Fix documentation

Author: lbelzile

DESCRIPTION

@@ -1,9 +1,8 @@
 Package: TruncatedNormal
 Type: Package
 Title: Truncated Multivariate Normal and Student Distributions
-Version: 2.2.2.9001
-Date: 2022-05-13
-Authors@R: c(person(given="Zdravko", family="Botev", role = "aut", email = "botev@unsw.edu.au", comment = c(ORCID = "0000-0001-9054-3452")), person(given="Leo", family="Belzile", role = c("aut", "cre"), email = "belzilel@gmail.com", comment = c(ORCID = "0000-0002-9135-014X"))), person(given="Anthony", family="Vankus", role = c("aut", "cre"))
+Version: 2.2.4.0001
+Authors@R: c(person(given="Zdravko", family="Botev", role = "aut", email = "botev@unsw.edu.au", comment = c(ORCID = "0000-0001-9054-3452")), person(given="Leo", family="Belzile", role = c("aut", "cre"), email = "belzilel@gmail.com", comment = c(ORCID = "0000-0002-9135-014X")))
 Description: A collection of functions to deal with the truncated univariate and multivariate normal and Student distributions, described in Botev (2017) <doi:10.1111/rssb.12162> and Botev and L'Ecuyer (2015) <doi:10.1109/WSC.2015.7408180>.
 License: GPL-3
 BugReports:
@@ -17,7 +16,7 @@ Imports:
 LinkingTo: 
     Rcpp, 
     RcppArmadillo
-RoxygenNote: 7.1.1
+RoxygenNote: 7.2.3
 VignetteBuilder: knitr
 Encoding: UTF-8
 Suggests: 

R/RcppExports.R

@@ -71,10 +71,10 @@ lnNpr <- function(a, b, check = TRUE) {
 #' @keywords internal
 #' @return a list with components
 #' \itemize{
-#' \item{\code{L}: }{Cholesky root}
-#' \item{\code{l}: }{permuted vector of lower bounds}
-#' \item{\code{u}: }{permuted vector of upper bounds}
-#' \item{\code{perm}: }{vector of integers with ordering of permutation}
+#' \item \code{L}: Cholesky root
+#' \item \code{l}: permuted vector of lower bounds
+#' \item \code{u}: permuted vector of upper bounds
+#' \item \code{perm}: vector of integers with ordering of permutation
 #' }
 #' @references Genz, A. and Bretz, F. (2009). Computations of Multivariate Normal and t Probabilities, volume 105. Springer, Dordrecht.
 #' @references Gibson G.J., Glasbey C.A. and D.A. Elton (1994).  Monte Carlo evaluation of multivariate normal integrals and sensitivity to variate ordering. In: Dimon et al., Advances in Numerical Methods and Applications, WSP, pp. 120-126.
@@ -99,10 +99,10 @@ lnNpr <- function(a, b, check = TRUE) {
 #' @keywords internal
 #' @return a list with components
 #' \itemize{
-#' \item{\code{L}: }{Cholesky root}
-#' \item{\code{l}: }{permuted vector of lower bounds}
-#' \item{\code{u}: }{permuted vector of upper bounds}
-#' \item{\code{perm}: }{vector of integers with ordering of permutation}
+#' \item \code{L}: Cholesky root
+#' \item \code{l}: permuted vector of lower bounds
+#' \item \code{u}: permuted vector of upper bounds
+#' \item \code{perm}: vector of integers with ordering of permutation
 #' }
 #' @references Genz, A. and Bretz, F. (2009). Computations of Multivariate Normal and t Probabilities, volume 105. Springer, Dordrecht.
 #' @references Gibson G.J., Glasbey C.A. and D.A. Elton (1994).  Monte Carlo evaluation of multivariate normal integrals and sensitivity to variate ordering. In: Dimon et al., Advances in Numerical Methods and Applications, WSP, pp. 120-126.

