#' @title Performs Correlation Tests on a given dataset
#'
#' @description This function performs a correlation tests on a given dataset.
#' Most notably; Pearson correlation and Spearman correlation.
#' The dataset can be a mixture of data types.
#' By default, the function performs the correlation tests on all numeric variables in the dataset.
#' However, a y_index can be assigned whereby all correlation tests are perform in relation to a specified response variable in the dataset.
#' The results of the correlation tests are returned as a data frame.
#' This data frame can be exported as a .csv to a specified directory.
#' The null hypothesis is that the correlation is equal to 0.
#' Ho: cor(Xi) = 0, where i != j.
#'
#' @param dataset The dataset on which the correlation tests are performed.
#'
#' @param y_index Integer value, the column index of the response variable, the default is NULL.
#'
#' @param y_name Character value, the column name of the response variable, the default is NULL.
#'
#' @param alternative The type of hypothesis being tested; two.sided, greater, less.
#' The default is "two.sided".
#'
#' @param conf.level The level of confidence used in the tests, default is 0.95
#'
#' @param file_name A character object indicating the file name when saving the data frame.
#' The default is NULL.
#' The name must include the .csv suffixs.
#'
#' @param directory A character object specifying the directory where the data frame is to be saved as a .csv file.
#'
#' @return Outputs the correlatiom test information as a data frame. This data frame can be saved as a .csv to a specified directory.
#'
#' @export
#'
#' @seealso \code{\link{tests_chisq}}, \code{\link{tests_ks}}, \code{\link{tests_norm}}, \code{\link{tests_proptest}}, \code{\link{tests_t}}, \code{\link{tests_var}}, \code{\link{tests_wilcoxon}}
#'
#' @keywords Correlation Tests, Pearson Correlation, Kendall Correlation, Spearman Correlation
#'
#' @examples
#' #-- Example Lung Cap Data --#
#'
#' # perform correlation tests on all pairs of numeric variables
#' tests_cors(dataset = lungcap)
#'
#' # perform correlation tests on the 2nd column and all other numeric variables
#' tests_cors(dataset = lungcap, y_index = 2)
#'
#' # perform correlation tests on Age and all other numeric varibales.
#' tests_cors(dataset = lungcap, y_name = 'Age')
#'
tests_cors <- function (dataset,
y_index = NULL,
y_name = NULL,
alternative = c("two.sided", "greater", "less"),
conf.level = 0.95,
file_name = NULL,
directory = NULL)
{
#-------------------------------------------------------------------------------#
# When y_index = NULL and y_name = NULL #
#-------------------------------------------------------------------------------#
if(is.null(y_index) & is.null(y_name)){
# Convert the dataset set to a data frame
dataset <- as.data.frame(dataset)
# Confirm correct choice for alternative
alternative <- match.arg(alternative)
# the number of numeric columns in the dataset
n_cols <- sum(sapply(X = dataset, FUN = function(x) is.numeric(x))) - 1
# Create a data frame to hold the correlation test data
cor_test_df <- as.data.frame(matrix(nrow = ((n_cols)^2 - (n_cols)) / 2,
ncol = 6))
# Name the columns of the Correlation Test Data Frame
colnames(cor_test_df) <- c("Xi", "Xj",
"Pearson Cor.", "Pearson P.v.",
"Spearman Cor.", "Spearman Pv.")
# Create a row index to populate the data frame with
r = 1
for (i in 1:ncol(dataset)) {
j = i + 1
while (j <= ncol(dataset)) {
if((is.numeric(dataset[,i]) & is.numeric(dataset[,j]))) {
# Fill in the Xi Variable Name
cor_test_df[r, 1] <- colnames(dataset)[i]
# Fill in the Xj Variable Name
cor_test_df[r, 2] <- colnames(dataset)[j]
#-- (1) Pearson Correlation --#
# Perform Correlation Test
c.t. <- cor.test(x = dataset[,i],
y = dataset[,j],
alternative = alternative,
conf.level = conf.level,
method = "pearson",
na.action = "na.omit")
# Fill in the correlation
cor_test_df[r, 3] <- round(c.t.$estimate,
digits = 5)
# Fill in the p-value
cor_test_df[r, 4] <- round(c.t.$p.value,
digits = 5)
#-- (2) Spearman Correlation --#
# Perform Correlation Test
c.t. <- cor.test(x = dataset[,i],
y = dataset[,j],
alternative = alternative,
conf.level = conf.level,
method = "spearman",
exact = FALSE,
na.action = "na.omit")
# Fill in the correlation
cor_test_df[r, 5] <- round(c.t.$estimate,
digits = 5)
# Fill in the p-value
cor_test_df[r, 6] <- round(c.t.$p.value,
digits = 5)
}
# update j
j = j + 1
# Update the row index
r = r + 1
}
}
# Remove the incomplete cases
cor_test_df <- cor_test_df[complete.cases(cor_test_df[,]), ]
#-------------------------------------------------------------------------------#
# When y_index != NULL or y_name != NULL #
#-------------------------------------------------------------------------------#
} else if(!is.null(y_index) | !is.null(y_name)){
if(!is.null(y_name)){
y_index = which(colnames(dataset) == y_name)
}
if(is.numeric(dataset[,y_index])){
# Convert the dataset set to a data frame
dataset <- as.data.frame(dataset)
# Confirm correct choice for alternative
alternative <- match.arg(alternative)
# extract the test data
test_data <- dataset[,-y_index]
# Create a data frame to hold the correlation test data
cor_test_df <- as.data.frame(matrix(nrow = sum(sapply(X = dataset,FUN = function(x) is.numeric(x))) - 1,
ncol = 6))
# Name the columns of the Correlation Test Data Frame
colnames(cor_test_df) <- c("Xi", "Y",
"Pearson Cor.", "Pearson P.v.",
"Spearman Cor.", "Spearman Pv.")
# Create a row index to populate the data frame with
r = 1
for (i in 1:ncol(test_data)) {
if(is.numeric(test_data[,i])) {
# Fill in the X Variable Name
cor_test_df[r, 1] <- colnames(test_data)[i]
# Fill in the Y Variable Name
cor_test_df[r, 2] <- colnames(dataset)[y_index]
#-- (1) Pearson Correlation --#
# Perform Correlation Test
c.t. <- cor.test(x = test_data[,i],
y = dataset[,y_index],
alternative = alternative,
conf.level = conf.level,
method = "pearson",
na.action = "na.omit")
# Fill in the correlation
cor_test_df[r, 3] <- round(c.t.$estimate,
digits = 5)
# Fill in the p-value
cor_test_df[r, 4] <- round(c.t.$p.value,
digits = 5)
#-- (2) Spearman Correlation --#
# Perform Correlation Test
c.t. <- cor.test(x = test_data[,i],
y = dataset[,y_index],
alternative = alternative,
conf.level = conf.level,
method = "spearman",
exact = FALSE,
na.action = "na.omit")
# Fill in the correlation
cor_test_df[r, 5] <- round(c.t.$estimate,
digits = 5)
# Fill in the p-value
cor_test_df[r, 6] <- round(c.t.$p.value,
digits = 5)
# Update the row index
r = r + 1
}
}
}
}
# Write the data frame to the specified directory
if(!is.null(directory)) {
write.csv(x = cor_test_df,
file = paste(directory, "/", file_name, sep = ""),
row.names = F)
}
# return the cor_test_df
return(cor_test_df)
}
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.