diff --git a/.gitignore b/.gitignore
index bf7affa..9e34124 100644
--- a/.gitignore
+++ b/.gitignore
@@ -17,3 +17,4 @@ vignettes/cache
 *.texpadtmp
 /doc/
 /Meta/
+.DS_Store
diff --git a/DESCRIPTION b/DESCRIPTION
index 01f3e96..7c29d20 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -35,4 +35,4 @@ LazyData: yes
 VignetteBuilder: 
   knitr,
   R.rsp
-RoxygenNote: 7.3.1
+RoxygenNote: 7.2.3
diff --git a/NAMESPACE b/NAMESPACE
index f8201f5..6a6582c 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -24,45 +24,8 @@ S3method(print,time)
 S3method(sigma,ipriorMod)
 S3method(summary,ipriorMod)
 S3method(update,ipriorMod)
-export(.A_times_a)
-export(.calc_Hlam)
-export(.checkLevels)
-export(.collapse_param)
-export(.convert_se)
-export(.correct_pearson_kernel)
-export(.deal_with_one.lam)
-export(.eigen_Hlam)
-export(.eigen_Hlam_nys)
-export(.em_loop_logical)
-export(.expand_Hl_and_lambda)
-export(.expand_theta)
-export(.fix_call_default)
-export(.fix_call_formula)
-export(.formula_to_xy)
-export(.get_Hl)
-export(.get_Hlam)
-export(.get_Htildelam)
-export(.get_Xl.nys)
-export(.get_hyperparam)
-export(.get_kernels_from_Hl)
-export(.get_polydegree)
-export(.get_y_and_levels)
-export(.iprior_method_checker)
-export(.is.categorical)
-export(.is.ipriorKernel_cv)
 export(.kernel_summary_translator)
-export(.kernel_to_param)
-export(.kernel_translator)
 export(.kernels_for_summary)
-export(.param_to_kernel)
-export(.param_to_theta)
-export(.param_translator)
-export(.reduce_theta)
-export(.terms_to_xy)
-export(.theta_to_collapsed_param)
-export(.theta_to_kernel)
-export(.theta_to_param)
-export(.update_control)
 export(as.time)
 export(check_theta)
 export(dec_plac)
diff --git a/R/Kernel_functions.R b/R/Kernel_functions.R
index 730c158..788f32b 100644
--- a/R/Kernel_functions.R
+++ b/R/Kernel_functions.R
@@ -62,7 +62,7 @@
 #' kern_linear(1:3)
 #' kern_fbm(1:5, 1:3, gamma = 0.7)
 #'
-#' @references \url{http://phd.haziqj.ml/intro/}
+#' @references \url{https://phd.haziqj.ml/intro/}
 #'
 #' @name kernel
 #' @aliases kernels
diff --git a/R/Kernel_loader_helper.R b/R/Kernel_loader_helper.R
index c39c1f9..03dd10e 100644
--- a/R/Kernel_loader_helper.R
+++ b/R/Kernel_loader_helper.R
@@ -41,9 +41,6 @@ param_to_kernel <- function(param) {
   as.character(param$kernels)
 }
 
-#' @export
-.param_to_kernel <- param_to_kernel
-
 theta_to_kernel <- function(theta, object) {
   # Convert theta to vector of kernels.
   #
@@ -54,9 +51,6 @@ theta_to_kernel <- function(theta, object) {
   param_to_kernel(param)
 }
 
-#' @export
-.theta_to_kernel <- theta_to_kernel
-
 param_to_theta <- function(param, est.list, logpsi = 0) {
   # Convert param table to the theta vector. Note that theta is designed so that
   # the values are unbounded, i.e. hurst is Phi^{-1}(hurst), lengthscale is
@@ -86,9 +80,6 @@ param_to_theta <- function(param, est.list, logpsi = 0) {
        theta.omitted = theta.omitted)
 }
 
-#' @export
-.param_to_theta <- param_to_theta
-
 kernel_to_param <- function(kernels, lambda) {
   # Convert vector of kernels to a param table.
   #
@@ -115,9 +106,6 @@ kernel_to_param <- function(kernels, lambda) {
   res
 }
 
