Evaluating Direct Multistep Forecasts

By Todd E. Clark, Michael W. McCracken. 2005

218 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/b883439e2ab7c03d5719e1b11187d0cd5da20c92

How researchers see this paper

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

Citations in the corpus

FORECAST EVALUATION (methodology): “…distributions that are asymptotically free of nuisance parameters under certain additional conditions: (6.2c) one step ahead predictions and conditionally homoskedastic prediction errors, or (6.2d) the number of additional regressors in the larger model is exactly 1 [Clark and McCracken (2005a)].”
Advances in Forecast Evaluation (2011, unknown): “To illustrate essential features, we present selected results, for the distributions of the MSE-t and MSE-F tests when the recursive sampling scheme is used, developed in Clark and McCracken (2005a).”
Working Paper Series (2019, unknown): “To determine any significant differences, we use the MSE-F statistic described in Clark and McCracken (2005) and obtain critical values using a fixed-regressor wild bootstrap as described in Clark and McCracken (2012).”
Macroeconomic Forecasting With Mixed-Frequency Data (2008, methodology): “Following in the tradition of testing for equal predictive ability of West (1996) and West and McCracken (1998) (also see the review in West 2006), we employ the test of equal forecast accuracy for multistep forecasts from nested models of Clark and McCracken (2005).”
Multi-Horizon Forecast Comparison (2019, unknown): “This is in contrast to the literature set out by West (1996), and greatly expanded on by amongst others Clark and McCracken (2005, 2012) and Clark and West (2007), whose aim is to use the forecasts to learn something about population-level predictive ability; accuracy of forecasts at the population…”
Approximately Normal Tests for Equal Predictive Accuracy in Nested Models (2007, unknown): “Standard critical values are appropriate when P/R-0 under an asymptotic approximation in which R-N, P-N (West 1996; West and McCracken (1998); McCracken 2004; Clark and McCracken 2001, 2005a ).”
Equivalence Between Out-of-Sample Forecast Comparisons and Wald Statistics ∗ (2012, methodology): “Such tests are frequently undertaken using the approach of West (1996), McCracken (2007) and Clark and McCracken (2001, 2005) which accounts for the effect of recursive updating in parameter estimates.”
Taylor Rules with Real-Time Data: A Tale of Two Countries and One Exchange Rate (2008, methodology): “Panel A presents forecasting results with the Central Banks’ measures of the output gaps, as used for estimation of the Taylor 18 Clark and McCracken (2001, 2005) and McCracken (2006) provide extensive documentation of the size properties of the DMW test.”
Direct multi-step estimation and forecasting (2006, unknown): “Clark and McCracken (2005) considered the asymptotic and finite sample properties of the previous tests of equal multi-step forecast accuracy and encompassing applied to nested models as the distribution of the DM statistics differed in this setting.”
The Predictive Content of the Output Gap for Inflation: Resolving In-Sample and Out-of-Sample Evidence (2006, methodology): “Such contrast in the outcomes of the in-sample and out-of-sample metrics is consistent with the analytical results of Clark and McCracken (2003, 2005b).”
Comparing forecast accuracy: A Monte Carlo investigation (2013, methodology): “In fact, Clark and McCracken (2005b, 2009) show that breaks significantly affect the properties of tests of predictive ability and thus they may render harder the task of discriminating between competing models, and they also argue that the choice of estimation window in rolling regressions becomes…”
Improving Forecast Accuracy by Combining Recursive and Rolling Forecasts (2008, unknown): “A detailed proof is provided in Lemma A6 of Clark and McCracken (2005) – albeit under the technical conditions provided in Hansen (1992) rather than those provided here.”
Nonparametric Bootstrap Procedures for Predictive Inference Based on Recursive Estimation Schemes (2007, methodology): “= 0 for all |k| > h (see Assumption A3 in Clark and McCracken, 2005).”