Back to search

University of Ioannina

Small sample size corrections of the t- and F-econometric tests in the linear models with ARMA(1,1) disturbances

Abstract

dc:description

Using refined asymptotic techniques, we derived small-sample size corrections for the t and F econometric tests in the linear regression model with ARMA(1,1) errors. These size corrections are based on the Edgeworth-corrected critical values and on the Cornish-Fisher-corrected test statistics. In particular, the size correction of the t-test can be derived from the normal or Student-t approximations. Moreover, the small-sample size corrections for the Wald and F tests can be derived from the Χ² and F approximations, respectively. Given that the Edgeworth and Cornish-Fisher corrections have an error of order O(T⁻³ᐟ²), where T is the sample size, the relative performance of these corrections can be investigated only by means of simulation experiments. In the context of the linear regression model with ARMA(1,1) errors, the simulation experiment conducted in this thesis seems to confirm the theoretical advantages of the Cornish-Fisher corrections. In almost all cases, the Edgeworth and Cornish-Fisher size corrections seem to improve the small-sample null rejection probabilities of the corrected t and F tests relative to the corresponding uncorrected tests.

Degree

thesis:*
Grantor dc:publisher
University of Ioannina
Year dc:date
2025

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Tatsi, Dimitra
  • Τάτση, Δήμητρα

Subjects

dc:subject × 23

Rights

Language dc:language
eng

Identifiers

dc:identifier.*
Identifier
10.12681/eadd/59603

Chain of custody

source
Harvested from
Greek National Archive of PhD Theses
Base URL
phdtheses.ekt.gr/eadd_oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Tatsi, Dimitra; Τάτση, Δήμητρα. Small sample size corrections of the t- and F-econometric tests in the linear models with ARMA(1,1) disturbances. University of Ioannina, 2025. http://hdl.handle.net/10442/hedi/59603