mse_hat {kader} | R Documentation |
MSE Estimator
Description
Vectorized (in \sigma
) function of the MSE estimator in eq. (2.3) of
Srihera & Stute (2011), and of the analogous estimator in the paragraph after
eq. (6) in Eichner & Stute (2013).
Usage
mse_hat(sigma, Ai, Bj, h, K, fnx, ticker = FALSE)
Arguments
sigma |
Numeric vector |
Ai |
Numeric vector expecting |
Bj |
Numeric vector expecting |
h |
Numeric scalar, where (usually) |
K |
Kernel function with vectorized in- & output. |
fnx |
|
ticker |
Logical; determines if a 'ticker' documents the iteration
progress through |
Value
A vector with corresponding MSE values for the values in
sigma
.
See Also
For details see bias_AND_scaledvar
.
Examples
require(stats)
set.seed(2017); n <- 100; Xdata <- sort(rnorm(n))
x0 <- 1; Sigma <- seq(0.01, 10, length = 11)
h <- n^(-1/5)
Ai <- (x0 - Xdata)/h
fnx0 <- mean(dnorm(Ai)) / h # Parzen-Rosenblatt estimator at x0.
# non-robust method:
theta.X <- mean(Xdata) - Xdata
kader:::mse_hat(sigma = Sigma, Ai = Ai, Bj = theta.X,
h = h, K = dnorm, fnx = fnx0, ticker = TRUE)
# rank transformation-based method (requires sorted data):
negJ <- -J_admissible(1:n / n) # rank trafo
kader:::mse_hat(sigma = Sigma, Ai = Ai, Bj = negJ,
h = h, K = dnorm, fnx = fnx0, ticker = TRUE)