-#' @export
-.kernel_to_param <- kernel_to_param
-
 reduce_theta <- function(theta.full, est.list) {
   # The user may specify for some of the hyperparameters to not be estimated,
   # therefore theta vector should be smaller than the full set of
@@ -163,9 +151,6 @@ reduce_theta <- function(theta.full, est.list) {
        theta.drop = theta.drop)
 }
 
-#' @export
-.reduce_theta <- reduce_theta
-
 expand_theta <- function(theta.reduced, theta.drop, theta.omitted) {
   # This convertes the reduced theta vector back to the full theta vector.
   # Useful in other functions such as theta_to_param().
@@ -182,9 +167,6 @@ expand_theta <- function(theta.reduced, theta.drop, theta.omitted) {
   theta.full
 }
 
-#' @export
-.expand_theta <- expand_theta
-
 collapse_param <- function(param) {
   # Args: A param table.
   #
@@ -208,9 +190,6 @@ collapse_param <- function(param) {
   list(param = res, na = na)
 }
 
-#' @export
-.collapse_param <- collapse_param
-
 theta_to_param <- function(theta, object) {
   # Args: A vector of parameters to be optimised, including logpsi. object must
   # be either a ipriorKernel type object, or a list containing param.na,
@@ -249,9 +228,6 @@ theta_to_param <- function(theta, object) {
   param
 }
 
-#' @export
-.theta_to_param <- theta_to_param
-
 param_translator <- function(x) {
   # Helper function in theta_to_param().
   #
@@ -268,9 +244,6 @@ param_translator <- function(x) {
   "linear"
 }
 
-#' @export
-.param_translator <- param_translator
-
 correct_pearson_kernel <- function(x, which.pearson) {
   # When using theta_to_param(), unable to identify which data x uses the
   # Pearson kernel. This helper function corrects it by reading from the logical
@@ -284,9 +257,6 @@ correct_pearson_kernel <- function(x, which.pearson) {
   x
 }
 
-#' @export
-.correct_pearson_kernel <- correct_pearson_kernel
-
 kernel_translator <- function(x, y = NULL, kernel, lam.poly = 1) {
   # Used as a helper function in get_Hl() to output list of kernel
   # matrices in kernL2() and predict(). For future expansion, add new kernels
@@ -329,9 +299,6 @@ kernel_translator <- function(x, y = NULL, kernel, lam.poly = 1) {
        call. = FALSE)
 }
 
-#' @export
-.kernel_translator <- kernel_translator
-
 theta_to_collapsed_param <- function(theta, object) {
   # This is a wrapper function for theta_to_param(). It is useful to get
   # the vector of parameters directly from theta.
@@ -343,9 +310,6 @@ theta_to_collapsed_param <- function(theta, object) {
   c(collapse_param(param)$param, theta_to_psi(theta, object))
 }
 
-#' @export
-.theta_to_collapsed_param <- theta_to_collapsed_param
-
 theta_to_psi <- function(theta, object) {
   # Obtains psi from the theta vector, or if not estimated, from the
   # ipriorKernel object.
@@ -373,9 +337,6 @@ get_hyperparam <- function(x) {
   as.numeric(unlist(strsplit(x, ","))[2])
 }
 
-#' @export
-.get_hyperparam <- get_hyperparam
-
 get_polydegree <- function(x) {
   # Obtain the degree of the polynomial kernel. Note: the exported version is
   # get_degree().
@@ -392,9 +353,6 @@ get_polydegree <- function(x) {
   degree
 }
 
-#' @export
-.get_polydegree <- get_polydegree
-
 get_kernels_from_Hl <- function(x) {
   # Obtain the kernels used to generate the list of kernel matrices.
   #
@@ -404,9 +362,6 @@ get_kernels_from_Hl <- function(x) {
   sapply(x, function(x) attributes(x)$kernel)
 }
 
