Indirect Inference for Dynamic Panel Models

By Christian Gouriéroux, Peter C. B. Phillips, Jun Yu. 2010

137 citations recorded by the source corpus.

Maximum likelihood (ML) estimation of the autoregressive parameter of a dynamic panel data model with fixed effects is inconsistent under fixed time series sample size and large cross section sample size asymptotics. This paper proposes a general, computationally inexpensive method of bias reduction that is based on indirect inference, shows unbiasedness and analyzes efficiency. Monte Carlo studies show that our procedure achieves substantial bias reductions with only mild increases in variance, thereby substantially reducing root mean square errors. The method is compared with certain consistent estimators and is shown to have superior finite sample properties to the generalized method of moment (GMM) and the bias-corrected ML estimator.

Subfields: Economics and Econometrics

View Paper: https://www.semanticscholar.org/paper/9260dfcf5dff9cc95cf57e5410ed9de0dc39abaf

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

1. Liangjun Su
2. Zhentao Shi
3. Peter C. B. Phillips
4. R. Poldermans
5. M. Pleus
6. Jan F. Kiviet
7. Sainan Jin
8. Xun Lu

Citations in the corpus

• Identifying Latent Structures in Panel Data (2016, methodology): “Other methods, such as median unbiased estimation, indirect inference (Gourieroux, Phillips, and Yu, 2010), and X-differencing (Han, Phillips, and Sul, 2014) have been used in dynamic panel data models to avoid bias problems.”
• Accuracy and Efficiency of Various GMM Inference Techniques in Dynamic Micro Panel Data Models (2017, background): “[20], Hayakawa [21], Dhaene and Jochmans [22], Flannery and Hankins [23], Everaert [24] and Kripfganz and Schwarz [25], this regressor is (weakly-)exogenous and most experiments just concern homoskedastic disturbances and stationarity regarding the impact of individual effects.”
• X-DIFFERENCING AND DYNAMIC PANEL MODEL ESTIMATION (2013, unknown): “Unlike the Hahn and Kuersteiner (2002) bias corrected LSDV estimator, the PFAE method does not require large T for consistency. The PFAE procedure also supersedes the Han and Phillips (2010) least squares method by generalizing it to AR(p) models and by considerably improving its efficiency both in ”
• In Search of Robust Methods for Dynamic Panel Data Models in Empirical Corporate Finance (2015, unknown): “…LSDVC) (Kiviet, 1995; Bruno, 2005), or approximate the bias function and search for unbiased estimates using an iterative bootstrap-based correction procedure (hereafter BC) (Everaert and Pozzi, 2007), or a simulation-based indirect inference method (hereafter II) (e.g., Gouriéroux et al., 2010).”