Z test for the difference in proportions

[Ramzan Afzal-2]

 

Dear All,

 

I have a question on Z test for quality between two proportions. I have multiple groups i.e. Group A to Group D. So, in a single run I want SPSS to perform z test between A and B , A & C, A and D, B and C, B and D, and finally C and D.

 

Any help or support would be very much appreciated.

 

Regards

 

Ramzan

[Samir Paul]

you can use ctable with the sig test option.

On Sun, May 17, 2009 at 7:10 PM, Ramzan Afzal <[hidden email]> wrote:

 

Dear All,

 

I have a question on Z test for quality between two proportions. I have multiple groups i.e. Group A to Group D. So, in a single run I want SPSS to perform z test between A and B , A & C, A and D, B and C, B and D, and finally C and D.

 

Any help or support would be very much appreciated.

 

Regards

 

Ramzan

--
Samir Paul
382 Main Street, TORONTO ON M4C4X8
CANADA
Phone: ( 001 )  416 686 9958

[Marta Garcia-Granero]

Ramzan Afzal wrote:
>   I have a question on Z test for quality between two proportions. I
> have multiple groups i.e. Group A to Group D. So, in a single run I
> want SPSS to perform z test between A and B , A & C, A and D, B and C,
> B and D, and finally C and D.
>

You can't, and shouldn't, besides. use a Chi-square test first to test
the null hypothesis that all proportions are equal, and, only if it is
rejected, then you an perform pairwise comparisons. You can use either
CTABLES (pairwise comparisons with Bonferroni adjustment), or Marascuilo
test. Check old messages of mine for  a solution for both approaches.

Marta

--
For miscellaneous SPSS related statistical stuff, visit:
http://gjyp.nl/marta/

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD