The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.
The goal of DLL is to implement the Decorrelated Local Linear estimator proposed in <arxiv:1907.12732>. It constructs the confidence interval for the derivative of the function of interest under the high-dimensional sparse additive model.
You can install the released version of DLL from CRAN with:
install.packages("DLL")
This is a basic example which shows you how to solve a common problem:
library(DLL)
library(MASS)
# evaluation points
= c(-0.5,0.25)
d0
= function(x) 1.5*sin(x)
f = function(x) 1.5*cos(x)
f.deriv = function(x) 2*exp(-x/2)
g1 = function(x) (x-1)^2 - 25/12
g2 = function(x) x - 1/3
g3 = function(x) 0.75*x
g4 = function(x) 0.5*x
g5
# sample size and dimension of X
= 500
n = 500
p
# covariance structure of D and X
= toeplitz(c(1, 0.7, 0.5, 0.3, seq(0.1, 0, length.out = p-3)))
Cov_Matrix
set.seed(123)
# X represents the (D,X) here
= mvrnorm(n,rep(-0.25,p+1),Sigma = Cov_Matrix)
X = rnorm(n,sd=1)
e # generating response
= f(X[,1]) + g1(X[,2]) + g2(X[,3]) + g3(X[,4]) + g4(X[,5]) + g5(X[,6]) + e
y
### DLL inference
= DLL(X=X, y=y, D.ind = 1, d0 = d0) DLL.model
true values
f.deriv(d0)
#> [1] 1.316374 1.453369
point estimates
$est
DLL.model#> f1
#> -0.5 1.258581
#> 0.25 1.659544
standard errors
$est.se
DLL.model#> f1
#> -0.5 0.3911074
#> 0.25 0.4301377
confidence interval
$CI
DLL.model#> $f1
#> lower upper
#> -0.5 0.4920249 2.025138
#> 0.25 0.8164900 2.502599
These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.