A class of chi-squared goodness-of-fit statistics is presented as being based on the so-called divergence of one probability distribution from another. A still more general class of goodness-of-fit statistics is then presented by eliminating some of the restrictions required of divergence-based statistics. This most general class of statistics includes, as particular cases, a variety of statistics used in the published literature.
Get full access to this article
View all access options for this article.
References
1.
AgrestiA. (2002) Categorical data analysis. (2nd ed.) New York: Wiley.
2.
CsiszárI. (1972) A class of measures of informativy of observation channels. Peridica Mathematica Hungarica, 2, 191–213.
3.
KapurJ. N. (1994) Measures of information and their applications.New York: Wiley.
4.
KvålsethT. O. (1991) On generalized information measures of human performance. Perceptual and Motor Skills, 72, 1059–1063.
5.
MenéndezM. L., & PardoJ. A. (2002) Tests of symmetry in three-dimensional contingency tables based on phi-divergence statistics. Paper presented at the 24th European Meeting of Statisticians and the 14th Prague Conference on Information Theory, Statistical Decision Functions and Random Processes, Prague, the Czech Republic, August 19–23.
6.
ReadT. R. C., & CressieN. A. C. (1988) Goodness-of-fit statistics for discrete multivariate data.Berlin: Springer-Verlag.
7.
WickensC. D., & HollandsJ. G. (2000) Engineering psychology and human performance. (3rd ed.) Upper Saddle River, NJ: Prentice Hall.
