loess() on subsets of data

Question

Apologies if this has been answered before, but I am unable to find an applicable example.

I am trying to detrend some data for variogram analysis.

I have a dataframe 'aa' with columns 'y' 'long' 'lat' and 'z'.

I am trying to run: loess(aa2$y ~ aa$long + aa$lat, aa, degree =2) on each level of factor z.

In the end, I need a dataframe of 'Long' 'Lat' 'Residual' and 'Z', residuals coming from the multiple facor-specific loess objects.

Given my limited knowledge of R, I cannot figure out the proper syntax to make this happen.

I am assuming one of the *apply functions could be used but I don't know the language well enough to write it properly.

Thank you for any guidance or clarification.

Answer 1

Like this?

aa <- data.frame(y=rnorm(100),long=rnorm(100),lat=rnorm(100),Z=rep(1:4, each=25))

result <- do.call(rbind,lapply(unique(aa$Z),function(z){
  df <- aa[aa$Z==z,]
  fit <- loess(y~long+lat,df,degree=2)
  cbind(Z=z,long=df$long,lat=df$lat,residuals=fit$residuals)
}))
head(result)
#   Z       long         lat  residuals
# 1 1  0.9622113  0.03114804 -0.2189496
# 2 1 -0.6539525  0.32908716  1.3904483
# 3 1  1.0066978 -0.78833830  0.1044707
# 4 1 -1.0873116 -0.55218226  1.8526030
# 5 1 -1.1286776  1.68879949  0.2459814
# 6 1 -1.0052768 -0.85890027 -0.9842824