R/cholperm.R

@@ -15,10 +15,10 @@
 #' @param method string indicating which method to use. Default to \code{"GGE"}
 #' @return a list with components
 #' \itemize{
-#' \item{\code{L}: }{Cholesky root}
-#' \item{\code{l}: }{permuted vector of lower bounds}
-#' \item{\code{u}: }{permuted vector of upper bounds}
-#' \item{\code{perm}: }{vector of integers with ordering of permutation}
+#' \item \code{L}: Cholesky root
+#' \item \code{l}: permuted vector of lower bounds
+#' \item \code{u}: permuted vector of upper bounds
+#' \item \code{perm}: vector of integers with ordering of permutation
 #' }
 #' @export
 #' @references Genz, A. and Bretz, F. (2009). Computations of Multivariate Normal and t Probabilities, volume 105. Springer, Dordrecht.
@@ -30,4 +30,4 @@ cholperm <- function(Sigma, l, u, method = c("GGE", "GB")){
   } else{
     .cholpermGB(Sigma = Sigma, l = l, u = u)
   }
-}
+}

R/mvNcdf.R

@@ -19,9 +19,9 @@
 #'  where \eqn{Y} is drawn from \eqn{N(0, A\Sigma A^\top)}.
 #' @return  a list with components
 #' \itemize{
-#' \item{\code{prob}: }{estimated value of probability Pr\eqn{(l<X<u)}}
-#' \item{\code{relErr}: }{estimated relative error of estimator} 
-#' \item{\code{upbnd}: }{ theoretical upper bound on true Pr\eqn{(l<X<u)}} 
+#' \item\code{prob}: estimated value of probability Pr\eqn{(l<X<u)}
+#' \item\code{relErr}: estimated relative error of estimator
+#' \item\code{upbnd}: theoretical upper bound on true Pr\eqn{(l<X<u)}
 #' }  
 #' @author Zdravko I. Botev
 #' @export

R/mvNqmc.R

@@ -16,9 +16,9 @@
 #'  where \eqn{Y} is drawn from \eqn{N(0, A\Sigma A^\top)}.
 #' @return  a list with components
 #' \itemize{
-#' \item{\code{prob}: }{estimated value of probability Pr\eqn{(l<X<u)}}
-#' \item{\code{relErr}: }{estimated relative error of estimator}
-#' \item{\code{upbnd}: }{ theoretical upper bound on true Pr\eqn{(l<X<u)}}
+#' \item \code{prob}: estimated value of probability Pr\eqn{(l<X<u)}
+#' \item \code{relErr}: estimated relative error of estimator
+#' \item \code{upbnd}: theoretical upper bound on true Pr\eqn{(l<X<u)}
 #' }
 #' @author Zdravko I. Botev
 #' @references Z. I. Botev (2017), \emph{The Normal Law Under Linear Restrictions:

R/mvTcdf.R

@@ -11,9 +11,9 @@
 #' @inheritParams mvrandt
 #' @return a list with components
 #' \itemize{
-#' \item{\code{prob}: }{estimated value of probability Pr\eqn{(l<X<u)} }
-#' \item{\code{relErr}: }{estimated relative error of estimator}
-#' \item{\code{upbnd}: }{theoretical upper bound on true Pr\eqn{(l<X<u)} }
+#' \item \code{prob}: estimated value of probability Pr\eqn{(l<X<u)}
+#' \item \code{relErr}: estimated relative error of estimator
+#' \item \code{upbnd}: theoretical upper bound on true Pr\eqn{(l<X<u)}
 #'}
 #' @note If you want to estimate Pr\eqn{(l<Y<u)},
 #' where \eqn{Y} follows a Student distribution with \code{df} degrees of freedom,

R/mvTqmc.R

@@ -14,9 +14,9 @@
 #' @inheritParams mvrandt
 #' @return a list with components
 #' \itemize{
-#' \item{\code{prob}: }{estimated value of probability Pr\eqn{(l<X<u)}}
-#' \item{\code{relErr}: }{estimated relative error of estimator}
-#' \item{\code{upbnd}: }{theoretical upper bound on true Pr\eqn{(l<X<u)} }
+#' \item \code{prob}: estimated value of probability Pr\eqn{(l<X<u)}
+#' \item \code{relErr}: estimated relative error of estimator
+#' \item \code{upbnd}: theoretical upper bound on true Pr\eqn{(l<X<u)}
 #'}
 #' @note If you want to estimate Pr\eqn{(l<Y<u)},
 #' where \eqn{Y} follows a Student distribution with \code{df} degrees of freedom,

