ciIter: Function for determining confidence intervals

In jkcshea/l1svr: Inference for Support Vector Regression Under l1 Regularization

Description

This function performs one iteration of estimating the confidence interval. That is, it performs the l1-SVR regression rankscore test under a single null hypothesis.

Usage

ciIter(gamma0, index, intercept, Y, X, U, epsilon, lambda, heteroskedastic,
  hc, kappa)

Arguments

gamma0	Scalar, a conjectured value of the coefficient for the covariate of interest, i.e. the covariate for which the confidence interval is being constructed.
index	Integer, indexes which covariate is of interest.
intercept	Boolean, indicates whether an intercept term is included in the regression.
Y	Vector of dependent variable.
X	Matrix of covariates.
U	Vector of residuals from regressing Y on X using l1svr.
epsilon	Real scalar, bandwidth for SVR.
lambda	Real scalar, parameter for SVR that scales the penalty.
heteroskedastic	Boolean, indicate whether data has heteroskedastic errors. If set to TRUE, then density estimation is performed when conducting inference.
hc	Scalar determing the quantiles of a standard normal distribution used to define the bandwidth for nonparametric density estimation. See Powell (1991) and Bai et. al. (2021) for details.
kappa	Scalar that directly scales the bandwdith for nonparametric density estimation. See Powell (1991) and Bai et. al. (2021) for details.
target	Target, equal to the size of the test.

jkcshea/l1svr documentation built on March 4, 2021, 12:51 a.m.