View Single Post
  #2   Report Post  
Stan Brown
 
Posts: n/a
Default

On Tue, 7 Jun 2005 13:29:01 -0700, PlugNChug
wrote:

Is there a function in Excel for conducting the Two-Sample Test for Binomial
Proportions (normal theory method)?


I couldn't find one directly.

However, you can compute the z statistic and then use it to run a
ZTEST. (Usual caveats about Excel's normal calculations apply.)

Assume P1 and P2 contain the proportion of "yes" responses in each
sample and N1 and N2 contain the size of each sample. Then compute
the pooled sample proportion in P3 as

( P1*N1 + P2*N2 ) / ( N1 + N2 )

and the z statistic (for a null hypothesis that the two population
proportions are equal) is

(P1-P2) / SQRT( P3 * (1-P3) * (1/N1 + 1/N2) )

--
Stan Brown, Oak Road Systems, Tompkins County, New York, USA
http://OakRoadSystems.com/
"I feel a wave of morning sickness coming on, and I want to
be standing on your mother's grave when it hits."