I've done 2-sample test for equality of proportions with continuity correction. (This is the second course of statistic I'm studying so I know basically nothing, at least so it feels.)

I'm using R and Rstudio for the first time in this course. I have no idea how to interpret the results of this test.

y1 <- 52
n1 <- 89
y2 <- 40
n2 <- 91
prop.test(c(y1,y2), c(n1,n2),
          alternative = "greater", conf.level=0.99)

2-sample test for equality of proportions with continuity correction

data:  c(y1, y2) out of c(n1, n2)
X-squared = 3.2138, df = 1, p-value = 0.03651
alternative hypothesis: greater
99 percent confidence interval:
 -0.03792798  1.00000000
sample estimates:
   prop 1    prop 2 
0.5842697 0.4395604 

So p-value is 0.03651. What do I compare it with? And what are the conclusions? Do I reject or retain the null hypothesis? I know pretty much nothing, so please keep it simple.

  • 1
    $\begingroup$ What is your $\alpha$? Ie, what is the long-run type I error rate you are willing to live with? Relatedly, why did you specify conf.level=0.99 in prop.test()? $\endgroup$ – gung - Reinstate Monica Jan 19 '14 at 1:49

As with all statistical tests, you compare the P-value with your significance level. If you use 0.05 as your significance level, you would reject the null hypothesis of equal success probabilities, since 0.03651 < 0.05. If, however, you use 0.01 as your significance level (as implied by your conf.level=0.99), you would not reject the null hypothesis, since 0.03651 ≰ 0.01.

If you’re not sure what a P-value is, or on how to interpret it, Wikipedia has a not too bad explanation, with a number of illustrating examples.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.