[R] Question about correlation

[Göran Broström]

On 2017-07-05 11:56, Jim Lemon wrote:
> Hi Chin Yi,
> If you are trying to correlate "Health" with "Disease", i.e.
> 
> cydf<-read.table(text="OTU ID Health Disease
>    Bacterial 1 0.29 0.34
>    Bacterial 2 0.25 0.07
>    Bacterial 3 0.06 0.06
>    Bacterial 4 0.07 0.09
>    Bacterial 5 0.02 0.05",
>    header=TRUE)
> print(cor(cydf$Health,cydf$Disease))
> [1] 0.7103517
> 
> If you are getting that error, it probably means that either "Health"
> or "Disease" or perhaps both have been read in as a factor. To test
> this:
> 
> is.factor(cydf$Health)
> [1] FALSE
>> is.factor(cydf$Disease)
> [1] FALSE
> 
> If either of these returns TRUE, that is almost certainly the problem.

Or maybe Chin Yi tried (as it seems)

 > cor(cydf)
Error in cor(cydf) : 'x' must be numeric

(with cydf == data): 'OTU' is not numeric.

Follow Jim's advice.

Göran

> 
> Jim
> 
> 
> On Wed, Jul 5, 2017 at 11:27 AM, SEB140004 Student
> <chinyi at siswa.um.edu.my> wrote:
>> Greeting.
>>
>> Dear Mr/Mrs/Miss,
>>
>> OTU ID Health Disease
>> Bacterial 1 0.29 0.34
>> Bacterial 2 0.25 0.07
>> Bacterial 3 0.06 0.06
>> Bacterial 4 0.07 0.09
>> Bacterial 5 0.02 0.05
>> Above show the first 6 data sets, may I ask that the reason of R show the
>> error like "Error in cor(data) : 'x' must be numeric" ? And how to solve
>> it? Besides, isn't this data can conduct correlation matrix?
>>
>> Moreover, isn't this data sets can be plot into network? If can, which
>> package should I use?
>>
>> Thank you.
>>
>> Best regards,
>> Kang Chin Yi
>>
>>          [[alternative HTML version deleted]]
>>
>> ______________________________________________
>> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
>> 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 -- To UNSUBSCRIBE and more, see
> 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.
>