-#' @export
-.get_kernels_from_Hl <- get_kernels_from_Hl
-
 get_Xl.nys <- function(object) {
   # When using the Nystrom method, we calculate the kernel matrix using
   # get_Hl(Xl, Xl.nys) which produces a smaller m x n matrix. This is the helper
@@ -427,9 +382,6 @@ get_Xl.nys <- function(object) {
   }
 }
 
-#' @export
-.get_Xl.nys <- get_Xl.nys
-
 get_Hl <- function(Xl, yl = list(NULL), kernels, lambda) {
   # Obtain the list of kernel matrices. Except for polynomial kernels, these are
   # not scaled, i.e. not Hlam matrices.
@@ -442,9 +394,6 @@ get_Hl <- function(Xl, yl = list(NULL), kernels, lambda) {
   mapply(kernel_translator, Xl, yl, kernels, lambda, SIMPLIFY = FALSE)
 }
 
-#' @export
-.get_Hl <- get_Hl
-
 expand_Hl_and_lambda <- function(Hl, lambda, intr, intr.3plus, env = NULL) {
   # Helper function to expand Hl (list of kernel matrices) and lambda (scale
   # parameters) according to any interactions specification.
@@ -485,9 +434,6 @@ expand_Hl_and_lambda <- function(Hl, lambda, intr, intr.3plus, env = NULL) {
   }
 }
 
-#' @export
-.expand_Hl_and_lambda <- expand_Hl_and_lambda
-
 BlockB_fn <- function(Hl, intr, n, p) {
   # This is the function which returns the BlockBStuff required for closed-form
   # EM algorithm.
diff --git a/R/Utilities.R b/R/Utilities.R
index d1dae8e..4db2aba 100644
--- a/R/Utilities.R
+++ b/R/Utilities.R
@@ -170,9 +170,6 @@ is.ipriorKernel_cv <- function(x) {
   }
 }
 
-#' @export
-.is.ipriorKernel_cv <- is.ipriorKernel_cv
-
 #' @rdname is.iprior_x
 #' @export
 is.nystrom <- is.ipriorKernel_nys
@@ -189,9 +186,6 @@ is.categorical <- function(x) {
   !is.null(x$y.levels)
 }
 
-#' @export
-.is.categorical <- is.categorical
-
 #' Test kernel attributes
 #'
 #' Test whether an object uses a specific type of kernel.
@@ -323,12 +317,6 @@ get_y_and_levels <- function(y) {
   list(y = as.numeric(y), levels = levels(y))
 }
 
-#' @export
-.checkLevels <- get_y_and_levels
-
-#' @export
-.get_y_and_levels <- get_y_and_levels
-
 fix_call_default <- function(cl = match.call(), new.name = "iprior") {
   # Replace the default call name with a new name. When using the default call,
   # it is possible that some of the X names are blank. This fixes that too.
@@ -343,9 +331,6 @@ fix_call_default <- function(cl = match.call(), new.name = "iprior") {
   cl
 }
 
-#' @export
-.fix_call_default <- fix_call_default
-
 fix_call_formula <- function(cl = match.call(), new.name = "iprior") {
   # Replace the formula call name with a new name.
   #
@@ -356,9 +341,6 @@ fix_call_formula <- function(cl = match.call(), new.name = "iprior") {
   cl
 }
 
-#' @export
-.fix_call_formula <- fix_call_formula
-
 formula_to_xy <- function(formula, data, one.lam) {
   # Convert formula entry to y, X entry.
   #
@@ -400,9 +382,6 @@ formula_to_xy <- function(formula, data, one.lam) {
        tt = tt)
 }
 
-#' @export
-.formula_to_xy <- formula_to_xy
-
 deal_with_one.lam <- function(x, interactions) {
   # Helper function to convert list of X according to one.lam option.
   #
@@ -430,9 +409,6 @@ deal_with_one.lam <- function(x, interactions) {
   list(x = x, xname = xname)
 }
 
-#' @export
-.deal_with_one.lam <- deal_with_one.lam
-
 terms_to_xy <- function(object, newdata) {
   # Args: An ipriorKernel object.
   tt <- object$terms
@@ -452,9 +428,6 @@ terms_to_xy <- function(object, newdata) {
   list(Xl = x, y = y)
 }
 
