arXiv subjects

Robert F. Phillips

Publications and source records attributed to Robert F. Phillips.

5 recordsLinked to original sources

arXiv2024

A Simple Interactive Fixed Effects Estimator for Short Panels

We study the interactive effects (IE) model as an extension of the conventional additive effects (AE) model. For the AE model, the fixed effects estimator can be obtained by applying least squares to a regression that adds a linear projection of the fixed effect on the explanatory variables (Mundlak, 1978; Chamberlain, 1984). In this paper, we develop a novel estimator -- the projection-based IE (PIE) estimator -- for the IE model that is based on a similar approach. We show that, for the IE model, fixed effects estimators that have appeared in the literature are not equivalent to our PIE estimator, though both can be expressed as a generalized within estimator. Unlike the fixed effects estimators for the IE model, the PIE estimator is consistent for a fixed number of time periods with no restrictions on serial correlation or conditional heteroskedasticity in the errors. We also derive a statistic for testing the consistency of the two-way fixed effects estimator in the possible presence of iterative effects. Moreover, although the PIE estimator is the solution to a high-dimensional nonlinear least squares problem, we show that it can be computed by iterating between two steps, both of which have simple analytical solutions. The computational simplicity is an important advantage relative to other strategies that have been proposed for estimating the IE model for short panels. Finally, we compare the finite sample performance of IE estimators through simulations.

econ.EM↗

arXiv2024

Forward Orthogonal Deviations GMM and the Absence of Large Sample Bias

It is well known that generalized method of moments (GMM) estimators of dynamic panel data regressions can have significant bias when the number of time periods ($T$) is not small compared to the number of cross-sectional units ($n$). The bias is attributed to the use of many instrumental variables. This paper shows that if the maximum number of instrumental variables used in a period increases with $T$ at a rate slower than $T^{1/2}$, then GMM estimators that exploit the forward orthogonal deviations (FOD) transformation do not have asymptotic bias, regardless of how fast $T$ increases relative to $n$. This conclusion is specific to using the FOD transformation. A similar conclusion does not necessarily apply when other transformations are used to remove fixed effects. Monte Carlo evidence illustrating the analytical results is provided.

econ.EM↗

arXiv2019

A Comparison of First-Difference and Forward Orthogonal Deviations GMM

This paper provides a necessary and sufficient instruments condition assuring two-step generalized method of moments (GMM) based on the forward orthogonal deviations transformation is numerically equivalent to two-step GMM based on the first-difference transformation. The condition also tells us when system GMM, based on differencing, can be computed using forward orthogonal deviations. Additionally, it tells us when forward orthogonal deviations and differencing do not lead to the same GMM estimator. When estimators based on these two transformations differ, Monte Carlo simulations indicate that estimators based on forward orthogonal deviations have better finite sample properties than estimators based on differencing.

econ.EM↗

arXiv2018

Quantifying the Computational Advantage of Forward Orthogonal Deviations

Under suitable conditions, one-step generalized method of moments (GMM) based on the first-difference (FD) transformation is numerically equal to one-step GMM based on the forward orthogonal deviations (FOD) transformation. However, when the number of time periods ($T$) is not small, the FOD transformation requires less computational work. This paper shows that the computational complexity of the FD and FOD transformations increases with the number of individuals ($N$) linearly, but the computational complexity of the FOD transformation increases with $T$ at the rate $T^{4}$ increases, while the computational complexity of the FD transformation increases at the rate $T^{6}$ increases. Simulations illustrate that calculations exploiting the FOD transformation are performed orders of magnitude faster than those using the FD transformation. The results in the paper indicate that, when one-step GMM based on the FD and FOD transformations are the same, Monte Carlo experiments can be conducted much faster if the FOD version of the estimator is used.

econ.EM↗

arXiv2017

Quasi Maximum-Likelihood Estimation of Dynamic Panel Data Models

This paper establishes the almost sure convergence and asymptotic normality of levels and differenced quasi maximum-likelihood (QML) estimators of dynamic panel data models. The QML estimators are robust with respect to initial conditions, conditional and time-series heteroskedasticity, and misspecification of the log-likelihood. The paper also provides an ECME algorithm for calculating levels QML estimates. Finally, it uses Monte Carlo experiments to compare the finite sample performance of levels and differenced QML estimators, the differenced GMM estimator, and the system GMM estimator. In these experiments the QML estimators usually have smaller --- typically substantially smaller --- bias and root mean squared errors than the panel data GMM estimators.

math.ST↗