[R] Wilcox paired test error message

[peter dalgaard]

On Jun 24, 2013, at 15:21 , Sarah Goslee wrote:

> G'morning.
> 
> On Mon, Jun 24, 2013 at 2:22 AM, peter dalgaard <pdalgd at gmail.com> wrote:
>> 
>> On Jun 23, 2013, at 22:30 , Sarah Goslee wrote:
>> 
>>> Hi,
>>> 
>>> If you're doing exactly as described below, then you need to add the
>>> data argument to wilcox.test so R knows where to find beforesmall and
>>> aftersmall. But if so, that's a rather uninformative error message.
>>> 
>>> Saraj
>> 
>> Not really, if you use the formula interface, the rhs is supposed to be the grouping, as in
>> 
>> wilcox.test(extra ~ group, data=sleep, paired=TRUE)
>> 
>> so it's telling you that "aftersmall" does not describe two groups.
> 
> Yep, sorry. That was actually my first thought, but then I misread the
> helpfile.
> 
> You do still need the data argument, though. :)

-- or a preceding attach(), which at least some of us still use occasionally despite its dangers. For paired tests, it doesn't actually work to use data=, you need

with(mydata, t.test(beforesmall, aftersmall, paired=TRUE))

-pd

> 
> Sarah
> 
>> (It is unfortunate, though, that we don't have a formula interface to the parallel-vector data layout for paired tests. That is the common case, the sleep data set is a rather rare exception. A formula specification for paired columns has been talked about; something like cbind(before, after) ~ 1 should be workable, but nothing has materialized to date.)
>> 
>> -pd
>> 
>>> 
>>> On Sun, Jun 23, 2013 at 2:34 PM, ruth parker <parkeractonruth at gmail.com> wrote:
>>>> Hi,
>>>> I've been trying to run a wilcox paired test on some data
>>>> beforesmall aftersmall
>>>> [1,]        63.5      512.0
>>>> [2,]        54.5      237.5
>>>> [3,]        52.5      161.5
>>>> [4,]        78.0      153.5
>>>> [5,]        53.5       68.0
>>>> [6,]        50.5       65.5
>>>> [7,]        69.0       52.0
>>>> [8,]        76.0       59.0
>>>> [9,]        68.0       66.5
>>>> [10,]        75.5       66.5
>>>> [11,]        67.0       45.5
>>>> [12,]        81.0       54.5
>>>> [13,]        49.0       44.0
>>>> [14,]        51.0       42.5
>>>> [15,]        53.0       34.5
>>>> 
>>>> using
>>>> wilcox.test(beforesmall ~ aftersmall,paired=T)
>>>> but I get the error message:
>>>> 
>>>> Error in wilcox.test.formula(beforesmall ~ aftersmall, paired = T) :
>>>> grouping factor must have exactly 2 levels
>>>> 
>>>> I don't have any missing values, I have the same amount of data points for
>>>> each group and I've looked everywhere trying to find the answer.
>>>> Please can somebody tell me how to make it work
>>>> thanks
>>>> 
>>> 
> 
> 
> -- 
> Sarah Goslee
> http://www.functionaldiversity.org
> 
> ______________________________________________
> 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.

-- 
Peter Dalgaard, Professor,
Center for Statistics, Copenhagen Business School
Solbjerg Plads 3, 2000 Frederiksberg, Denmark
Phone: (+45)38153501
Email: pd.mes at cbs.dk  Priv: PDalgd at gmail.com