[R] power.t.test threading on 'power'

[Uwe Ligges]

On 02.10.2014 00:27, Stephen Kennedy wrote:
> Thanks.  I’ve been getting some nice workarounds.  I was pleasantly surprised when the function ‘threaded’ on the number of samples, but I guess that was not really part of the design, just an accident.

One could argue that the error message could be improved. ;-)

Indeed, the function was not designed to work on vectors, but most parts 
of R are, hence the "accident". :-)

Best,
Uwe Ligges



> Best,
>
> Steve
>
>
>
> On Oct 1, 2014, at 6:15 PM, Uwe Ligges <ligges at statistik.tu-dortmund.de> wrote:
>
> On 01.10.2014 14:29, Stephen Kennedy wrote:
>> Simple question.  A vector of ‘number of observations’ can be input to power.t.test, and a vector of ‘power’ s is output.  But, inputting a vector of powers generates an error.  Am I missing something?
>>
>> Vector of ’n’ s
>>
>> power.t.test(n=c(28,29,30), delta=2, sd=3, sig.level=0.05, type="two.sample", alternative="one.sided")
>>
>>       Two-sample t test power calculation
>>
>>                n = 28, 29, 30
>>            delta = 2
>>               sd = 3
>>        sig.level = 0.05
>>            power = 0.7933594, 0.8058963, 0.8177506
>>      alternative = one.sided
>>
>> NOTE: n is number in *each* group
>>
>>
>>
>> Vector of ‘power’ s
>>
>> power.t.test(power=c(0.7,0.8,0.9), delta=2, sd=3, sig.level=0.05, type="two.sample", alternative="one.sided")
>> Error in uniroot(function(n) eval(p.body) - power, c(2, 1e+07)) :
>>    f() values at end points not of opposite sign
>> In addition: Warning messages:
>> 1: In if (is.na(f.lower)) stop("f.lower = f(lower) is NA") :
>>    the condition has length > 1 and only the first element will be used
>> 2: In if (is.na(f.upper)) stop("f.upper = f(upper) is NA") :
>>    the condition has length > 1 and only the first element will be used
>>
>
> power.t.test oes not work on vectors in general.
>
> Here, you want:
>
> lapply(c(0.7, 0.8, 0.9),
>     function(power)
>         power.t.test(power=power, delta=2, sd=3, sig.level=0.05,
>                      type="two.sample", alternative="one.sided")
> )
>
> Best,
> Uwe Ligges
>
>
>
>
>>
>> Thanks,
>>
>> Steve
>> ______________________________________________
>> R-help at r-project.org mailing list
>> https://stat.ethz.ch/mailman/listinfo/r-help
>> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
>> and provide commented, minimal, self-contained, reproducible code.
>>
>