Neglected serial correlation tests in UCARIMA models

Artikel

We derive computationally simple and intuitive score tests of neglected serial correlation in unobserved component univariate models using frequency domain techniques. In some common situations in which the alternative model information matrix is singular under the null, we derive one-sided extremum tests, which are asymptotically equivalent to likelihood ratio tests, and explain howto compute reliable Wald tests. We also explicitly relate the incidence of those problems to the model identification conditions and compare our tests with tests based on the reduced form prediction errors. Our Monte Carlo exercises assess the finite sample reliability and power of our proposed tests.

Angaben zum Objekt

• Sprache: Englisch

Verweise und Beziehungen

• Erschienen in: Journal: SERIEs - Journal of the Spanish Economic Association ; ISSN: 1869-4195 ; Volume: 7 ; Year: 2016 ; Issue: 1 ; Pages: 121-178 ; Heidelberg: Springer

Klassifikation und Themen

• Klassifikation: Wirtschaft ; Single Equation Models; Single Variables: Time-Series Models; Dynamic Quantile Regressions; Dynamic Treatment Effect Models; Diffusion Processes ; Model Evaluation, Validation, and Selection ; Hypothesis Testing: General
• Thema: Extremum tests ; Kalman filter ; LM tests ; Singular information matrix ; Spectral maximum likelihood ; Wiener-Kolmogorov filter

Beteiligte, Orts- und Zeitangaben

• Ereignis: Geistige Schöpfung
• (wer): Fiorentini, Gabriele ; Sentana, Enrique
• Ereignis: Veröffentlichung
• (wer): Springer
• (wo): Heidelberg
• (wann): 2016

Weitere Informationen

• DOI: doi:10.1007/s13209-015-0132-3
• Handle: http://hdl.handle.net/10419/158553
• Letzte Aktualisierung: 10.03.2025, 11:44 MEZ