[Rd] confint's in t.test

[Kurt Hornik]

>>>>> Torsten Hothorn writes:

>> t.test(rnorm(10), rnorm(10), alternative="less")

>          Welch Two Sample t-test 

> data:  rnorm(10) and rnorm(10) 
> t = -2.3628, df = 17.848, p-value = 0.01485 
> alternative hypothesis: true difference in means is less than 0 
> 95 percent confidence interval:
>          NA -0.2590752 
>         ^^^^

> I suppose that is what the prototype does, should one replace it by
> -Inf, + Inf resp. ?

I'd say yes (which agrees with confidence intervals for the variance
and odds ratios) ...

-k
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-devel mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-devel-request@stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._