[R] prop.test() - need algorithm or reference

gheine at mathnmaps.com gheine at mathnmaps.com
Thu Aug 13 16:44:46 CEST 2009


Preparing a paper for a medical journal.  

Using the prop.test() function in R (v2.4.0) 

to compare two groups' response to data like the following.

A sample of 100 individuals from Population I, 18 with positive readings

from a certain test,

  vs.

A sample of 148 individuals from Population II, 61 with positive readings.



Results look like this:



R version 2.4.0 Patched (2006-11-25 r39997)

......

> prop.test(c(18,61),c(100,148))



        2-sample test for equality of proportions with continuity

correction



        data:  c(18, 61) out of c(100, 148)

        X-squared = 13.7676, df = 1, p-value = 0.0002069

        alternative hypothesis: two.sided

        95 percent confidence interval:

         -0.3498963 -0.1144280

         sample estimates:

            prop 1    prop 2

            0.1800000 0.4121622





Presumably the p-value measures that the likelihood

that the two populations have the same proportion of

response.  My question is this.  The reviewer of the

paper has asked for a reference on the algorithm used

to compute the p-value. The R Reference Manual is not

clear on this.  Is this a standard algorithm that can

be quoted by name (e.g., "Two-sample T Test")?  I

do note that the manual quotes a 1927 article by E.B.

Wilson.  Is the method of computation explained there?



Thank you for any assistance you can provide.



George Heine

gheine at mathnmaps.com




More information about the R-help mailing list