Size corrected significance tests in seemingly unrelated regressions with autocorrelated errors

Yiannis Karavias, Elias Tzavalis, Spyridon Symeonides

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)
159 Downloads (Pure)

Abstract

Refined asymptotic methods are used to produce degrees-of-freedom- adjusted Edgeworth and Cornish-Fisher size corrections of the t and F testing procedures for the parameters of a S.U.R. model with serially correlated errors. The corrected tests follow the Student-t and F distributions, respectively, with an approximation error of order O(τ3), where τ=1/T√ and T is the number of time observations. Monte Carlo simulations provide evidence that the size corrections suggested hereby have better finite sample properties, compared to the asymptotic testing procedures (either standard or Edgeworth corrected), which do not adjust for the degrees of freedom.
Original languageEnglish
JournalJournal of Time Series Econometrics
Volume9
Issue number1
Early online date14 Apr 2016
DOIs
Publication statusPublished - 1 Jan 2017

Keywords

  • AR(1) errors
  • Asymptotic approximations
  • Linear regression
  • S.U.R. models
  • Stochastic expansions

ASJC Scopus subject areas

  • Economics and Econometrics

Fingerprint

Dive into the research topics of 'Size corrected significance tests in seemingly unrelated regressions with autocorrelated errors'. Together they form a unique fingerprint.

Cite this