Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: pairwise test of proportions
From
Phil Clayton <[email protected]>
To
[email protected]
Subject
Re: st: pairwise test of proportions
Date
Wed, 20 Oct 2010 12:12:05 +1100
Not sure about earlier versions but in version 11 -prtest- can perform one-sample, two-sample (ie paired) or two-group comparisons depending on the syntax used.
The two-group syntax is:
prtest varname, by(groupvar)
You can also use -mcc- to calculate McNemar's chi-squared for paired proportions.
Phil
On 20/10/2010, at 10:42 AM, Richard Williams wrote:
> At 06:30 PM 10/19/2010, Stas Kolenikov wrote:
>> On Tue, Oct 19, 2010 at 5:12 PM, helen bian <[email protected]> wrote:
>> > Has anyone written a program that does a pairwise test of proportions
>> > and contains the p-values in its output?
>>
>> Is it -prtest- or -prtesti-?
>
> That was my first impulse. However, the documentation refers to "Two-sample test of proportion." From the examples, I got the impression it was for unpaired samples. ttest, by way of contrast, refers to "Two-sample mean-comparison test (unpaired)" and "Two-sample mean-comparison test (paired)". So, ttest lets you do something like a before and after comparison of the same subjects; prtest sounds to me like it is comparing proportions for two different samples, rather than paired values.
>
>
> -------------------------------------------
> Richard Williams, Notre Dame Dept of Sociology
> OFFICE: (574)631-6668, (574)631-6463
> HOME: (574)289-5227
> EMAIL: [email protected]
> WWW: http://www.nd.edu/~rwilliam
>
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/