Re: [R] Error in Quantile function

From: David Winsemius <dwinsemius_at_comcast.net>
Date: Fri, 14 Nov 2008 11:10:54 -0500

I should also point out that the .01 and .99 quantiles for a set that only has 18 elements are not particularly meaningful results. And even the .05 and .95 ones are pretty suspect. You may be getting numbers, but what do they mean?

-- 
David Winsemius


On Nov 14, 2008, at 9:33 AM, irishmhw wrote:


>
> That worked the charm, the line that you suggested age me a bad
> atomic number
> error but I just assigned the spread$bootdataframe.age to a new
> vector and
> it works great. Thanks you have been a great help. Best in all to
> you and
> yours.
>
>
>
> David Winsemius wrote:
>>
>>
>> On Nov 13, 2008, at 7:56 PM, irishmhw wrote:
>>
>>>
>>> This is strange the first function that I am doing this for is
>>> saying in the
>>> typeof() is a double for some reason this is coming up as a list.
>>
>> Well, dataframes _are_ lists.
>>
>>>
>>>> str(spread)
>>> 'data.frame': 18 obs. of 1 variable:
>>> $ bootdataframe.age: num 1.46e-09 1.67e-09 1.46e-09 1.45e-09
>>> 1.37e-09 ...
>>
>> I'm pretty sure you cannot send an entire dataframe to quantile.
>> Pretty sure you need to give a vector argument. So what happens when
>> you try:
>>
>> exp_CIs <- quantile( spread$bootdataframe.age,
>> probs=c(0.01,0.05,0.95,0.99) )
>>
>> --
>> David Winsemius
>> Heritage Labs
>>
>>>
>>>> typeof(spread)
>>> [1] "list"
>>>> class(spread)
>>> [1] "data.frame"
>>>>
>>>
>>>
>>> David Winsemius wrote:
>>>>
>>>> Please show us what you get when you execute:
>>>>
>>>> str(spead)
>>>> typeof(spread)
>>>> class(spread)
>>>>
>>>> It is doubtful that either of your theories is correct. It's more
>>>> likely that spread is a more complex object than you realize. We
>>>> need
>>>> to know what spread looks like to the R interpreter in the
>>>> environment
>>>> where it is being called.
>>>>
>>>> --
>>>> David Winsemius
>>>> Heritage Labs
>>>>
>>>>
>>>> On Nov 13, 2008, at 3:29 PM, irishmhw wrote:
>>>>
>>>>>
>>>>> If anyone can assist with this problem you have my great thanks:
>>>>>
>>>>> I am trying to establish and plot confidence intervals on a
>>>>> bootstrapped
>>>>> function. I have a more complicated function that has no problems
>>>>> with
>>>>> determining the confidence intervals using the quantile command.
>>>>> This is
>>>>> outside the bootstrap portion of the code that is working fine
>>>>> it is
>>>>> just
>>>>> determining everything for the more complicated model, not even
>>>>> sure
>>>>> what
>>>>> the error is telling me.
>>>>>
>>>>>> spread <- expntl.dr(plot_k_list,pdose)
>>>>>> exp_CIs <- quantile(spread,probs=c(0.01,0.05,0.95,0.99))
>>>>> Error in order(list(bootdataframe.age = c(1.56064428047387e-09,
>>>>> 1.63862234892065e-09, :
>>>>> unimplemented type 'list' in 'orderVector1'
>>>>>>
>>>>>
>>>>> I am not sure if this is problem with the quantile command
>>>>> trying to
>>>>> order
>>>>> the data or if the values in the spread are too close together.
>>>>>
>>>>> Thank you for any assistance you can offer.
>>>>>
>>>>> Mark
>>>>> --
>>>>
>>>> ______________________________________________
>>>> 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.
>>>>
>>>>
>>>
>>> --
>>> View this message in context:
>>> http://www.nabble.com/Error-in-Quantile-function-tp20488954p20492856.html
>>> Sent from the R help mailing list archive at Nabble.com.
>>>
>>> ______________________________________________
>>> 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.
>>
>>
>> [[alternative HTML version deleted]]
>>
>> ______________________________________________
>> 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.
>>
>>
>
> --
> View this message in context: http://www.nabble.com/Error-in-Quantile-function-tp20488954p20501578.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> 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.
______________________________________________ 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.
Received on Fri 14 Nov 2008 - 16:12:45 GMT

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.2.0, at Fri 14 Nov 2008 - 16:30:25 GMT.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.

list of date sections of archive