Asymptotic Inference about Predictive Ability

By Ken West. 1996

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

Deep Learning for Predicting Asset Returns (2018, methodology): “The most popular method for testing signiﬁcant difference in MSPE is the Diebold and Mariano (2002) and West (1996) test.”
Noncausal Autoregressions for Economic Time Series (2010, unknown): “N model at the 1% level according to the test of Diebold and Mariano (1995) and West (1996).”
Forecasting crude oil price volatility (2018, unknown): “Building on the Diebold and Mariano framework , West ( 1996 ) develops the asymptotic theory for the EPA test ; meanwhile Giacomini and White ( 2006 ) investigate the …nite sample properties of the EPA test .”
Evaluating the Predictive Accuracy of Volatility Models (2001, methodology): “As in West and Cho (1994), two autoregressive models of are estimated using t ordinary least squares and an assumed conditionally normal distribution.”
The Predictive Power of Google Searches in Forecasting Unemployment (2012, background): “Nevertheless, after the seminal papers by Diebold and Mariano (1995) and West (1996), the community of forecasters has increasingly understood the importance of correctly testing for out-of-sample equal forecast accuracy.”
Tests of Equal Forecast Accuracy and Encompassing for Nested Models (2001, background): “While West (1999) shows the ENC-T statistic can be asymptotically standard normal when applied to non-nested forecasts, the asymptotic distribution is non-normal when the forecasts are nested under the null.”
Asymptotics for out of sample tests of Granger causality (2007, methodology): “Such an estimator can be shown to be consistent using the results in either West (1996) or McCracken (2000b).”
Model Averaging and Value-at-Risk Based Evaluation of Large Multi Asset Volatility Models for Risk Management (2004, unknown): “The proposed test converges to a standard Normal variate provided T1/T0+1/T1 → 0, a condition also encountered in forecast evaluation literature that uses root mean square error as evaluation criteria, as discussed in West (1996).”
Evaluating Volatility and Correlation Forecasts (2009, methodology): “The DMW tests the null of equal predictive accuracy against composite alternatives that indicate which forecast performs better: H0 : E [ L(Σt , HAt ) ] = E [ L(Σt , HBt ) ] (30) vs. H1 : E [ L(Σt , HAt ) ] > E [ L(Σt , HBt ) ] H2 : E [ L(Σt , HAt ) ] E [ L(Σt , HBt ) ] Since Σt is unobservable, t”
Comparing Predictive Accuracy, Twenty Years Later: A Personal Perspective on the Use and Abuse of Diebold–Mariano Tests (2015, unknown): “That approach traces to the work of West (1996) and Clark and McCracken (2001), inter alia, and in what follows I will use "WCM" in broad reference to it.”
Data-based ranking of realised volatility estimators (2011, methodology): “Inference under the RW approximation is based on Newey andWest (1987) standard errors, while inference under the AR approximation is based on 1000 samples from the stationary bootstrap.”
Making and Evaluating Point Forecasts (2009, background): “In evaluating volatility forecasts, Patton and Sheppard (2009) recommend the use of the latter because of its superior power in Diebold and Mariano (1995) and West (1996) tests of predictive ability, which depend on differences between mean scores of the form (1) as test statistics.”
Testing Density Forecasts, With Applications to Risk Management (2001, background): “The drawback, as stressed by West (1996), is that forecasts are sometimes produced by models estimated with small samples and are thus subject to parameter uncertainty.”
Combination forecasts of output growth in a seven-country data set (2004, background): “Moreover, it is not clear how applicable the West (1996) and Clark and McCracken (2001) distribution theory is when the parameter vector is very large, as is the case for the combination forecasts.”
Forecasting volatility: A reality check based on option pricing, utility function, value-at-risk, and predictive likelihood (2004, background): “0 as T ! l ; so that the effect of parameter estimation vanishes ( as in West , 1996 , Theorem 4 .”
Estimation and Testing of Forecast Rationality under Flexible Loss (2005, background): “For general results on asymptotic inference in the presence of parameter uncertainty, see West (1996), West and McCracken (1998), McCracken (2000) and Corradi and Swanson (2002).”