## On the Heterogeneity Bias of Pooled Estimators in Stationary VAR Specifications

_IMF Working Papers, April 1, 2003_

## Source details

**Canonical URL:** [On the Heterogeneity Bias of Pooled Estimators in Stationary VAR Specifications](https://www.imf.org/en/publications/wp/issues/2016/12/30/on-the-heterogeneity-bias-of-pooled-estimators-in-stationary-var-specifications-16356)

## Other formats

- [Markdown version](/en/publications/wp/issues/2016/12/30/on-the-heterogeneity-bias-of-pooled-estimators-in-stationary-var-specifications-16356/index.md)
- [Structured JSON version](/en/publications/wp/issues/2016/12/30/on-the-heterogeneity-bias-of-pooled-estimators-in-stationary-var-specifications-16356/index.json)
- [Bundle manifest](/en/publications/wp/issues/2016/12/30/on-the-heterogeneity-bias-of-pooled-estimators-in-stationary-var-specifications-16356/bundle-manifest.json)

## Bibliographic details
- Authors: Alessandro Rebucci
- Published: April 1, 2003
- Series: IMF Working Papers
- DOI: https://doi.org/10.5089/9781451849486.001

---

### Summary and research question
- Paper studies asymptotically the bias of the fixed effect (FE) estimator induced by cross-section heterogeneity in the slope parameters of stationary vector autoregressions (VARs).
- Also compares the FE, the mean group estimator (MG), and a simple instrumental variable alternative (IV) in Monte Carlo simulations.

### Main findings
- (i) Asymptotically, the heterogeneity bias of the FE may be more or less severe in VAR specifications than in standard dynamic panel data specifications.
- (ii) In Monte Carlo simulations, slope heterogeneity must be relatively high to be a source of concern for pooled estimators.
- (iii) When this happens, the panel must be longer than a typical macro dataset for the MG to be a viable solution.

### Methodology highlights
- Analytical asymptotic study of FE bias under cross-sectional slope heterogeneity in stationary VARs.
- Monte Carlo simulations to compare FE, MG, and a simple IV alternative across heterogeneity scenarios.

### Subject and keywords
- Subject: Vector autoregression, Vector error correction models
- Keywords: WP

---

## Content in this bundle

- **On the Heterogeneity Bias of Pooled Estimators in Stationary VAR Specifications - WP/03/73**
  - [On the Heterogeneity Bias of Pooled Estimators in Stationary VAR Specifications - WP/03/73 (Markdown version)](/-/media/websites/imf/imported-full-text-pdf/external/pubs/ft/wp/2003/_wp0373.pdf.md){rel="alternate" type="text/markdown"}
  - [On the Heterogeneity Bias of Pooled Estimators in Stationary VAR Specifications - WP/03/73 (PDF)](/-/media/websites/imf/imported-full-text-pdf/external/pubs/ft/wp/2003/_wp0373.pdf){rel="external" type="application/pdf"}

---

_Source: https://www.imf.org/en/publications/wp/issues/2016/12/30/on-the-heterogeneity-bias-of-pooled-estimators-in-stationary-var-specifications-16356_