Bias in Local Projections

By Edward Herbst, Benjamin K. Johannsen. Finance and Economics Discussion Series, 2020

69 citations recorded by the source corpus.

Local projections (LPs) are a popular tool in macroeconomic research. We show that LPs are often used with very small samples in the time dimension. Consequently, LP point estimates can be severely biased. We derive simple expressions for this bias and propose a way to bias-correct LPs. Small sample bias can also lead autocorrelation-robust standard errors to dramatically understate sampling uncertainty. We argue they should be avoided in LPs like the ones we study. Using identified monetary policy shocks, we demonstrate that the bias in point estimates can be economically meaningful and the bias in standard errors can affect inference.

Subfields: Economics and Econometrics

View Paper: https://www.semanticscholar.org/paper/b456b39ee4f1c1b228d46472b1185fa84d15bfdc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

Citations in the corpus

Local Projection Inference Is Simpler and More Robust Than You Think (2020, methodology): “like VAR estimation (Herbst and Johannsen, 2020), we consider a simple and computationally convenient bootstrap implementation of local projection.”
Local Projections vs. VARs: Lessons From Thousands of DGPs (2021, methodology): “…frontier by considering: (i) small-sample bias correction of the VAR coefficients (Pope, 1990; Kilian, 1998) and LP impulse response estimates (Herbst & Johannsen, 2023); (ii) penalized LP (Barnichon & Brownlees, 2019), which smooths out impulse response functions; (iii) Bayesian VAR…”