Small-Sample Comparisons of Exact Levels for Chi-Squared Goodness-of-Fit Statistics

Abstract The small-sample properties of three goodness-of-fit statistics for the analysis of categorical data are examined with respect to the adequacy of the asymptotic chi-squared approximation. The approximate tests based on the likelihood ratio and Freeman-Tukey statistics yield exact levels that are typically in excess of the nominal levels for moderate expected values. In contrast, the Pearson statistic attains exact levels that are quite close to the nominal values. The reason for the large number of rejections for the likelihood ratio and Freeman-Tukey statistics is related to their handling of small observed counts.

[1]  M. Bartlett.  Contingency Table Interactions , 1935 .

[2]  William Feller,et al.  An Introduction to Probability Theory and Its Applications , 1951 .

[3]  J. Tukey,et al.  Transformations Related to the Angular and the Square Root , 1950 .

[4]  W. G. Cochran.  The $\chi^2$ Test of Goodness of Fit , 1952 .

[5]  D. Darling,et al.  A Test of Goodness of Fit , 1954 .

[6]  Rory A. Fisher,et al.  Statistical Methods for Research Workers. , 1956 .

[7]  J. Hammersley,et al.  Monte Carlo Methods , 1965 .

[8]  W. Hoeffding.  Asymptotically Optimal Tests for Multinomial Distributions , 1965 .

[9]  C. I. Bliss,et al.  Statistics in Biology, Volume I , 1967 .

[10]  R. R. Bahadur.  An optimal property of the likelihood ratio statistic , 1967 .

[11]  P. A. P. Moran,et al.  An introduction to probability theory , 1968 .

[12]  S. Fienberg,et al.  Incomplete two-dimensional contingency tables. , 1969, Biometrics.

[13]  Irving John Good,et al.  Exact Distributions for χ2 and for the Likelihood-Ratio Statistic for the Equiprobable Multinomial Distribution , 1970 .

[14]  James K. Yarnold,et al.  The Minimum Expectation in X 2 Goodness of Fit Tests and the Accuracy of Approximations for the Null Distribution , 1970 .

[15]  E. Staub.  A child in distress: The influence of age and number of witnesses on children's attempts to help. , 1970 .

[16]  C. Odoroff.  A Comparison of Minimum Logit Chi-Square Estimation and Maximum Likelihood Estimation in 2×2×2 and 3×2×2 Contingency Tables: Tests for Interaction , 1970 .

[17]  John A. Nelder,et al.  Statistics In Biology. , 1971 .

[18]  S. Fienberg,et al.  Some models for individual-group comparisons and group behavior , 1971 .

[19]  J. Roscoe,et al.  An Investigation of the Restraints with Respect to Sample Size Commonly Imposed on the Use of the Chi-Square Statistic , 1971 .

[20]  Y. Bishop.  Effects of collapsing multidimensional contingency tables. , 1971, Biometrics.

[21]  Robert G. Easterling,et al.  Combining Component and System Information , 1971 .

[22]  Merle W. Tate,et al.  Inaccuracy of the x2 Test of Goodness of Fit When Expected Frequencies Are Small , 1973 .

[23]  Leo A. Goodman,et al.  Guided and Unguided Methods for the Selection of Models for a Set of T Multidimensional Contingency Tables , 1973 .

[24]  Barry H. Margolin,et al.  An Analysis of Variance for Categorical Data, II: Small Sample Comparisons with Chi Square and other Competitors , 1974 .

[25]  P. Holland,et al.  Discrete Multivariate Analysis. , 1976 .