Efficient estimation of models for dynamic panel data

Ahn, Seung C.; Schmidt, Peter

doi:10.1016/0304-4076(94)01641-c

Cited by 796 publications

(565 citation statements)

References 15 publications

Supporting

Mentioning

547

Contrasting

Unclassified

Order By: Relevance

“…As we do not expect wages and capital to be strictly exogenous in our employment application, we focus here on moment conditions of the type E(u GR y G R\ )"0 and E(u GR x G R\ )"0. Stricter exogeneity restrictions on the x GR would allow the use of further instruments, as detailed in Arellano and Bond (1991), Ahn and Schmidt (1995) and Arellano and Bover (1995). For the same reason we do not consider conditional GLS results here.…”

Section: The Modelmentioning

confidence: 99%

Initial conditions and moment restrictions in dynamic panel data models

Blundell

Bond

1998

Journal of Econometrics

18,246

116

10,784

View full text Add to dashboard Cite

Estimation of the dynamic error components model is considered using two alternative linear estimators that are designed to improve the properties of the standard firstdifferenced GMM estimator. Both estimators require restrictions on the initial conditions process. Asymptotic efficiency comparisons and Monte Carlo simulations for the simple AR(1) model demonstrate the dramatic improvement in performance of the proposed estimators compared to the usual first-differenced GMM estimator, and compared to non-linear GMM. The importance of these results is illustrated in an application to the estimation of a labour demand model using company panel data.1998 Elsevier Science S.A. All rights reserved. JEL classification: C23

show abstract

Section: The Modelmentioning

confidence: 99%

Initial conditions and moment restrictions in dynamic panel data models

Blundell

Bond

1998

Journal of Econometrics

18,246

116

10,784

View full text Add to dashboard Cite

show abstract

“…which shows that Var (-?= Yl'i=-i 13^=1 (^®^o"io)^0~''(^)-^^^t herefore follows that (15) is Op (1) Lemma 3 Let ya he generated by (1 The last line of the display follows by Cesaro summability and stationarity. The second part of the theorem follows from Lemma (4) which implies that /C(ii,f2) = for all ii and i2-…”

Section: =1mentioning

confidence: 90%

Asymptotically Unbiased Inference for a Dynamic Panel Model with Fixed Effects when Both n and T Are Large

2002

View full text Add to dashboard Cite

We consider a dynamic panel AR(1) model with fixed effects when both n and T are large. Under the "T fixed n large" asymptotic approximation, the maximum likelihood estimator is known to be inconsistent due to the well-known incidental peirameter problem. We consider an alternative asymptotic approximation where n and T grow at the same rate. It is shown that, although the MLE is asymptotically biased, a relatively simple fix to the MLE results in an asymptotically unbiased estimator. The bias corrected MLE is shown to be asymptotically efficient by a Hajek type convolution theorem.

show abstract

“…To describe the intuition behind this result, we consider the AR(1) 12 The reason why we consider the GMM estimator using z it (1) as instruments is that, in terms of MAE, the GMM estimator may perform better than the IV estimator since the GMM estimator is more efficient than the IV estimator under large N and fixed T asymptotics. Also, the reason why we choose = 1 is that the IV estimator with = 1 performs best as will be shown.…”

Section: Monte Carlo Simulationmentioning

confidence: 99%

“…1 However, since the IV estimator is not generally efficient, Holtz-Eakin, Newey, and Rosen (1988) and Arellano and Bond (1991) proposed to use the generalized method of moments (GMM) estimator to improve efficiency. The GMM estimator has subsequently been refined in a number of studies, including Arellano and Bover (1995), Schmidt (1995, 1997) and Blundell and Bond (1998).…”

Section: Introductionmentioning

confidence: 99%

A SIMPLE EFFICIENT INSTRUMENTAL VARIABLE ESTIMATOR FOR PANEL AR(p) MODELS WHEN BOTHNANDTARE LARGE

Hayakawa¹

2009

Econom. Theory

View full text Add to dashboard Cite

In this paper, we show that for panel AR(p) models, an instrumental variable (IV) estimator with instruments deviated from past means has the same asymptotic distribution as the infeasible optimal IV estimator when both N and T , the dimensions of the cross section and the time series, are large. If we assume that the errors are normally distributed, the asymptotic variance of the proposed IV estimator is shown to attain the lower bound when both N and T are large. A simulation study is conducted to assess the estimator.Keywords: panel AR(p) models, the optimal instruments, instruments deviated from past means.

show abstract

Efficient estimation of models for dynamic panel data

Cited by 796 publications

References 15 publications

Initial conditions and moment restrictions in dynamic panel data models

Initial conditions and moment restrictions in dynamic panel data models

Asymptotically Unbiased Inference for a Dynamic Panel Model with Fixed Effects when Both n and T Are Large

A SIMPLE EFFICIENT INSTRUMENTAL VARIABLE ESTIMATOR FOR PANEL AR(p) MODELS WHEN BOTHNANDTARE LARGE

Contact Info

Product

Resources

About