VAR meets DSGE: Uncovering the Monetary Transmission Mechanism in Low-Income Countries
IMF Working Papers, April 11, 2016
Source details
- Canonical URL
- VAR meets DSGE: Uncovering the Monetary Transmission Mechanism in Low-Income Countries
Other formats
Bibliographic details
- Authors: Grace B Li, Stephen A. O'Connell, Christopher S Adam, Andrew Berg, Peter J Montiel
- Published: April 11, 2016
- Series: IMF Working Papers
- DOI: https://doi.org/10.5089/9781484324752.001
Research question and methodology
- Core question: Are structural VARs identified via short-run restrictions capable of detecting a monetary transmission mechanism when one exists, under research conditions typical of low-income countries (LICs)?
- Method: Use small DSGEs as data-generating processes to assess the impact on VAR-based inference of:
- short data samples,
- measurement error,
- high-frequency supply shocks,
- and other features of the LIC environment.
- Emphasis on assessing finite-sample bias and precision of estimated impulse responses to monetary policy shocks.
Key findings
- VAR methods suggest that the monetary transmission mechanism may be weak and unreliable in low-income countries (LICs).
- The impact of LIC data features on finite-sample bias:
- Appears to be relatively modest when identification is valid.
- This modest bias is presented as a strong caveat, especially in LICs.
- The impact of LIC data features on precision:
- Many features undermine the precision of estimated impulse responses to monetary policy shocks.
- Cumulatively, these features suggest that “insignificant” results can be expected even when the underlying transmission mechanism is strong.
Implications for empirical practice and interpretation
- Insignificant VAR-based impulse responses in LIC contexts do not necessarily imply an absent or weak underlying monetary transmission mechanism; they may reflect features of the estimation environment.
- Researchers should be cautious in interpreting non-significant VAR results from LICs because:
- Short data samples, measurement error, and high-frequency supply shocks reduce precision.
- Valid identification reduces finite-sample bias, but precision problems remain important.
- Use of small DSGEs as data-generating processes provides a framework to evaluate how typical LIC data features affect VAR inference.
Subject areas and keywords emphasized in the study
- Subjects: Dynamic stochastic general equilibrium models, Econometric analysis, Economic theory, Environment, Structural vector autoregression, Supply shocks, Vector autoregression
- Keywords: Africa; Dynamic stochastic general equilibrium models; estimation environment; exchange-rate elasticity; features of the estimation environment; GDP gap; inflation rate; interest rate; interest rate target; LIC context; LIC environment; Low Income Countries; monetary policy; monetary policy effect; monetary policy rule; monetary policy shock; Monetary Transmission Mechanism; Monte Carlo Methods; research environment; Structural vector autoregression; Supply shocks; transmission mechanism; Vector autoregression; Vector Autoregression Methods; WP
VAR meets DSGE: Uncovering the Monetary Transmission Mechanism in Low-Income Countries, IMF Working Paper No. 2016/090 (April 11, 2016).