Quantile Residuals for Multivariate Models

  title={Quantile Residuals for Multivariate Models},
  author={Leena Kalliovirta},
  • Leena Kalliovirta
  • Published 2007
So-called quantile residuals are generalized for multivariate time series models. These residuals are applicable for example to nonlinear time series models based on mixture distributions for which conventional residuals are not well suited. We show that under mild regularity conditions multivariate quantile residuals are approximately independent with standard normal distribution. A general framework of obtaining tests based on smooth functions of quantile residuals and the likelihood function… CONTINUE READING


Publications citing this paper.


Publications referenced by this paper.
Showing 1-10 of 28 references

Testind Density Forecasts, With Applications to Risk Management,

  • J. Berkowitz
  • Journal of Business & Economic Statistics,
  • 2001
Highly Influential
5 Excerpts

Evaluating the Forecast Densities of Linear and Non-linear Models: Application to Output Growth and Unemployment,

  • M. P. Clements, J. Smith
  • Journal of Forecasting,
  • 2000
Highly Influential
8 Excerpts

Multivariate Density Forecast Evaluation and Calibration in Financial Risk Management: High-Frequency Returns on Foreign Exchange,

  • F. X. Diebold, J. Hahn, A. S. Tay
  • The Review of Economics and Statistics,
  • 1999
Highly Influential
5 Excerpts

Misspecification Tests Based on Quantile Residuals,

  • L. Kalliovirta
  • HECER Discussion
  • 2006
Highly Influential
3 Excerpts

Randomized Quantile Residuals,

  • P. K. Dunn, G. K. Smyth
  • Journal of Computational and Graphical Statistics…
  • 1996
Highly Influential
5 Excerpts

Evaluating multivariate forecast densities : a comparison of two approaches

  • D. R. Cox, D. V. Hinkley
  • International Journal of Forecasting
  • 2002

Similar Papers

Loading similar papers…