VAR forecasting under misspecification

By Frank Schorfheide. 2005

106 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/4dcb7591a63860e283af09574739ba961be36d17

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

In Management Science and Operations Research

Citations in the corpus

A Comparison of Direct and Iterated Multistep Ar Methods for Forecasting Macroeconomic Time Series (2006, background): “Contributions to the theory of iterated vs. direct forecasts include Findley (1983, 1985), Weiss (1991), Tiao and Xu (1993), Lin and Granger (1994), Tiao and Tsay (1994), Clements and Hendry (1996), Bhansali (1996, 1997), Kang (2003), Chevillon and Hendry (2005), and Schorfheide (2005).”
Model averaging, asymptotic risk, and regressor groups (2014, methodology): “The local asymptotic framework is a technical device commonly seen in model selection and averaging asymptotic theory, for example, Hjort and Claeskens (2003) and Schorfheide (2005).”
Forecasting with Factor-Augmented Regression: A Frequentist Model Averaging Approach, Second Version (2013, background): “…that the Mallows criterion is asymptotically unbiased for the MSFE, it does not establish that the selected weight vector is asymptotically effi cient in the sense of Shibata (1980), Ing and Wei (2005), or Schorfheide (2005) for forecast selection, or Hansen (2007) in the case of model averaging.”
Nonparametric Bootstrap Procedures for Predictive Inference Based on Recursive Estimation Schemes (2007, methodology): “15 In the context of multistep ahead vector autoregressive prediction, Schorfheide (2005) proposes a new prediction criterion that can be used to jointly select the number of lags as well as to choose between (quasi)-maximum likelihood estimators and loss function based estimators. such as Bierens’…”
Do Macro Variables, Asset Markets or Surveys Forecast Inflation Better? (2007, unknown): “While Schorfheide (2005) shows that in theory, iterated forecasts need not be superior to direct forecasts from horizon-specific models, Marcellino et al. (2006) document the empirical superiority of iterated forecasts in predicting U.S. macroeconomic series.”
Direct multi-step estimation and forecasting (2006, unknown): “Schorfheide (2005) extended and confirmed these results by presenting the case of local misspecification, whereby the disturbances exhibited serial correlation that asymptotically vanished.”
Evaluating Direct Multistep Forecasts (2005, result): “As described in studies such as Clements and Hendry ( 1996 ), Schorfheide ( 2005 ), Chevillon and Hendry ( 2005 ), and Marcellino et al.”
Dynamic Prediction Pools: An Investigation of Financial Frictions and Forecasting Performance (2016, unknown): “Notes: This figure is taken from Del Negro and Schorfheide (2013). The panels show for each model real time data on real GDP growth (upper panel) and inflation (GDP deflator, lower panel) (black line); multi-step (fixed origin) posterior mean forecasts (red line); credible bands from the predictive ”
Asset Pricing in the Frequency Domain: Theory and Empirics (2016, methodology): “Vector autoregressions (VARs) have the advantage that they are easy to estimate (in that they require no numerical optimization), they have been widely used in the previous literature,25 and because when the number of lags in the VAR increases, the VAR structure can asymptotically capture arbitraril”
Order selection for same-realization predictions in autoregressive processes (2005, unknown): “When the candidate vector AR models are misspecified, Schorfheide [23] also considered order selection problems for the purpose of independent-realization predictions.”
ACCUMULATED PREDICTION ERRORS, INFORMATION CRITERIA AND OPTIMAL FORECASTING FOR AUTOREGRESSIVE TIME SERIES (2007, methodology): “On the other hand, if the process used in estimation (or model selection) and that for prediction are independent, then it is called an independent-realization prediction (see [2, 16, 22] and [25]).”
Local Projections vs. VARs: Lessons From Thousands of DGPs (2021, methodology): “We here formalize this basic intuition by extending the arguments of Schorfheide (2005) to structural impulse response estimation in a simple, albeit non-stationary DGP.”