Home > Statistics Every Writer Should Know > The Stats Board > Discusssion
power analysis
Message posted by boulton (via 142.106.180.133) on February 21, 2002 at 4:35 PM (ET)
does it make sense to incorporate the sample variance in a post-hoc power analysis of a chi-square test of indenpendence (contingency table, binomial)?
i don't think it'd be useful..... your response would be appreciated....
READERS RESPOND:
(In chronological order. Most recent at the bottom.)
Re: power analysis
Message posted by JG (via 128.8.22.31) on February 22, 2002 at 7:18 AM (ET)
Variance of what?
Re: power analysis
Message posted by Jack Tomsky (via 12.144.103.66) on February 22, 2002 at 1:58 PM (ET)
If the power function depends on unknown parameters and you replace these parameters by the corresponding sample estimates, you end up with an estimate of the power function. That's how it should be interpreted.
Your $5 contribution helps cover part the $500 annual cost of keeping this site online.