Re: Significance testing of Dependent proportions

Hi Bruce,

Let me take the data from the link you provided me long ago when I
wanted to do significance testing of Independent proportions (
http://www.gseis.ucla.edu/courses/ed230a2/notes3/portion.html )

Group n Frequency p
Group1 261 127 0.487
Group2 160 65 0.400

My doubt is, if I want to do significance testing on the above data and
if I know that Group1 and Group2 are NOT independent then how do I go
about it?

Please guide me.

Regards,
Hari
India

>Are you asking how to partition the overall (goodness of fit) chi-square into orthogonal components?
Frankly speaking, it has gone above my head.

.

Relevant Pages

  • Re: Significance testing of Dependent proportions
    ... Hari wrote: ... wanted to do significance testing of Independent proportions ( ... Bruce Weaver ...
    (sci.stat.consult)
  • Re: Binomial dta: how to handle dont-cares?
    ... If you used the usual z-test for comparing two independent proportions, ... And of course, chi-square GOF tests can ... the number & percentage of Neutrals). ... If you were looking for associations between Yes/No/Neutral and some ...
    (sci.stat.edu)