Comparisons of Some Chi-squared Tests for the Test of Independence in Sparse Two-Way Contingency Tables
β Scribed by H. B. Lawal; G. J. G. Uptong
- Publisher
- John Wiley and Sons
- Year
- 1990
- Tongue
- English
- Weight
- 609 KB
- Volume
- 32
- Category
- Article
- ISSN
- 0323-3847
No coin nor oath required. For personal study only.
β¦ Synopsis
Abstract
We consider in this paper, the behaviour of a class of the CRESSIE READ (1984) power divergence test statistics indexed by parameter Ξ» β I (Ξ»), with the modified X~2~ test statistics (LU) proposed by LAWAL and UPTON (1984), for sparse contingency tables ranging from the 3Γ3 to the 10Γ10. We present a sample of our results here. The results indicate that the LU test outβperforms either the CressieβRead suggested test I(2/3) or the Pearson's test β I(1). Our results further show that the modification to the likelihood ratio test [Y~2~ = I'(0)] proposed by WILLIAMS (1976) performs like the parent Y~2~ test, very poorly compared with either the I(2/3), X~2~ or the LU test statistics.
Power results also indicate that the powers of the LU test are in all cases considered in this study slightly higher than those of X~2~ and I(2/3) tests. The LU test is therefore strongly recommended for use with sparse twoβway contingency tables because in all of the cases considered, none of the other test statistics consistently outβperforms the LU test with respect to attained Ξ± level or power.
π SIMILAR VOLUMES
several asymptotic tats were proposed for testing the null hypothesis of marginal homogeneity in square oontingency tables with r categories. A simulation study was performed for comparing the power at four finite conservative conditional test procedures and of two asymptotic tests for twelve differ
We consider the problem of testing for heterogeneity of K proportions when K is not small and the binomial sample sizes may not be large. We aasume that the binomial proportions are normally distributed with variance a? The asymptotic relath e efficiency (ARE) of the usual chi-square test iefoundrel
One of the accepted criteria for comparing two independent proportions, in the case of small samples, is the so-called "Fisher's exact test". The authors give tables of P-values for critical regions constructed under the optionel version of the said test. and with the following characteristics: i) t