The moments of the Pearson chi-squared statistic and the minimum expected value in two-way tables
作者： T. LEWIS , I. W. SAUNDERS , M. WESTCOTT
关键词: Mathematics 、 Expected value 、 Pearson's chi-squared test 、 Injury control 、 Statistic 、 Poison control 、 L-moment 、 Contingency table 、 Distribution (mathematics) 、 Applied mathematics
摘要: SUMMARY Explicit expressions for the first three moments of Pearson's X2 statistic a two-way contingency table are used to investigate accuracy x2 approximation its distribution. The usual 'minimum expected value' criterion is shown give global bound on moments, but be too conservative. This illustrated by examples. It that adequacy depends significance level as well moments. When inadequate, corrections based can used. Numerical studies usefulness these presented.
oup.com
oxfordjournals.org
jstor.org 
sci-hub.se 参考文章(10)
James K. Yarnold, The Minimum Expectation in X 2 Goodness of Fit Tests and the Accuracy of Approximations for the Null Distribution Journal of the American Statistical Association. ,vol. 65, pp. 864- 886 ,(1970) , 10.1080/01621459.1970.10481131
C. A. G. NASS, THE X2 TEST FOR SMALL EXPECTATIONS IN CONTINGENCY TABLES, WITH SPECIAL REFERENCE TO ACCIDENTS AND ABSENTEEISM Biometrika. ,vol. 46, pp. 365- 385 ,(1959) , 10.1093/BIOMET/46.3-4.365
I. J. Good, T. N. Gover, G. J. Mitchell, Exact Distributions for χ2and for the Likelihood-Ratio Statistic for the Equiprobable Multinomial Distribution Journal of the American Statistical Association. ,vol. 65, pp. 267- 283 ,(1970) , 10.1080/01621459.1970.10481078
REED B. DAWSON, A simplified expression for the variance of the χ2-function on a contingency table Biometrika. ,vol. 41, pp. 280- 280 ,(1954) , 10.1093/BIOMET/41.1-2.280
Kinley Larntz, Small-Sample Comparisons of Exact Levels for Chi-Squared Goodness-of-Fit Statistics Journal of the American Statistical Association. ,vol. 73, pp. 253- 263 ,(1978) , 10.1080/01621459.1978.10481567
J. B. S. HALDANE, THE MEAN AND VARIANCE OF χ2, WHEN USED AS A TEST OF HOMOGENEITY, WHEN EXPECTATIONS ARE SMALL Biometrika. ,vol. 31, pp. 346- 355 ,(1940) , 10.1093/BIOMET/31.3-4.346
Merle W. Tate, Leon A. Hyer, Inaccuracy of the x2 Test of Goodness of Fit When Expected Frequencies Are Small Journal of the American Statistical Association. ,vol. 68, pp. 836- 841 ,(1973) , 10.1080/01621459.1973.10481433
William G. Cochran, Some Methods for Strengthening the Common χ 2 Tests Bioethics. ,vol. 10, pp. 417- ,(1954) , 10.2307/3001616
Stephen E. Fienberg, The Use of Chi-Squared Statistics for Categorical Data Problems Journal of the Royal Statistical Society: Series B (Methodological). ,vol. 41, pp. 54- 64 ,(1979) , 10.1111/J.2517-6161.1979.TB01057.X
M. E. Wise, Multinomial Probabilities and the χ 2 and X 2 Distributions Biometrika. ,vol. 50, pp. 145- ,(1963) , 10.2307/2333755