## Chi square and Cramers V

### Chi square and Cramers V

I have a little question. Recently I have read that Chi square and
Cramers V are related. Therefore I would like to know if I may
interpret the results of Cramers V (in significant cases) when the Chi
Square conditions (expected count less then 5, or p > 0,05) are not
met.

Thanks for lighting my candle.

### Chi square and Cramers V

Hi Fedra

Chi2 ist the test's name (on relation / dependency of the two vars by
doing a comparison of expected frequencies and observed frequencies and
calculating a significance value for the result),
Cramer's V is the contingency coefficient (a measure for strength of
dependency or of effect size).

For 2*2 tables the easier coefficient Phi is used instead of Cramer's V
(for 2*n Tables you have: Phi=Cramer's V).
As a measure of effect-size Phi and Cramer's V are not dependent on N,
while Chi2 of course is.
Formula ist PHI = SQRT (Chi2/N).

HTH
Matthias

Fedra schrieb:

Quote:> I have a little question. Recently I have read that Chi square and
> Cramers V are related. Therefore I would like to know if I may
> interpret the results of Cramers V (in significant cases) when the Chi
> Square conditions (expected count less then 5, or p > 0,05) are not
> met.

> Thanks for lighting my candle.

An analysis of survey data obtained using a stratified sampling design
gives us Region (4 values) and alcohol measures such as Heavy drinker
(yes/no).  The chi-square analysis yields both LLCHISQ and CHISQ
estimates.  When is it appropriate to report one or the other of these
results?  Achieved levels of significance vary ... e.g.,
ChiSq = 6.74
p = .0811
LLChiSq = 36.00
p = .0000

Thank you,
Laurel & Kyunghee

13. Chi-square