Stationary Linear Models
Confidence intervals for the Model Parameters
Covariance estimation by AR fitting
Spectral density estimation: Efromovich method
Kernel estimation: bootstrap method
Covariance matrix estimator for slm object
Methods to estimate the autocovariances of a process
Covariances Selection
Data-driven spectral density estimation
Some linear model
Some stationary processes
Plot.slm
Predict for slm object
Risk estimation for a tapered covariance matrix estimator via bootstra...
Rectangular kernel
slm class
slm: A package for stationary linear models
Fitting Stationary Linear Models
Summarizing Stationary Linear Model Fits
Trapeze kernel
Kernel triangle
Calculate Variance-Covariance Matrix for a Fitted Model Object of clas...
Provides statistical procedures for linear regression in the general context where the errors are assumed to be correlated. Different ways to estimate the asymptotic covariance matrix of the least squares estimators are available. Starting from this estimation of the covariance matrix, the confidence intervals and the usual tests on the parameters are modified. The functions of this package are very similar to those of 'lm': it contains methods such as summary(), plot(), confint() and predict(). The 'slm' package is described in the paper by E. Caron, J. Dedecker and B. Michel (2019), "Linear regression with stationary errors: the R package slm", arXiv preprint <arXiv:1906.06583>.