-#' @export
-.terms_to_xy <- terms_to_xy
-
 fastSquareRoot2 <- function(x) {
   # Function to quickly find a square root of a matrix from its
   # eigendecomposition.
diff --git a/R/iprior-package.R b/R/iprior-package.R
index 06a89e4..d81bb7c 100644
--- a/R/iprior-package.R
+++ b/R/iprior-package.R
@@ -31,7 +31,11 @@
 #'
 #'   Contributors: \itemize{\item{Wicher Bergsma}}
 #'
-#' @seealso \url{http://phd.haziqj.ml/}
-#'
+#' @seealso \url{https://phd.haziqj.ml/}
 #' @keywords internal
+#' @aliases iprior-package
 "_PACKAGE"
+
+## usethis namespace: start
+## usethis namespace: end
+NULL
diff --git a/R/iprior_helper.R b/R/iprior_helper.R
index 2511c86..3d1933b 100644
--- a/R/iprior_helper.R
+++ b/R/iprior_helper.R
@@ -67,9 +67,6 @@ iprior_method_checker <- function(object, method) {
   res
 }
 
-#' @export
-.iprior_method_checker <- iprior_method_checker
-
 update_control <- function(arg.list, default.list) {
   # In most of the iprior_x functions, a list of control options is required.
   # This helper function checks whether the list supplied contains the allowed
@@ -88,9 +85,6 @@ update_control <- function(arg.list, default.list) {
   default.list
 }
 
-#' @export
-.update_control <- update_control
-
 convert_se <- function(se, theta, object) {
   # Converts the standard errors for theta into the standard errors for param
   # using the delta method. These are then used in the summary() method for
@@ -117,9 +111,6 @@ convert_se <- function(se, theta, object) {
   res
 }
 
-#' @export
-.convert_se <- convert_se
-
 get_Hlam <- function(object, theta, theta.is.lambda = FALSE) {
   # Obtain the scaled kernel matrix Hlam.
   #
@@ -204,15 +195,6 @@ calc_Hlam <- function(Hl, lambda, object) {
   res
 }
 
-#' @export
-.get_Hlam <- get_Hlam
-
-#' @export
-.get_Htildelam <- get_Htildelam
-
-#' @export
-.calc_Hlam <- calc_Hlam
-
 eigen_Hlam <- function(Hlam, env = NULL) {
   # The routine for the eigendecomposition of the scaled kernel matrix.
   #
@@ -227,9 +209,6 @@ eigen_Hlam <- function(Hlam, env = NULL) {
   else list2env(res, env)
 }
 
-#' @export
-.eigen_Hlam <- eigen_Hlam
-
 eigen_Hlam_nys <- function(Hlam, env = NULL) {
   # The routine for the eigendecomposition of the scaled kernel matrix using
   # Nystrom approximation.
@@ -261,9 +240,6 @@ eigen_Hlam_nys <- function(Hlam, env = NULL) {
   else list2env(res, env)
 }
 
-#' @export
-.eigen_Hlam_nys <- eigen_Hlam_nys
-
 A_times_a <- function(u, V, a) {
   # Calculate A %*% a from the eigendecomposition of A. Mostly used to calculate
   # Vy^{-1} %*% a without having to invert Vy, because the eigendecompostion of
@@ -275,9 +251,6 @@ A_times_a <- function(u, V, a) {
   (V * rep(u, each = nrow(V))) %*% crossprod(V, a)
 }
 
-#' @export
-.A_times_a <- A_times_a
-
 em_loop_logical <- function() {
   # Helper function to determine when to stop the while loop for the EM
   # algorithm.
@@ -304,9 +277,6 @@ em_loop_logical <- function() {
   }
 }
 
-#' @export
-.em_loop_logical <- em_loop_logical
-
 get_w <- function(u, V, Vy.inv.y, psi) {
   # Helper function to obtain posterior mean of I-prior random effects. It is
   # calculated as psi * Hlam %*% Vy.inv %*% y.
diff --git a/README.md b/README.md
index fa72760..c40385e 100644
--- a/README.md
+++ b/README.md
@@ -2,7 +2,7 @@
 
