Kernel smoothing function with cumulative distribution

Question

I am trying to do a cumulative distribution. I know the matlab script to do it but I can't figure out how to do it in R

Here is my matlab code :

[p2,xp2,up2] = ksdensity(X(:,2),xi,'Kernel','epanechnikov','function','cdf','Support',[m(2),M(2)]);

Any idea ?

What about https://stat.ethz.ch/R-manual/R-devel/library/stats/html/density.html ? — Severin Pappadeux, Jan 25 '18 at 19:03
Well, density function is only for probability density function I think. But I managed to do it with density function and simple sum. Thanks ! — Yohann L., Jan 26 '18 at 10:17

score 0 · Accepted Answer · answered Jan 26 '18 at 10:22

Ok, I managed to it with density function and a little sum. Here is my code for those who would like :

dens = density(X[,1], kernel = 'epanechnikov', from = m[1], to = M[1])
x = matrix(unlist(dens[1]))
y = matrix(unlist(dens[2]))
c1 <- cdf(x,y)
plot(x, c1)

cdf <- function(x,y) {
  S <- matrix(0, length(y), 1)
  S[1] <- y[1]
  for(k in seq(2, length(y))) {
    S[k] <- S[k-1] + y[k]
  }
  return(S)
}

Kernel smoothing function with cumulative distribution

1 Answers1