search for: sspl

...earth() to get more: ## Can we do knot-selection for simple (x,y) splines? === Yes, via earth() {using MARS}! x <- (0:800)/8 f <- function(x) 7 * sin(pi/8*x) * abs((x-50)/20)^1.25 - (x-40)*(12-x)/64 curve(f(x), 0, 100, n = 1000, col=2, lwd=2) set.seed(11) y <- f(x) + 10*rnorm(x) m.sspl <- smooth.spline(x,y) # base line "standard smoother" require(earth) fm1 <- earth(x, y) # default settings summary(fm1, style = "pmax") #-- got 10 knots (x = 44 "used twice") below ## Call: earth(x=x, y=y) ## y = ## 175.9612 ## - 10.6744 * pmax(0, x...

...for simple (x,y) splines? === Yes, via earth() {using MARS}! > > x <- (0:800)/8 > > f <- function(x) 7 * sin(pi/8*x) * abs((x-50)/20)^1.25 - (x-40)*(12-x)/64 > curve(f(x), 0, 100, n = 1000, col=2, lwd=2) > > set.seed(11) > y <- f(x) + 10*rnorm(x) > > m.sspl <- smooth.spline(x,y) # base line "standard smoother" > > require(earth) > fm1 <- earth(x, y) # default settings > summary(fm1, style = "pmax") #-- got 10 knots (x = 44 "used twice") below > ## Call: earth(x=x, y=y) > > ## y = > ## 17...

How can I do automatic knot selection while fitting piecewise linear splines to two variables x and y? Which package to use to do it simply? I also want to visualize the splines (and the scatter plot) with a graph. Anupam [[alternative HTML version deleted]]

Hi, I posted some days ago a question concerning the computation of lambda in the smooth.spline function (which I repreat at the bottom of the mail) given _df_ . Unfortunately the documentation is not clear to me. Maybee someone can help to answer in my view the basic question: If the penalized log likelihood is L = (y - f)' W (y - f) + lambda c' Sigma c how the _lambda_ in the above

hi, I am using R's "kernlab" package, exactly i am doing classification using ksvm(.) and predict.ksvm(.).I want use of custom kernel. I am getting some error. # Following R code works (with promotergene dataset): library("kernlab") s <- function(x, y) { sum((x*y)^1.25) } class(s) <- "kernel" data("promotergene") gene <- ksvm(Class ~ .,