 <!-- badges: start -->
 [![R-CMD-check](https://github.com/haziqj/iprior/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/haziqj/iprior/actions/workflows/R-CMD-check.yaml)
-[![codecov](https://codecov.io/gh/haziqj/iprior/graph/badge.svg?token=W4xTtuyt6r)](https://codecov.io/gh/haziqj/iprior)
+[![codecov](https://codecov.io/gh/haziqj/iprior/graph/badge.svg?token=W4xTtuyt6r)](https://app.codecov.io/gh/haziqj/iprior)
 [![CRAN_Status_Badge_version_ago](http://www.r-pkg.org/badges/version-ago/iprior)](https://cran.r-project.org/package=iprior)
 [![CRAN downloads](http://cranlogs.r-pkg.org/badges/grand-total/iprior)](https://cran.r-project.org/package=iprior)
 <!-- badges: end -->
@@ -21,7 +21,7 @@ The package estimates these parameters using direct log-likelihood maximisation,
 While the main interest of I-prior modelling is prediction, inference is also possible, e.g. via log-likelihood ratio tests.
 
 For installation instructions and some examples of I-prior modelling, continue reading below. 
-The package is documented with help files, and the [vignette](http://phd.haziqj.ml/iprior_paper.pdf) provides an introduction to the concept of I-priors and also to using the package.
+The package is documented with help files, and the [vignette](https://phd.haziqj.ml/iprior_paper.pdf) provides an introduction to the concept of I-priors and also to using the package.
 
 ## Installation
 
@@ -38,7 +38,7 @@ or the developmental version from this GitHub repository. R/iprior makes use of
 -   On Mac, install Xcode from the app store.
 -   On Linux, `sudo apt-get install r-base-dev` or similar.
 
-The easiest way to then install from this repo is by using the [devtools](https://github.com/hadley/devtools) package. 
+The easiest way to then install from this repo is by using the [devtools](https://github.com/r-lib/devtools) package. 
 Install this first.
 
 ``` r
diff --git a/man/iprior-package.Rd b/man/iprior-package.Rd
index 3aeec3e..d2c3183 100644
--- a/man/iprior-package.Rd
+++ b/man/iprior-package.Rd
@@ -3,6 +3,7 @@
 \docType{package}
 \name{iprior-package}
 \alias{iprior-package}
+\alias{_PACKAGE}
 \title{\code{iprior}: Regression using priors with Fisher information covariance
 kernels.}
 \description{
@@ -19,7 +20,7 @@ log-likelihood or an EM algorithm.
 }
 
 \seealso{
-\url{http://phd.haziqj.ml/}
+\url{https://phd.haziqj.ml/}
 }
 \author{
 \strong{Maintainer}: Haziq Jamil \email{haziq.jamil@gmail.com}
diff --git a/man/kernel.Rd b/man/kernel.Rd
index 7f9ddb1..f554cc5 100644
--- a/man/kernel.Rd
+++ b/man/kernel.Rd
@@ -78,5 +78,5 @@ kern_fbm(1:5, 1:3, gamma = 0.7)
 
 }
 \references{
-\url{http://phd.haziqj.ml/intro/}
+\url{https://phd.haziqj.ml/intro/}
 }
diff --git a/vignettes/tecator.Rmd b/vignettes/tecator.Rmd
index 17966be..42375e8 100644
--- a/vignettes/tecator.Rmd
+++ b/vignettes/tecator.Rmd
@@ -14,7 +14,7 @@ vignette: >
 library(iprior)
 ```
 
-Continuing on Section 3.4 of the [vignette](http://phd.haziqj.ml/iprior_paper.pdf), we revisit the code used to obtain out-of-sample test error rates, and extend the analysis to a leave-one-out cross-validation (LOOCV) scheme.
+Continuing on Section 3.4 of the [vignette](https://phd.haziqj.ml/iprior_paper.pdf), we revisit the code used to obtain out-of-sample test error rates, and extend the analysis to a leave-one-out cross-validation (LOOCV) scheme.
 
 # Easy train/test split