Estimating nonlinear effects of fiscal policy using quantile regression methods

Abstract

We use quantile regression methods to estimate the effects of government spending shocks on output and unemployment rates. This allows to uncover nonlinear effects of fiscal policy by letting the parameters of either vector autoregressive models or local projection regressions vary across the distribution of macroeconomic activity. In quarterly US data, we find that fiscal output multipliers are notably larger if GDP is predicted to be below trend. Conversely, higher government spending appears to significantly lower unemployment only if the unemployment rate is in the largest deciles of its conditional distribution.

US Fiscal Policy and Asset Prices: The Role of Partisan Conflict

“…More importantly, we examine these dynamic responses by conditioning on various quantiles of the growth of the PCI that allows us to capture the various levels of political disagreements. See Koenker and d'Orey (), Cecchetti and Li (), Kilian and Park (), and Linnemann and Winkler () for details on the methods.…”

Assessing Macroeconomic Tail Risk

“…Confidence bands are based on Newey-West corrected standard errors that control for serial correlation in the error terms induced by the successive leading of the dependent variable. At this point it is useful to contrast our approach with another approach that aims to combine quantile regressions with local projections, an approach advocated for by Linnemann and Winkler (2016). We want to interpret the 10th percentile of 4-quarters ahead GDP growth as a measure of downside risk and we then ask how this measure of risk reacts to different shocks.…”

“…We study a number of shocks and find it useful to use the same quantile (or measure of risk) for all shocks we study in our local projections. Linnemann and Winkler (2016), instead, are interested in one shock only and model the conditional quantiles conditional on, among other things, a fiscal shock and thus include the shock directly in the quantile regression. By following their approach, Linnemann and Winkler (2016) cannot distinguish between the two horizons h and s that we emphasized above (given that they ask a different question, they probably would not want to).…”

“…Linnemann and Winkler (2016), instead, are interested in one shock only and model the conditional quantiles conditional on, among other things, a fiscal shock and thus include the shock directly in the quantile regression. By following their approach, Linnemann and Winkler (2016) cannot distinguish between the two horizons h and s that we emphasized above (given that they ask a different question, they probably would not want to). 5 With impulse responses to various quantiles at hand, we fit a flexible distribution to our es-timated path of GDP growth distributions after each shock.…”

The Asymmetric Effects of Oil Price Shocks on the Chinese Stock Market: Evidence from a Quantile Impulse Response Perspective

“…This method was first proposed by Cecchetti and Li [33] and has been used to explore the asymmetric and nonlinear effects between financial and economic variables [34,35]. Lee and Kim [36] argue that the quantile impulse response function is widely applicable and is beneficial in that it captures the dynamic responses that the conventional impulse response does not explain.…”