| Title: | Sure Independence Screening via Quantile Correlation and Composite Quantile Correlation |
|---|---|
| Description: | Quantile correlation-sure independence screening (QC-SIS) and composite quantile correlation-sure independence screening (CQC-SIS) for ultrahigh-dimensional data. |
| Authors: | Xuejun Ma, Jingxiao Zhang, Jingke Zhou |
| Maintainer: | Xuejun Ma <[email protected]> |
| License: | GPL-2 |
| Version: | 0.1 |
| Built: | 2025-02-22 04:24:17 UTC |
| Source: | https://github.com/cran/QCSIS |
Quantile correlation-sure independence screening (QC-SIS) and composite quantile correlation-sure independence screening (CQC-SIS) for ultrahigh-dimensional data.
| Package: | QCSIS |
| Type: | Package |
| Title: | Sure Independence Screening via Quantile Correlation and Composite Quantile Correlation |
| Version: | 0.1 |
| Date: | 2015-12-02 |
| Author: | Xuejun Ma, Jingxiao Zhang, Jingke Zhou |
| Maintainer: | Xuejun Ma <[email protected]> |
| Description: | Quantile correlation-sure independence screening (QC-SIS) and composite quantile correlation-sure independence screening (CQC-SIS) for ultrahigh-dimensional data. |
| License: | GPL-2 |
| URL: | http://www.r-project.org |
| NeedsCompilation: | no |
| Packaged: | 2015-12-02 11:38:00 UTC; yinuo |
| Date/Publication: | 2015-12-02 14:22:26 |
| Repository: | https://xuejunma.r-universe.dev |
| RemoteUrl: | https://github.com/cran/QCSIS |
| RemoteRef: | HEAD |
| RemoteSha: | f04db1a185bad7c87e43a898d45988211b344a51 |
Index of help topics:
CQCSIS Compsote Quantile Correlation-Sure Independence
Screening (CQC-SIS)
QCSIS Quantile Correlation-Sure Independence
Screening (QC-SIS)
QCSIS-package Sure Independence Screening via Quantile
Correlation and Composite Quantile Correlation
cqc Composite Quantile Correlation
qc Quantile Correlation
Xuejun Ma, Jingxiao Zhang, Jingke Zhou
Maintainer: Xuejun Ma <[email protected]>
Xuejun Ma and Jingxiao Zhang. Robust model-free feature screening via quantile correlation. Journal of Multivariate Analysis. Online, 2015.
Xuejun Ma et al.. Robust feature screening via composite quantile correlation learning. In submission.
cqc is used to compute the composite quantile correlation.
cqc(x, y)cqc(x, y)
x |
The covariate variable. |
y |
The response variable. |
cqc |
The value of composite quantile correlation. |
Xuejun Ma, Jingxiao Zhang, Jingke Zhou
Xuejun Ma et al.. Robust feature screening via composite quantile correlation learning. In submission.
x <- rnorm(100) y <- rnorm(100) cqc(x = x, y = y)x <- rnorm(100) y <- rnorm(100) cqc(x = x, y = y)
The function implemrnts the composite quantile correlation-sure independence screening (CQC-SIS).
CQCSIS(x, y, d)CQCSIS(x, y, d)
x |
The design matrix, of dimensions n * p, without an intercept. |
y |
The response vector of dimension n * 1. |
d |
The tuning parameter used to covarites had significant effect on the response variable, such as [n/log(n)], or n-1. |
w |
The estimate of w. |
M |
The subscript of x recuited by CQC-SIS. |
Xuejun Ma, Jingxiao Zhang, Jingke Zhou
Xuejun Ma et al.. Robust feature screening via composite quantile correlation learning. In submission.
n <- 20 p <- 200 x <- matrix(rnorm(n * p), n, p) e <- rnorm(n, 0, 1) beta1 <- 3 - runif(1) beta2 <- 3 - runif(1) beta3 <- 3 - runif(1) y <- beta1 * x[, 1] + beta2 * x[, 2] + beta3 * x[, 3] + e d <- 19 fit.CQCSIS <- CQCSIS(x = x, y = y, d = d) fit.CQCSIS$Mn <- 20 p <- 200 x <- matrix(rnorm(n * p), n, p) e <- rnorm(n, 0, 1) beta1 <- 3 - runif(1) beta2 <- 3 - runif(1) beta3 <- 3 - runif(1) y <- beta1 * x[, 1] + beta2 * x[, 2] + beta3 * x[, 3] + e d <- 19 fit.CQCSIS <- CQCSIS(x = x, y = y, d = d) fit.CQCSIS$M
qc is used to compute the quantile correlation with given quantiles.
qc(x, y, tau)qc(x, y, tau)
x |
The covariate variable. |
y |
The response variable. |
tau |
The quantile(s) to be estimated. |
tau |
The quantile(s). |
rho |
The value of quantile correlation. |
Xuejun Ma, Jingxiao Zhang, Jingke Zhou
Li et al.. Quantile correlations and quantile autoregressive modeling. Journal of the American Statistical Association,2015,110(509):246–261.
n <- 1000 x <- rnorm(n) y <- 2 * x + rt(n,df = 1) tau <- 1:9 / 10 qc(x = x, y = y, tau = tau)n <- 1000 x <- rnorm(n) y <- 2 * x + rt(n,df = 1) tau <- 1:9 / 10 qc(x = x, y = y, tau = tau)
The function implemrnts the quantile correlation-sure independence screening (QC-SIS).
QCSIS(x, y, tau, d)QCSIS(x, y, tau, d)
x |
The design matrix, of dimensions n * p, without an intercept. |
y |
The response vector of dimension n * 1. |
tau |
The quantile(s) to be estimated. By default, tau=1:(n-1)/n. |
d |
The tuning parameter used to covarites had significant effect on the response variable, such as [n/log(n)],or n-1 |
w |
The estimate of w. |
M |
The subscript of x recuited by QC-SIS. |
Xuejun Ma, Jingxiao Zhang, Jingke Zhou
Xuejun Ma and Jingxiao Zhang. Robust model-free feature screening via quantile correlation. Journal of Multivariate Analysis. Online, 2015.
n <- 20 p <- 200 r <- 0.05 x <- matrix(rnorm(n * p), n, p) e <- rnorm(n, 0, 1) inde <- sample(n, r * n) x[inde, 1] <- 2 * sqrt(rchisq(r * n, df = p)) y <- 5 * x[, 1] + 5 * x[, 2] + 5 * x[, 3] + e d <- 19 fit.QCSIS <- QCSIS(x = x, y = y, d = d) fit.QCSIS$Mn <- 20 p <- 200 r <- 0.05 x <- matrix(rnorm(n * p), n, p) e <- rnorm(n, 0, 1) inde <- sample(n, r * n) x[inde, 1] <- 2 * sqrt(rchisq(r * n, df = p)) y <- 5 * x[, 1] + 5 * x[, 2] + 5 * x[, 3] + e d <- 19 fit.QCSIS <- QCSIS(x = x, y = y, d = d) fit.QCSIS$M