Group: | Statistical Data Analysis |
Topic: | Nonparametric Methods |
See also: | sker sknn l1line lowess |
Function: | isoreg | |
Description: | isoreg computes the isotonic regression smoother via the Pool Adjacent Violators algorithm. Given a data set {(X_i,Y_i)} where X_i <= X_(i+1) i=1,...,n finds the values {mhat(X_i)} i=1,...,n, such that, minimizes (1/n) sum_i=1,...,n [Y_i - mhat(X_i)]^2 subject to mhat(X_i) <= mhat[X_(i+1)], i=1,...,n |
Usage: | yh = isoreg (y) | |
Input: | ||
y | array | |
Output: | ||
yh | array |
x = read("geyser") x = sort(x, #(1,2)) mh = x[,1]~isoreg(x[,2]) d = createdisplay(1,1) show(d, 1, 1, x, mh)
shows the geyser data and the isotonic regression smoother