[R] Error; contrasts can be applied only to factors with 2 or more levels

[R. Michael Weylandt]

On Tue, Aug 14, 2012 at 5:54 AM, grace <sololorox at hotmail.com> wrote:
> Hi,
>
> I have been running the same code without problem for the last few days,
> changing data sets etc with no issue.
> Today I changed the covariates for the model and am now getting this error
> message:
> Error in `contrasts<-`(`*tmp*`, value = contr.funs[1 + isOF[nn]]) :
>   contrasts can be applied only to factors with 2 or more levels
>
[snip]
>>
>> ndvi<-data.frame(x1=factor(c(4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
>> 3, 4, 4, 4, 4, 3, 3, 4, 4, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
>> 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
>> 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
>> 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4,
>> 4, 4, 4, 4, 4, 4)), x2=factor(c(4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
>> 3, 3, 4, 4, 4, 4, 3, 3, 4, 4, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
>> 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
>> 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
>> 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4,
>> 4, 4, 4, 4, 4, 4, 4)))
>>
[snip]
>>
>> ndvi<-data.frame(x1=factor(c(3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
>> 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
>> 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
>> 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
>> 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
>> 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3)), x2=factor(c(3, 3, 3, 3,
>> 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
>> 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
>> 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
>> 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
>> 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
>> 3, 3)))

Hi Grace,

Next time, could you use dput() to make a _small_ reproducible
example? Editing out all the symbols added by your mailer and command
prompt takes quite some time.  You have the idea, but this was a bit
much to wade through. Also, you don't need to give the result of
tests, since we can run them ourselves if they aren't too time
intensive. You might find this of use:

 http://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example

Anyways: take a look at the two code blocks I left: in the first
(working) one, you'll see you have factors level 3 and 4, while you
only have 3 in the latter data. I believe this is the source of your
error: contrasts between groups can't be calculated when there is only
one group.

Cheers,
Michael