Robustness of Multistep Forecasts and Predictive Regressions at Intermediate and Long Horizons

Chevillon, Guillaume

doi:10.2139/ssrn.3019901

Cited by 3 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Richardson and Stock (1989) and Valkanov (2003) developed a non‐standard limit distribution theory for long‐horizon forecasts. Chevillon (2017) proved a robustness property of direct multi‐step inference that involves non‐normal asymptotics due to the lack of lag augmentation. Phillips and Lee (2013) tested the null hypothesis of no long‐horizon predictability using a novel approach that requires a choice of tuning parameters, but yields uniformly‐over‐persistence normal asymptotics.…”

Section: Introductionmentioning

confidence: 99%

Local Projection Inference Is Simpler and More Robust Than You Think

Olea

Plagborg‐Møller

2021

ECTA

189

View full text Add to dashboard Cite

Applied macroeconomists often compute confidence intervals for impulse responses using local projections, that is, direct linear regressions of future outcomes on current covariates. This paper proves that local projection inference robustly handles two issues that commonly arise in applications: highly persistent data and the estimation of impulse responses at long horizons. We consider local projections that control for lags of the variables in the regression. We show that lag‐augmented local projections with normal critical values are asymptotically valid uniformly over (i) both stationary and non‐stationary data, and also over (ii) a wide range of response horizons. Moreover, lag augmentation obviates the need to correct standard errors for serial correlation in the regression residuals. Hence, local projection inference is arguably both simpler than previously thought and more robust than standard autoregressive inference, whose validity is known to depend sensitively on the persistence of the data and on the length of the horizon.

show abstract

Section: Introductionmentioning

confidence: 99%

Local Projection Inference Is Simpler and More Robust Than You Think

Olea

Plagborg‐Møller

2021

ECTA

189

View full text Add to dashboard Cite

show abstract

“…While this DMS approach is less fully specified than the VAR‐based IMS approach, Bhansali (), Findley (), Schorfheide () each argued that, under certain assumptions, DMS models could be more robust to model misspecification than were IMS models. More recently, Chevillon () showed that DMS models had an advantage when balancing a bias–variance trade‐off at longer horizons.…”

Section: Introductionmentioning

confidence: 99%

An empirical investigation of direct and iterated multistep conditional forecasts

McCracken

McGillicuddy

2018

J of Applied Econometrics

View full text Add to dashboard Cite

Summary When constructing unconditional point forecasts, both direct and iterated multistep (DMS and IMS) approaches are common. However, in the context of producing conditional forecasts, IMS approaches based on vector autoregressions are far more common than simpler DMS models. This is despite the fact that there are theoretical reasons to believe that DMS models are more robust to misspecification than are IMS models. In the context of unconditional forecasts, Marcellino et al. (Journal of Econometrics, 2006, 135, 499–526) investigate the empirical relevance of these theories. In this paper, we extend that work to conditional forecasts. We do so based on linear bivariate and trivariate models estimated using a large dataset of macroeconomic time series. Over comparable samples, our results reinforce those in Marcellino et al.: the IMS approach is typically a bit better than DMS with significant improvements only at longer horizons. In contrast, when we focus on the Great Moderation sample we find a marked improvement in the DMS approach relative to IMS. The distinction is particularly clear when we forecast nominal rather than real variables where the relative gains can be substantial.

show abstract

“…While this DMS approach is less fully specified than the VAR-based IMS approach, Bhansali (1997), Findley (1983), and Schorfheide (2005) each argue that, under certain assumptions, DMS models can be more robust to model misspecification than are IMS models. More recently, Chevillon (2017) shows that DMS models have an advantage when balancing a bias-variance trade-off at longer horizons.…”

Section: Introductionmentioning

confidence: 99%

An Empirical Investigation of Direct and Iterated Multistep Conditional Forecasts

McCracken

McGillicuddy

2017

View full text Add to dashboard Cite

When constructing unconditional point forecasts, both direct-and iterated-multistep (DMS and IMS) approaches are common. However, in the context of producing conditional forecasts, IMS approaches based on vector autoregressions (VAR) are far more common than simpler DMS models. This is despite the fact that there are theoretical reasons to believe that DMS models are more robust to misspecification than are IMS models. In the context of unconditional forecasts, Marcellino, Stock, and Watson (MSW, 2006) investigate the empirical relevance of these theories. In this paper, we extend that work to conditional forecasts. We do so based on linear bivariate and trivariate models estimated using a large dataset of macroeconomic time series. Over comparable samples, our results reinforce those in MSW: the IMS approach is typically a bit better than DMS with significant improvements only at longer horizons. In contrast, when we focus on the Great Moderation sample we find a marked improvement in the DMS approach relative to IMS. The distinction is particularly clear when we forecast nominal rather than real variables where the relative gains can be substantial. JEL Nos.: C53, C52, C12, C32

show abstract

Robustness of Multistep Forecasts and Predictive Regressions at Intermediate and Long Horizons

Cited by 3 publications

References 32 publications

Local Projection Inference Is Simpler and More Robust Than You Think

Local Projection Inference Is Simpler and More Robust Than You Think

An empirical investigation of direct and iterated multistep conditional forecasts

An Empirical Investigation of Direct and Iterated Multistep Conditional Forecasts

Contact Info

Product

Resources

About