John.Morrongiello at csiro.au
2011-Oct-03 05:33 UTC
[R] new standardised variable based on group membership
Hi I have a data comprised of repeated measures of growth (5-15 records per individual) for 580 fish (similar to Orange dataset from nlme library). I would like to standardise these growth measures (yi – ŷ/sd) using mean and standard deviation unique to each fish. Can someone suggest a function that would help me do this? I’ve had a look at scale and sweep but can’t find a worked example that does what I’m after Cheers John [[alternative HTML version deleted]]
ONKELINX, Thierry
2011-Oct-03 07:35 UTC
[R] new standardised variable based on group membership
Dear John, You need to combine scale with a grouping function. data(Orange) library(plyr) Orange <- ddply(Orange, .(Tree), function(x){ x$ddplyAge <- scale(x$age)[, 1] x }) Orange$aveAge <- ave(Orange$age, by = Orange$Tree, FUN = scale) all.equal(Orange$ddplyAge, Orange$aveAge) Best regards, Thierry> -----Oorspronkelijk bericht----- > Van: r-help-bounces at r-project.org [mailto:r-help-bounces at r-project.org] > Namens John.Morrongiello at csiro.au > Verzonden: maandag 3 oktober 2011 7:34 > Aan: r-help at r-project.org > Onderwerp: [R] new standardised variable based on group membership > > Hi > I have a data comprised of repeated measures of growth (5-15 records per > individual) for 580 fish (similar to Orange dataset from nlme library). I would like > to standardise these growth measures (yi ? ?/sd) using mean and standard > deviation unique to each fish. Can someone suggest a function that would help > me do this? I?ve had a look at scale and sweep but can?t find a worked example > that does what I?m after > > Cheers > > John > > > [[alternative HTML version deleted]]
Seemingly Similar Threads
- How to Standardise the x/y coordinates to the unit square?
- Multiple regression in R - unstandardised coefficients are a different sign to standardised coefficients, is this correct?
- sdev value returned by princomp function (used for PCA)
- hist function: freq=FALSE for standardised histograms
- standardised residuals using standard deviation