1973
DOI: 10.2307/2284803
|View full text |Cite
|
Sign up to set email alerts
|

How Many Classes in the Pearson Chi-Square Test?

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
20
0

Year Published

1974
1974
2020
2020

Publication Types

Select...
5
3
1

Relationship

0
9

Authors

Journals

citations
Cited by 33 publications
(20 citation statements)
references
References 0 publications
0
20
0
Order By: Relevance
“…However Williams (1950) shows that for n > 200, the value of k given by the Mann-Wald formula can be halved without significant loss of power. The more recent studies of Hamdan (1963), Dahiya and Gurland (1973), Gvanceladze and Chibisov (1979), Best and Rayner (1981), and Quine and Robinson (1985) indicate that the Mann-Wald formula may result in a choice of k that is too large, and reduces the power of the test against specific alternatives.…”
Section: Choosing the Cell Boundariesmentioning
confidence: 99%
“…However Williams (1950) shows that for n > 200, the value of k given by the Mann-Wald formula can be halved without significant loss of power. The more recent studies of Hamdan (1963), Dahiya and Gurland (1973), Gvanceladze and Chibisov (1979), Best and Rayner (1981), and Quine and Robinson (1985) indicate that the Mann-Wald formula may result in a choice of k that is too large, and reduces the power of the test against specific alternatives.…”
Section: Choosing the Cell Boundariesmentioning
confidence: 99%
“…In this subsection, the correctness of the distributions of the identification and detection statistics, formulated as Eqs. (33), (39), (47) and (48), are verified.…”
Section: A Validation Of the Theoretical Analysismentioning
confidence: 63%
“…1) The Distribution of Identification Statistics: The correctness of the distributions of identification statistics D KL , formulated as Eqs. (33) and (39), can justify the distribution of the eigenvalues of matrix Φ R shown in Eq. (26).…”
Section: A Validation Of the Theoretical Analysismentioning
confidence: 75%
“…Exceptions occur when testing for normality as shown in [13] and when the alternative has light tails compared to the hypothesized distribution [7, 12]. In these cases, small k is optimal for all values of n .…”
Section: Bin Selection For Xn2mentioning
confidence: 99%