#' Automatic index builder for regression coefficients
#'
#' @description In our time lagged regression problem, each covariate \eqn{x_i} is either present or absent for all lags,
#' this function makes it easy to only specify the general sparsity, and convert it for all 5 lags. Used for both generation of
#' response, and for the estimation purpose. Caution: so far only for total of 10 covariates!
#'
#' @param xs a vector. Index of non 0 covariates
#'
#' @return a list of components
#'
#' \item{xs}{The initial indices, also lag0 (at t-0)}
#' \item{in2}{Indices for lag1, t-1}
#' \item{in3}{Indices for lag2, t-2}
#' \item{in4}{Indices for lag3, t-3}
#' \item{in5}{Indices for lag4, t-4}
#'
#' @export
#'
#' @examples
#' xs.est <- c(4, 5, 6, 7, 8, 9, 10)
#' fullindex = full.index(xs.est)
#'
full.index <- function(xs){ # duplicate xs 5 times
in2 <- c(xs, xs + 10)
in3 <- c(in2, xs+20)
in4 <- c(in3, xs+30)
in5 <- c(in4, xs+40)
return(list(lag0 = xs,
lag1 = in2,
lag2 = in3,
lag3 = in4,
lag4 = in5))
}
# for full.index.large(), go to the original Rproj
# here for simplicity, one function per file
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.