On 09.02.2013 19:10, Steven LeBlanc wrote:> Hi Uwe,
>
> Thanks much. I don't think this is the issue. My entire data set is:
>
>>p3.18
> s xbar subgroup
> 1 0.84 12.2 1
> 2 1.64 11.2 2
> 3 2.07 10.6 3
> 4 2.49 12.2 4
> 5 0.84 11.2 5
> 6 1.82 12.6 6
> 7 2.95 12.2 7
> 8 1.67 13.6 8
> 9 1.30 12.2 9
> 10 1.52 10.4 10
> 11 1.95 10.4 11
> 12 1.67 10.6 12
> 13 1.67 10.4 13
> 14 2.91 12.0 14
> 15 0.84 11.2 15
> 16 1.82 10.6 16
> 17 1.14 10.4 17
> 18 2.17 9.8 18
> 19 2.07 9.6 19
> 20 1.95 10.6 20
>
> It is also the case that variable s is correctly interpreted by mean(x):
>
>>mean(p3.18$s)
> [1] 1.7665
>
> Thus, it seems either I'm failing to appreciate a detail in the help
> documentation that accounts for the different response between type
> "xbar" and type "S", or there is an unintended outcome
in the
> implementation.
So if the error message makes not too much sense with the data, you may
start to debug the function or ask the package maintainer.
And you learned that sending reproducible examples is very worthwhile,
particularly since now I found you used type="xbar" in the first but
type="S" in the second case, the latter trying to calculate variances
of
each observation in your s vector, hence given NA in the statsitics that
is to be plotted.
Best,
Uwe Ligges
>
> Best Regards,
> Steven
>
> On Feb 9, 2013, at 9:29 AM, Uwe Ligges <ligges at
statistik.tu-dortmund.de
> <mailto:ligges at statistik.tu-dortmund.de>> wrote:
>
>>
>>
>> On 08.02.2013 23:37, Steven LeBlanc wrote:
>>> Greets,
>>>
>>> My data looks like:
>>>
>>>> p3.18
>>> s xbar subgroup
>>> 1 0.84 12.2 1
>>> 2 1.64 11.2 2
>>> 3 2.07 10.6 3
>>> 4 2.49 12.2 4
>>> 5 0.84 11.2 5
>>> ...
>>>
>>> Using the command
>>>
>>>>
qcc(p3.18$xbar,type="xbar",sizes=5,center=mean(p3.18$xbar),std.dev=mean(p3.18$s)/0.94,title="X-bar
>>>> Chart for Paper Sheet Length Data")
>>>
>>> I get the x-bar chart I expect.
>>>
>>> However, using the command
>>>
>>>>
qcc(p3.18$s,type="S",sizes=5,center=mean(p3.18$s),std.dev=mean(p3.18$s)/0.94,title="S
>>>> Chart for Paper Sheet Length Data")
>>>
>>> I get the following error:
>>>
>>> Error in plot.window(...) : need finite 'ylim' values
>> >
>>> It seems reasonable that if the first command produces correct
>>> results, so should the second. What am I doing wrong?
>>
>> Watch out for NA, NaN, Inf or -Inf values in p3.18$s ?
>>
>> Uwe Ligges
>>
>>
>>
>>> Thanks & Best Regards,
>>> Steven
>>>
>>>
>>>
>>>
>>>
>>> [[alternative HTML version deleted]]
>>>
>>> ______________________________________________
>>> R-help at r-project.org <mailto: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.
>>>
>