R/mvrandn.R

@@ -11,20 +11,20 @@
 #' @param mu location parameter
 #' @details
 #' \itemize{
-#' \item{Bivariate normal:}{
+#' \item Bivariate normal:
 #' Suppose we wish to simulate a bivariate \eqn{X} from \eqn{N(\mu,\Sigma)}, conditional on
 #' \eqn{X_1-X_2<-6}. We can recast this as the problem of simulation
 #' of \eqn{Y} from \eqn{N(0,A\Sigma A^\top)} (for an appropriate matrix \eqn{A})
 #' conditional on \eqn{l-A\mu < Y < u-A\mu} and then setting \eqn{X=\mu+A^{-1}Y}.
-#'    See the example code below.}
-#'  \item{Exact posterior simulation for Probit regression:}{Consider the
+#'    See the example code below.
+#'  \item Exact posterior simulation for Probit regression: Consider the
 #'      Bayesian Probit Regression model applied to the \code{\link{lupus}} dataset.
 #'      Let the prior for the regression coefficients \eqn{\beta} be \eqn{N(0,\nu^2 I)}. Then, to simulate from the Bayesian
 #'      posterior exactly, we first simulate
 #'      \eqn{Z} from \eqn{N(0,\Sigma)}, where  \eqn{\Sigma=I+\nu^2 X X^\top,}
 #'      conditional on \eqn{Z\ge 0}. Then, we simulate the posterior regression coefficients, \eqn{\beta}, of the Probit regression
 #'      by drawing \eqn{(\beta|Z)} from \eqn{N(C X^\top Z,C)}, where \eqn{C^{-1}=I/\nu^2+X^\top X}.
-#' See the example code below.}
+#' See the example code below.
 #' }
 #' @return a \eqn{d} by \eqn{n} matrix storing the random vectors, \eqn{X}, drawn from \eqn{N(0,\Sigma)}, conditional on \eqn{l<X<u};
 #' @note The algorithm may not work or be very inefficient if \eqn{\Sigma} is close to being rank deficient.

R/tmvnorm.R

@@ -75,7 +75,7 @@ NULL
 #' @export
 #' @keywords internal
 dtmvnorm <- function(x, mu, sigma, lb, ub, log = FALSE, type = c("mc", "qmc"), B = 1e4, check = TRUE, ...){
-  if (any(missing(x), missing(mu), missing(sigma))) {
+  if (isTRUE(any(missing(x), missing(mu), missing(sigma)))) {
     stop("Arguments missing in function call to `dtmvnorm`")
   }
   sigma <- as.matrix(sigma)
@@ -168,15 +168,15 @@ ptmvnorm <- function(q, mu, sigma, lb, ub, log = FALSE, type = c("mc", "qmc"), B
   if(missing(ub)){
     ub <- rep(Inf, d) 
   }
-  stopifnot(all(lb < ub))
+  stopifnot(isTRUE(all(lb < ub)))
   prob <- rep(0, nrow(q))
   kst <- switch(type,
                 mc = mvNcdf(l = lb - mu, u = ub - mu, Sig = sigma, n = B)$prob,
                 qmc = mvNqmc(l = lb - mu, u = ub - mu, Sig = sigma, n = B)$prob)
   for(i in 1:nrow(q)){
-    if(all(q[i,] >= ub)){
+    if(isTRUE(all(q[i,] >= ub))){
       prob[i] <- ifelse(log, 0, 1)
-    } else if(any(q[i,] <= lb)){
+    } else if(isTRUE(any(q[i,] <= lb))){
       prob[i] <- ifelse(log, -Inf, 0)
     } else{
       pb <- switch(type,
@@ -224,7 +224,7 @@ rtmvnorm <- function(n, mu, sigma, lb, ub, check = TRUE, ...){
     ub <- rep(Inf, d) 
   }
   stopifnot(length(lb) == length(ub), length(lb) == d, lb <= ub)
-  if(!any((ub - lb) < 1e-10)){
+  if(isTRUE(!any((ub - lb) < 1e-10))){
     if(n == 1){
       as.vector(mvrandn(l = lb, u = ub, Sig = sigma, n = n, mu = mu)) 
     } else{