documentation update

.Rbuildignore

@@ -1,3 +1,6 @@
+.Rprofile
+^renv$
+^renv\.lock$
 ^codecov\.yml$
 ^_pkgdown\.yml$
 ^.*\.Rproj$
@@ -24,3 +27,5 @@ CONTRIBUTING.md
 
 ^CRAN-RELEASE$
 ^cran-comments\.md$
+^doc$
+^Meta$

.Rprofile

@@ -0,0 +1 @@
+source("renv/activate.R")

.gitignore

@@ -4,3 +4,6 @@
 .Ruserdata
 /.Rapp.history
 internal/
+/doc/
+/Meta/
+renv

DESCRIPTION

@@ -24,7 +24,7 @@ Depends:
  R (>= 3.5.0)
 License: GPL-3
 Encoding: UTF-8
-RoxygenNote: 7.1.2
+RoxygenNote: 7.2.1
 VignetteBuilder: knitr
 BugReports: https://github.com/simulatr/simrel/issues
 URL: https://simulatr.github.io/simrel/
@@ -35,20 +35,21 @@ Imports:
  gridExtra,
  jsonlite,
  magrittr,
+ methods,
  miniUI,
  purrr,
  reshape2,
+ rlang,
  rstudioapi,
  scales,
  sfsmisc,
  shiny,
+ testthat,
  tibble,
- tidyr,
- rlang,
- testthat
+ tidyr
 Suggests: 
+ DoE.base,
  covr,
  knitr,
- pls,
  markdown,
- DoE.base
+ pls

R/ggsimrelplot.R

@@ -9,7 +9,7 @@
 #' @param use_population Logical, TRUE if population values should be used and FALSE if sample values should be used
 #' @return A list of plots
 #' @examples
-#' sim.obj <- simrel(n = 100, p = 16, q = c(3, 4, 5),
+#' sim.obj <- simrel(n = 50, p = 16, q = c(3, 4, 5),
 #' relpos = list(c(1, 2), c(3, 4), c(5, 7)), m = 5,
 #' ypos = list(c(1, 4), 2, c(3, 5)), type = "multivariate",
 #' R2 = c(0.8, 0.7, 0.9), gamma = 0.8)

