Jonas Stein wrote:
> Hi,
>
> i have some data, that has 1-5 % noise.
> I want to smooth this data without loosing rows.
>
> rollmean() would be great, but it returns a vector of different size as the
> initial vector.
You might consider one of the smoothers in smooth() from the stats
package.
If you are referring to rollmean in the zoo package then na.pad = TRUE
will cause the output to be the same length as the input:
> library(zoo)
> rollmean(zoo(1:10), 3, na.pad = TRUE)
1 2 3 4 5 6 7 8 9 10
NA 2 3 4 5 6 7 8 9 NA
> rollmean(zoo(matrix(1:10, 5)), 3, na.pad = TRUE)
1
Hi,
i have some data, that has 1-5 % noise.
I want to smooth this data without loosing rows.
rollmean() would be great, but it returns a vector of different size as the
initial vector.
--
kind regards,
Jonas Stein <[EMAIL PROTECTED]>
__
R-help@r-pr
3 matches
Mail list logo