|
Teoriya Veroyatnostei i ee Primeneniya, 1973, Volume 18, Issue 3, Pages 583–591
(Mi tvp2730)
|
|
|
|
This article is cited in 65 scientific papers (total in 65 papers)
Chi-square test for continuous distributions with location and scale parameters
M. S. Nikulin V. A. Steklov Mathematical Institute, USSR Academy of Sciences
Abstract:
The problem of testing the hypothesis that the distribution function of independent equally distributed random variables is $G[(x-\theta_1)/\theta_2]$ is considered; $\theta_1$ and $\theta_2$ being unknown parameters. A statistic which is a modification of Pearson's $\chi^2$ is proposed whose limit distribution is chi-square with $(k-1)$ degrees of freedom, $k$ being the number of cells (it means that the number of degrees of freedom does not depend on the number of unknown parameters). In the statistic the maximum likelihood estimations of $\theta_1$ and $\theta_2$ based on the original observations are used. A similar result is obtained for the quantile test.
Received: 24.04.1973
Citation:
M. S. Nikulin, “Chi-square test for continuous distributions with location and scale parameters”, Teor. Veroyatnost. i Primenen., 18:3 (1973), 583–591; Theory Probab. Appl., 18:3 (1974), 559–568
Linking options:
https://www.mathnet.ru/eng/tvp2730 https://www.mathnet.ru/eng/tvp/v18/i3/p583
|
|