Ajout des return() et update du namespace avec roxygen

NAMESPACE

@@ -1,8 +1,7 @@
-export(covariance.GMM,
-delta.method.covariance.GMM,
-fourmoments.gmm.vector,
-iterative.GMM,
-mean.variance.gmm.vector,
-objective.GMM,
-optim.GMM
-)
+export(covariance.GMM)
+export(delta.method.covariance.GMM)
+export(fourmoments.gmm.vector)
+export(iterative.GMM)
+export(meanvariance.gmm.vector)
+export(objective.GMM)
+export(optim.GMM)

R/covariance.GMM.R

@@ -11,7 +11,7 @@
 #' @param sample Individual data sample
 #' @param ... Functions of the vector of moment conditions
 #' @return A square covariance matrix
-#' 
+#' @export covariance.GMM
 #' @author François Pelletier
 covariance.GMM <- function(conditions.vector,param,sample...)
 {

R/delta.method.covariance.GMM.R

@@ -11,7 +11,7 @@
 #' @param gradient Gradient matrix of the moment conditions
 #' @param size Sample size
 #' @return The covariance matrix of the parameters
-#'
+#' @export delta.method.covariance.GMM
 #' @author François Pelletier
 delta.method.covariance.GMM <- function(covariance,gradient,size)
 {

R/fourmoments.gmm.vector.R

@@ -13,7 +13,7 @@
 #' @param skewnessf Skewness function
 #' @param kurtosisf Kurtosis function
 #' @return A four column matrix of differences
-#' 
+#' @export fourmoments.gmm.vector
 #' @author François Pelletier
 fourmoments.gmm.vector <- function(param,sample,meanf,variancef,skewnessf,kurtosisf)
 {

R/iterative.GMM.R

@@ -17,7 +17,7 @@
 #' @param max.iter Maximum number of iterations
 #' @param epsilon Minimum precision level
 #' @return A list containing the optimized vector of parameter and corresponding covariance matrix
-#' 
+#' @export iterative.GMM
 #' @author François Pelletier
 iterative.GMM <- function(start,conditions.vector,sample,...,
 		W,R,r,max.iter=50,epsilon=1E-6)

R/mean.variance.gmm.vector.R

@@ -12,9 +12,9 @@
 #' @param meanf Mean function
 #' @param variancef Variance function
 #' @return A two column matrix of differences
-#' 
+#' @export meanvariance.gmm.vector
 #' @author François Pelletier
-mean.variance.gmm.vector <- function(param,sample,meanf,variancef)
+meanvariance.gmm.vector <- function(param,sample,meanf,variancef)
 {
 	cbind(X-meanf(param),(X-meanf(param))^2 - variancef(param))
 }

R/objective.GMM.R

@@ -14,7 +14,7 @@
 #' @param R Linear constraint matrix of coefficients
 #' @param r Linear constraint constants
 #' @return A scalar value
-#' 
+#' @export objective.GMM
 #' @author François Pelletier
 objective.GMM <- function(param.lagrangian,conditions.vector,sample,...,
 		W=diag(length(conditions.vector)),R=0,r=0)

R/optim.GMM.R

@@ -8,7 +8,7 @@
 #' @param R Linear constraint matrix of coefficients
 #' @param r Linear constraint constants
 #' @return une liste contenant le résultat de l'optimisation
-#' 
+#' @export optim.GMM
 #' @author François Pelletier
 optim.GMM <- function(start,conditions.vector,sample,...,W,R,r)
 {

man/meanvariance.gmm.vector.Rd

@@ -1,8 +1,8 @@
-\name{mean.variance.gmm.vector}
-\alias{mean.variance.gmm.vector}
+\name{meanvariance.gmm.vector}
+\alias{meanvariance.gmm.vector}
 \title{GMM vector for mean and variance moment conditions}
 \usage{
-\method{mean}{variance.gmm.vector}(param, sample, meanf, variancef)
+meanvariance.gmm.vector(param, sample, meanf, variancef)
 }
 \arguments{
   \item{param}{Estimated parameters}