Working Paper: CEPR ID: DP2208
Authors: Alexander Benkwitz; Helmut Ltkepohl; Jrgen Wolters
Abstract: It is argued that standard impulse response analysis based on vector autoregressive models has a number of shortcomings. Although the impulse responses are estimated quantities, measures for sampling variability such as confidence intervals are often not provided. If confidence intervals are given they are often based on bootstrap methods with poor theoretical properties. These problems are illustrated using two German monetary systems. Proposals are made for improving current practice. Special emphasis is placed on systems with cointegrated variables.
Keywords: impulse response; bootstrap; money demand system; monetary policy
JEL Codes: C32
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| estimation uncertainty (C13) | impulse responses (C22) |
| wide confidence intervals (C46) | impulse responses (C22) |
| traditional bootstrap methods (C51) | confidence intervals (C46) |
| Hall's method (C23) | confidence intervals (C46) |
| restrictions on short-term dynamics (C69) | precision of impulse responses (C22) |
| changes in money supply (E51) | price levels (E30) |
| changes in money supply (E51) | income (E25) |