[R] Comparing proportions between groups

[Chuck Cleland]

On 3/28/2008 5:33 AM, Lila86 wrote:
> Hello there,
> 
> I have two groups (men and women) and I know per group how many of them
> smoke or don't smoke (women 40 of 200; men 100 of 300). I would like to know
> how I can compare in R if men and women differ significantly in their
> smoking.  However, because there are more men in the sample than women I
> cannot just compare the number of smokers and non-smokers in both groups,
> right?! (I would not really know how to do that either, to be honest :(). 
> 
> I have done this:
> 
> gensmoke <- table(data$gender,data$smoke)   	#save table 
> 
> old.digits = options("digits")        # store the number of digits
> options(digits=3)                     # only print 3 decimal places
> gensmokePROP = prop.table(gensmoke,1)    #table of the proportions I'd like
> to compare
> 
>                 smoker  non-smoker
> women       0.200   0.800
> men          0.333   0.667
> 
> 
> But then when I try to run a t-test on it, for example
> 
> t.test(gensmokePROP[3], gensmokePROP[4], alternative = "less")
> 
> then R tells me that there are not enough observations in x.
> Could anyone help me? That would be really great. Thank you,
> Lila

prop.test(x=c(40,100), n=c(200,300))

OR

prop.test(matrix(c(40,100,160,200), ncol=2))

?prop.test

-- 
Chuck Cleland, Ph.D.
NDRI, Inc. (www.ndri.org)
71 West 23rd Street, 8th floor
New York, NY 10010
tel: (212) 845-4495 (Tu, Th)
tel: (732) 512-0171 (M, W, F)
fax: (917) 438-0894