Predictive density and conditional confidence interval accuracy tests

By Valentina Corradi, Norman R. Swanson. 2006

122 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Finance

View Paper: https://www.semanticscholar.org/paper/5471a8f6262fc8d25b42eb6995ecc086f4a4a07a

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 Finance

Citations in the corpus

Specification Tests of Parametric Dynamic Conditional Quantiles (2010, unknown): “Andrews (1997) and Corradi and Swanson (2006).”
Likelihood-based scoring rules for comparing density forecasts in tails (2011, methodology): “This problem of relative predictive accuracy has been considered by Sarno and Valente (2004); Mitchell and Hall (2005); Corradi and Swanson (2005, 2006b); Amisano and Giacomini (2007) and Bao et al. (2004, 2007).”
Comparing Density Forecasts Using Threshold- and Quantile-Weighted Scoring Rules (2011, methodology): “In the case of threshold weighting, it is formally equivalent to the approach of Corradi and Swanson (2006a), who provided a wealth of relevant theoretical results under rolling and recursive estimation schemes.”
Combining inflation density forecasts (2010, methodology): “One is based on a distributional analog of the mean squared error norm (Corradi & Swanson 2003b, 2006b), the other is based on the Kullback-Leibler divergence or Kullback-Leibler Information Criterion (KLIC) (Kitamura 2002, Mitchell & Hall 2005, Amisano & Giacomini 2007).”
Model Selection, Estimation and Forecasting in INAR(p) Models: (2008, methodology): “Given the relatively small sample size on which the forecast experiments in this study are based, it is di¢ cult to perform robust statistical tests on the predictive accuracy of competing models as in, for example, Corradi and Swanson (2006).”
Comparing Density Forecasts via Weighted Likelihood Ratio Tests (2007, unknown): “Tests that account for parameter estimation uncertainty were proposed by Hong and Li (2005), Bai (2003), and Corradi and Swanson (2006a) (the latter further allowing for dynamic misspecification under the null hypothesis).”
Testing for Structural Stability of Factor Augmented Forecasting Models (2014, unknown): “As explained in detail in Corradi and Swanson ( 2006 ) , the location bias problem is solved by simply recentering the bootstrap statistic around the full sample .”
Nonparametric Bootstrap Procedures for Predictive Inference Based on Recursive Estimation Schemes (2007, methodology): “…a benchmark model, and the objective is to test whether there is an alternative model that can provide more accurate, loss function specific, 3 An application to predictive density and confidence interval forecast evaluation is given in Corradi and Swanson (2006a). out-of-sample predictions.”
Evaluating, Comparing and Combining Density Forecasts Using the KLIC with an Application to the Bank of England and NIESR 'Fan' Charts of Inflation (2005, unknown): “Related approaches to compare density forecasts statistically have been proposed by Sarno and Valente (2004) and Corradi and Swanson (2004). Rather than use the KLIC measure of ‘distance’, they rely on the integrated square difference between the forecast density and the true density (Sarno and Vale”
Statistical tests for multiple forecast comparison (2012, methodology): “In all cases one can also use bootstrap critical values, along the lines of Corradi and Swanson (2006) and Corradi and Swanson (2007).”
Information in the Revision Process of Real-Time Datasets (2008, unknown): “From a theoretical perspective, it remains to extend the predictive density accuracy tests of Corradi and Swanson (2006a, 2006b) to the case of real-time data, thus furthering the pointwise predictive accuracy test results reported in Clark and McCracken (2009).”
Alternative tests for correct specification of conditional predictive densities (2019, unknown): “We are interested in the test statistics: κP = sup r∈[0,1] |ΨP (r) |, (4) CP = ∫ 1 0 ΨP (r) 2 dr. (5) The κP test statistic is the same as the V1T test statistic considered by Corradi and Swanson (2006a) when applied to predictive densities.”