revised description and help files

DESCRIPTION

@@ -4,11 +4,11 @@ Version: 0.3.1.9000
 Authors@R: 
     person("Ang", "Yu", , "ang_yu@outlook.com", role = c("aut", "cre", "cph"),
            comment = c(website = "<https://ang-yu.github.io/>", ORCID = "0000-0002-1828-0165"))
-Description: The causal decompositions of group disparities developed by
+Description: The framework of causal decomposition of group disparities developed by
     Yu and Elwert (2023)
-    <https://ang-yu.github.io/files/Causal_Decomposition_of_Group_Disparities_2023.pdf>.
-    This package implements the estimators for the decomposition
-    components that are based on efficient influence functions. For the
+    <https://arxiv.org/abs/2306.16591>.
+    This package implements the decomposition estimators
+    that are based on efficient influence functions. For the
     nuisance functions of the estimators, both parametric and
     nonparametric options are provided, as well as manual options in case
     the default models are not satisfying.

NEWS.md

@@ -1,5 +1,9 @@
 # cdgd (development version)
 
+# cdgd 0.3.2
+
+* Revised package description and help files. No change in the actual code.  
+
 # cdgd 0.3.1
 
 * Fixed an issue that prevents the ranger option from working when there is only one Q variable.

R/cdgd0_manual.R

@@ -5,7 +5,7 @@
 #' For the unconditional decomposition, three nuisance functions (YgivenGX.Pred_D0, YgivenGX.Pred_D1, and DgivenGX.Pred) need to be estimated.
 #' The nuisance functions should be estimated using cross-fitting if Donsker class is not assumed.
 #'
-#' @param Y Outcome. The name of a continuous variable.
+#' @param Y Outcome. The name of a numeric variable.
 #' @param D Treatment status. The name of a binary numeric variable taking values of 0 and 1.
 #' @param G Advantaged group membership. The name of a binary numeric variable taking values of 0 and 1.
 #' @param YgivenGX.Pred_D0 A numeric vector of predicted Y values given X, G, and D=0. Vector length=nrow(data).

R/cdgd0_ml.R

@@ -3,10 +3,10 @@
 
 #' Perform unconditional decomposition via machine learning
 #'
-#' @param Y Outcome. The name of a continuous variable.
+#' @param Y Outcome. The name of a numeric variable.
 #' @param D Treatment status. The name of a binary numeric variable taking values of 0 and 1.
 #' @param G Advantaged group membership. The name of a binary numeric variable taking values of 0 and 1.
-#' @param X Confounders. The vector of the names of numeric variables.
+#' @param X Confounders. A vector of names of numeric variables.
 #' @param data A data frame.
 #' @param algorithm The ML algorithm for modelling. "nnet" for neural network, "ranger" for random forests, "gbm" for generalized boosted models.
 #' @param alpha 1-alpha confidence interval.

R/cdgd0_pa.R

@@ -3,10 +3,10 @@
 
 #' Perform unconditional decomposition via parametric models
 #'
-#' @param Y Outcome. The name of a continuous variable.
+#' @param Y Outcome. The name of a numeric variable.
 #' @param D Treatment status. The name of a binary numeric variable taking values of 0 and 1.
 #' @param G Advantaged group membership. The name of a binary numeric variable taking values of 0 and 1.
-#' @param X Confounders. The vector of the names of numeric variables.
+#' @param X Confounders. A vector of names of numeric variables.
 #' @param data A data frame.
 #' @param alpha 1-alpha confidence interval.
 #' @param trim Threshold for trimming the propensity score. When trim=a, individuals with propensity scores lower than a or higher than 1-a will be dropped.

R/cdgd1_manual.R

@@ -5,7 +5,7 @@
 #' For the unconditional decomposition, ten nuisance functions need to be estimated.
 #' The nuisance functions should be estimated using cross-fitting if Donsker class is not assumed.
 #'
-#' @param Y Outcome. The name of a continuous variable.
+#' @param Y Outcome. The name of a numeric variable.
 #' @param D Treatment status. The name of a binary numeric variable taking values of 0 and 1.
 #' @param G Advantaged group membership. The name of a binary numeric variable taking values of 0 and 1.
 #' @param YgivenGXQ.Pred_D0 A numeric vector of predicted Y values given X, G, and D=0. Vector length=nrow(data).

R/cdgd1_ml.R

@@ -3,11 +3,11 @@
 
 #' Perform conditional decomposition via machine learning
 #'
-#' @param Y Outcome. The name of a continuous variable.
+#' @param Y Outcome. The name of a numeric variable.
 #' @param D Treatment status. The name of a binary numeric variable taking values of 0 and 1.
 #' @param G Advantaged group membership. The name of a binary numeric variable taking values of 0 and 1.
-#' @param Q Conditional set. The vector of the names of numeric variables.
-#' @param X Confounders. The vector of the names of numeric variables.
+#' @param Q Conditional set. A vector of names of numeric variables.
+#' @param X Confounders. A vector of names of numeric variables.
 #' @param data A data frame.
 #' @param algorithm The ML algorithm for modelling. "nnet" for neural network, "ranger" for random forests, "gbm" for generalized boosted models.
 #' @param alpha 1-alpha confidence interval.

R/cdgd1_pa.R

@@ -3,11 +3,11 @@
 
 #' Perform conditional decomposition via parametric models
 #'
-#' @param Y Outcome. The name of a continuous variable.
+#' @param Y Outcome. The name of a numeric variable.
 #' @param D Treatment status. The name of a binary numeric variable taking values of 0 and 1.
 #' @param G Advantaged group membership. The name of a binary numeric variable taking values of 0 and 1.
-#' @param Q Conditional set. The vector of the names of numeric variables.
-#' @param X Confounders. The vector of the names of numeric variables.
+#' @param Q Conditional set. A vector of names of numeric variables.
+#' @param X Confounders. A vector of names of numeric variables.
 #' @param data A data frame.
 #' @param alpha 1-alpha confidence interval.
 #' @param trim1 Threshold for trimming the propensity score. When trim1=a, individuals with propensity scores lower than a or higher than 1-a will be dropped.

README.Rmd

@@ -17,7 +17,7 @@ knitr::opts_chunk$set(
 ![CRAN Downloads overall](http://cranlogs.r-pkg.org/badges/grand-total/cdgd)
 
 
-The goal of cdgd is to implement the causal decompositions of group disparities in [Yu and Elwert (2023)](https://ang-yu.github.io/files/Causal_Decomposition_of_Group_Disparities_2023.pdf).
+The package cdgd implements the causal decompositions of group disparities in [Yu and Elwert (2023)](https://arxiv.org/abs/2306.16591).
 
 ## Installation
 

README.md

@@ -5,9 +5,8 @@
 ![CRAN Downloads
 overall](http://cranlogs.r-pkg.org/badges/grand-total/cdgd)
 
-The goal of cdgd is to implement the causal decompositions of group
-disparities in [Yu and Elwert
-(2023)](https://ang-yu.github.io/files/Causal_Decomposition_of_Group_Disparities_2023.pdf).
+The package cdgd implements the causal decompositions of group
+disparities in [Yu and Elwert (2023)](https://arxiv.org/abs/2306.16591).
 
 ## Installation
 

cran-comments.md

@@ -1 +1 @@
-* This is a patch release that fixes a couple of small issues.
+* This is a patch release that revises package description and help files.