variance ratio test

variance ratio test

[′ver·ē·əns ′rā·shō ‚test]
(statistics)
A technique for comparing the spreads or variabilities of two sets of figures to determine whether the two sets of figures were drawn from the same population. Also known as F test.
Mentioned in ?
References in periodicals archive ?
The test is used to verify if the outcomes of the variance ratio test support the existence of a random walk behaviour and consequently if it aligns with the concept of "weak-form efficiency".
Kim and Shamsuddin (2008) examined Asian countries and used the variance ratio test and concluded that market efficiency is related to the stage of development.
Using the variance ratio test, he pointed out that the random model on weekly returns did exist for those countries.
The results of unit root test accepted the null hypothesis of random walk for all the indices, whereas it was rejected using corrected variance ratio test. The study also showed that there were significant first order autocorrelation in daily returns, which are in general absent in weekly returns.
Visando a contornar essa questao, CHOW & DENNING (1993) propuseram o quociente de variancias multiplas (multiple variance ratio test).
In the last stage of the investigation the variance ratio test was used.
Using the Cochrane (1988) variance ratio test and the Campbell and Mankiw (1987) variance decomposition test, they suggest that the real net discount ratio follows a trend stationary process with mean-reverting properties.
MacKinlay, 1989, "The Size and Power of the Variance Ratio Test in Finite Samples: A Monte Carlo Investigation," Journal of Econometrics 40, 203-238.
Values of [Delta]15N in samples of salmon berry buds, spruce needles, grass blades, and moss fronds from latrine sites showed higher variability than those of plants collected from nonlatrine sites (one-tailed variance ratio test; P [less than] 0.05 for each pairwise comparisons).
Baldev, ed., Needham, MA: Kluwer Academic, 1989] shows that the variance ratio test has good power against fractionally integrated alternatives.
Another explanation of the variance ratio test's failure to confirm smoothing is that firms may attempt to maintain average inventory at a fixed proportion of average sales, so that if sales are trending up, then inventory will also trend up.(3) West (1986) and others recognized that when firms maintain inventory for stockout avoidance, production smoothing will not be [TABULAR DATA FOR TABLE 1 OMITTED] confirmed in the data.