slides] [Link to video presentation]
An updated, cleaned version can be found here: [paper] [appendix].
Abstract: This paper considers the problem of using local estimator in a forecasting model which is affected by parameter instability. We first show that local estimator is consistent under various types of parameter instability.
Then, we analyse the choices of weighting function and tuning parameter associated with the local estimator. We prove the asymptotic optimality of the tuning parameter selection procedure and provide analytical criterion on the choice of weighting function.
The theoretical results are examined through an extensive Monte Carlo study and four empirical applications on forecasting inflation, growth and inflation shocks, house price changes and bond returns.
-
Yu Bai. Local GMM estimation for nonparametric time-varying coefficient moment condition models. (2023, Revision requested by JTSA)
[PDF]
Abstract: I develop a local continuously updated GMM estimator for nonparametric time-varying coefficient moment condition models. The uniform consistency rate and the pointwise asymptotic normality of the proposed estimator are derived.
The finite sample performance of the proposed estimator is investigated through a Monte Carlo study and an empirical application on asset pricing models with stochastic discount factor (SDF) representation.
Work in progress