R/simrel.r

@@ -1,37 +1,80 @@
 #' Simulation of Multivariate Linear Model Data
 #' @param n Number of observations.
 #' @param p Number of variables.
-#' @param q An integer for univariate, a vector of 3 integers for bivariate and 3 or more for multivariate simulation (for details see Notes).
-#' @param relpos A list (vector in case of univariate simulation) of position of relevant component for predictor variables corresponding to each response.
-#' @param gamma A declining (decaying) factor of eigenvalues of predictors (X). Higher the value of \code{gamma}, the decrease of eigenvalues will be steeper.
-#' @param R2 Vector of coefficient of determination (proportion of variation explained by predictor variable) for each relevant response components.
-#' @param type Type of simulation - \code{univariate}, \code{bivariate} and \code{multivariate}
-#' @param ... Since this is a wrapper function to simulate univariate, bivariate or multivariate, it calls their respective function. This parameter should contain all the necessary arguements for respective simulations. See \code{\link{unisimrel}}, \code{\link{bisimrel}} and \code{\link{multisimrel}}
-#' @return A simrel object with all the input arguments along with following additional items.
-#' \item{X}{Simulated predictors}
-#' \item{Y}{Simulated responses}
-#' \item{W}{Simulated predictor components}
-#' \item{Z}{Simulated response components}
-#' \item{beta}{True regression coefficients}
-#' \item{beta0}{True regression intercept}
-#' \item{relpred}{Position of relevant predictors}
-#' \item{testX}{Test Predictors}
-#' \item{testY}{Test Response}
-#' \item{testW}{Test predictor components}
-#' \item{testZ}{Test response components}
-#' \item{minerror}{Minimum model error}
-#' \item{Xrotation}{Rotation matrix of predictor (R)}
-#' \item{Yrotation}{Rotation matrix of response (Q)}
-#' \item{type}{Type of simrel object \emph{univariate} or \emph{multivariate}}
-#' \item{lambda}{Eigenvalues of predictors}
-#' \item{SigmaWZ}{Variance-Covariance matrix of components of response and predictors}
-#' \item{SigmaWX}{Covariance matrix of response components and predictors}
-#' \item{SigmaYZ}{Covariance matrix of response and predictor components}
-#' \item{Sigma}{Variance-Covariance matrix of response and predictors}
-#' \item{RsqW}{Coefficient of determination corresponding to response components}
-#' \item{RsqY}{Coefficient of determination corresponding to response variables}
+#' @param q Number of predictors related to each relevant components
+#' An integer for univariate, a vector of 3 integers for bivariate and 3 or
+#' more for multivariate simulation (for details see Notes).
+#' @param relpos A list (vector in case of univariate simulation) of position
+#' of relevant component for predictor variables corresponding
+#' to each response.
+#' @param gamma A declining (decaying) factor of eigenvalues of predictors (X).
+#' Higher the value of \code{gamma}, the decrease of eigenvalues
+#' will be steeper.
+#' @param R2 Vector of coefficient of determination (proportion of variation
+#' explained by predictor variable) for each relevant response components.
+#' @param type Type of simulation - \code{univariate}, \code{bivariate} and
+#' \code{multivariate}
+#' @param ... Since this is a wrapper function to simulate univariate,
+#' bivariate or multivariate, it calls their respective function.
+#' This parameter should contain all the necessary arguements for respective
+#' simulations. See \code{\link{unisimrel}}, \code{\link{bisimrel}} and
+#' \code{\link{multisimrel}}
+#' @return A simrel object with all the input arguments along with 
+#' following additional items. For more detail on the return values see the
+#' individual simulation functions \code{\link{unisimrel}}, 
+#' \code{\link{bisimrel}} and \code{\link{multisimrel}}.
+#' 
+#' \strong{Common returns from univariate, bivariate and multivariate simulation:}
+#' 
+#' \item{call}{the matched call}
+#' \item{X}{simulated predictors}
+#' \item{Y}{simulated responses}
+#' \item{beta}{true regression coefficients}
+#' \item{beta0}{true regression intercept}
+#' \item{relpred}{position of relevant predictors}
+#' \item{n}{number of observations}
+#' \item{p}{number of predictors (as supplied in the arguments)}
+#' \item{p}{number of responses (as supplied in the arguments)}
+#' \item{q}{number of relevant predictors (as supplied in the arguments)}
+#' \item{gamma}{declining factor of eigenvalues of predictors 
+#' (as supplied in the arguments)}
+#' \item{lambda}{eigenvalues corresponding to the predictors}
+#' \item{R2}{theoretical R-squared value (as supplied in the arguments)}
+#' \item{relpos}{position of relevant components (as supplied in the arguments)}
+#' \item{minerror}{minimum model error}
+#' \item{Sigma}{variance-Covariance matrix of response and predictors}
+#' \item{testX}{simulated test predictor (in univarite simulation \code{TESTX})}
+#' \item{testY}{simulated test response (in univarite simulation \code{TESTY})}
+#' \item{Rotation}{Random rotation matrix used to rotate latent components. Is 
+#' equivalent to the transpose of eigenvector-matrix. In multivariate
+#' simulation, \code{Xrotation} (R) and \code{Yrotation} (Q) refers to this matrix
+#' corresponding to the predictor and response.}
+#' \item{type}{type of simrel object \code{univariate}, \code{bivariate} or 
+#' \emph{multivariate}}
+#' 
+#' \strong{Returns from multivariate simulation:}
+#' 
+#' \item{eta}{a declining factor of eigenvalues of response (Y)
+#' (as supplied in the arguments)}
+#' \item{ntest}{number of simulated test observations}
+#' \item{W}{simulated response components}
+#' \item{Z}{simulated predictor components}
+#' \item{testW}{test predictor components}
+#' \item{testZ}{test response components}
+#' \item{SigmaWZ}{Variance-Covariance matrix of components of response and predictors}
+#' \item{SigmaWX}{Covariance matrix of response components and predictors}
+#' \item{SigmaYZ}{Covariance matrix of response and predictor components}
+#' \item{RsqW}{Coefficient of determination corresponding to response components}
+#' \item{RsqY}{Coefficient of determination corresponding to response variables}
+#' 
 #' @concept simulation 
 #' @concept linear model data
+#' @note The parameter \code{q} represents the number of predictor variables 
+#' that forms a basis for each of the relevant components. For example,
+#' for \code{q = 8} and relevant components 1, 2, and 3 specified by 
+#' parameter \code{relpos} then the randomly selected 8 predictor variables 
+#' forms basis for these three relevant components and thus in the model 
+#' these 8 predictors will be relevant for the response (outcome).
 #' @keywords datagen
 #' @references Sæbø, S., Almøy, T., & Helland, I. S. (2015). simrel—A versatile tool for linear model data simulation based on the concept of a relevant subspace and relevant predictors. Chemometrics and Intelligent Laboratory Systems, 146, 128-135.
 #' @references Almøy, T. (1996). A simulation study on comparison of prediction methods when only a few components are relevant. Computational statistics & data analysis, 21(1), 87-107.
@@ -103,7 +146,7 @@ simrel <- function (n, p, q, relpos, gamma, R2, type = "univariate", ...) {
  stopMsg <-
  append(stopMsg, "Decaying factor of eigenvalues in univariate simulation must be specified by a number between 0 and 1.")
  if (!is.null(sim))
- if (class(sim) == "simrel") stopMsg <- append(stopMsg, "Unknown simulation object.")
+ if (methods::is(sim, "simrel")) stopMsg <- append(stopMsg, "Unknown simulation object.")
  if (!is.null(muX))
  if (length(muX) != p) stopMsg <- append(stopMsg, "Please input mean vector of correct dimension.")
 

_pkgdown.yml

@@ -1,8 +1,8 @@
 authors:
  Raju Rimal:
- href: http://mathatistics.com
+ href: https://mathatistics.com
  Solve Sæbø:
- href: http://solvsa.nmbu.no
+ href: https://solvsa.nmbu.no
 navbar:
  right:
  - icon: fa-github fa-lg