search for: dpill

Hi, just a quick question does dpill computes the bandwidth or half-bandwidth? The help says bandwidth, but in the literature there is often confusion between the bandwidth and half-bandwidth. thanks, Giacomo [[alternative HTML version deleted]]

I would like to get the fortran code for the functions locpol and dpill in the kernsmooth library , the purpose is to incorporate other selection criterion for the bandwidth in which a varying bandwidths are replaced instead of the constant bandwidth. I will send you back the improved version as soon as I get the fortran code for the upper mention functions. ((LOCPOLY...

...# In case you don't have "KernSmooth" package installed, please uncomment below line. # install.packages("KernSmooth") library(KernSmooth) rst <- data.frame(hsp = rnorm(23), dal = rnorm(23) gs <- 350 ts <- seq(1, 353, 16) bw <- lapply(rst, dpill, x = ts, gridsize = gs) # If I just want to apply locpoly function seperately lp.hsp <- locpoly(x = ts, y = rst$hsp, bandwidth = bw$hsp, gridsize = gs) lp.dal <- locpoly(x = ts, y = rst$dal, bandwidth = bw$dal, gridsize = gs) ------------------------------------------------------------------...

...ncerning difference between loess and locpoly. I have to use a plug-in method to chose a bandwith so I take locpoly method to fit a curve. My problem is:I know how to get predicted values in loess: m=loess(y~x) y_fitted=predict(m). But how to get the same in locpoly? I computed like this: bw=dpill(x, y, blockmax = 5, divisor = 20,trim = 0.01, proptrun = 0.05, gridsize = n, range(x), truncate = FALSE) m=locpoly(x, y, drv = 0, degree = 1, gridsize= n, bandwidth=bw, bwdisc = 25, range(x), binned = FALSE) fitfn <- approxfun(m$x, m$y) m_y...