## Limited Information Bayesian Model Averaging for Dynamic Panels with An Application to a Trade Gravity Model

_IMF Working Papers, October 1, 2011_

## Source details

**Canonical URL:** [Limited Information Bayesian Model Averaging for Dynamic Panels with An Application to a Trade Gravity Model](https://www.imf.org/en/publications/wp/issues/2016/12/31/limited-information-bayesian-model-averaging-for-dynamic-panels-with-an-application-to-a-25270)

## Other formats

- [Markdown version](/en/publications/wp/issues/2016/12/31/limited-information-bayesian-model-averaging-for-dynamic-panels-with-an-application-to-a-25270/index.md)
- [Structured JSON version](/en/publications/wp/issues/2016/12/31/limited-information-bayesian-model-averaging-for-dynamic-panels-with-an-application-to-a-25270/index.json)
- [Bundle manifest](/en/publications/wp/issues/2016/12/31/limited-information-bayesian-model-averaging-for-dynamic-panels-with-an-application-to-a-25270/bundle-manifest.json)

## Bibliographic details
- Authors: Huigang Chen, Alin T Mirestean, Charalambos G Tsangarides
- Published: October 1, 2011
- Series: IMF Working Papers
- DOI: https://doi.org/10.5089/9781463921309.001

---

### Overview and contribution
- Extends the Bayesian Model Averaging framework to panel data models where the lagged dependent variable as well as endogenous variables appear as regressors.
- Proposes a Limited Information Bayesian Model Averaging (LIBMA) methodology.
- Illustrates LIBMA with an application to the estimation of a dynamic gravity model for bilateral trade.

### Methodology
- Limited Information Bayesian Model Averaging (LIBMA) designed for short dynamic panel data models with endogenous regressors and model uncertainty.
- Tests LIBMA using simulated data.

### Key findings from simulations
- Simulation results suggest that asymptotically the methodology performs well both in Bayesian model averaging and selection.
- LIBMA recovers the data generating process well.
- LIBMA yields high posterior inclusion probabilities for all the relevant regressors.
- Parameter estimates from LIBMA are very close to their true values.
- Findings indicate LIBMA is well suited for inference in short dynamic panel data models with endogenous regressors in the context of model uncertainty.

### Application
- Application to a dynamic gravity model for bilateral trade is used to illustrate the methodology (details of the application are presented in the paper).

### Publication and metadata
- Authors: Huigang Chen, Alin T Mirestean, Charalambos G Tsangarides
- Date: October 1, 2011
- Series: Working Paper No. 2011/230
- Issue: 230
- Volume: 2011
- Pages: 45
- DOI: https://doi.org/10.5089/9781463921309.001
- Stock No: WPIEA2011230
- ISBN: 9781463921309
- ISSN: 1018-5941
- Subject: Bayesian models, Estimation techniques, Exchange rate arrangements, Gravity models
- Keywords: WP

*IMF Working Papers — Limited Information Bayesian Model Averaging for Dynamic Panels with An Application to a Trade Gravity Model (Huigang Chen, Alin T Mirestean, Charalambos G Tsangarides), October 1, 2011.*

---

## Content in this bundle

- **_wp11230**
  - [_wp11230 (Markdown version)](/-/media/websites/imf/imported-full-text-pdf/external/pubs/ft/wp/2011/_wp11230.pdf.md){rel="alternate" type="text/markdown"}
  - [_wp11230 (PDF)](/-/media/websites/imf/imported-full-text-pdf/external/pubs/ft/wp/2011/_wp11230.pdf){rel="external" type="application/pdf"}

---

_Source: https://www.imf.org/en/publications/wp/issues/2016/12/31/limited-information-bayesian-model-averaging-for-dynamic-panels-with-an-application-to-a-25270_