correlation_matrix <- function(df,
type = "pearson",
digits = 3,
decimal.mark = ".",
use = "all",
show_significance = TRUE,
replace_diagonal = FALSE,
replacement = ""){
# check arguments
stopifnot({
is.numeric(digits)
digits >= 0
use %in% c("all", "upper", "lower")
is.logical(replace_diagonal)
is.logical(show_significance)
is.character(replacement)
})
# we need the Hmisc package for this
require(Hmisc)
# retain only numeric and boolean columns
isNumericOrBoolean = vapply(df, function(x) is.numeric(x) | is.logical(x), logical(1))
if (sum(!isNumericOrBoolean) > 0) {
cat('Dropping non-numeric/-boolean column(s):', paste(names(isNumericOrBoolean)[!isNumericOrBoolean], collapse = ', '), '\n\n')
}
df = df[isNumericOrBoolean]
# transform input data frame to matrix
x <- as.matrix(df)
# run correlation analysis using Hmisc package
correlation_matrix <- Hmisc::rcorr(x, type = )
R <- correlation_matrix$r # Matrix of correlation coeficients
p <- correlation_matrix$P # Matrix of p-value
# transform correlations to specific character format
Rformatted = formatC(R, format = 'f', digits = digits, decimal.mark = decimal.mark)
# if there are any negative numbers, we want to put a space before the positives to align all
if (sum(R < 0) > 0) {
Rformatted = ifelse(R > 0, paste0(' ', Rformatted), Rformatted)
}
# add significance levels if desired
if (show_significance) {
# define notions for significance levels; spacing is important.
stars <- ifelse(is.na(p), " ", ifelse(p < .001, "***", ifelse(p < .01, "** ", ifelse(p < .05, "* ", " "))))
Rformatted = paste0(Rformatted, stars)
}
# build a new matrix that includes the formatted correlations and their significance stars
Rnew <- matrix(Rformatted, ncol = ncol(x))
rownames(Rnew) <- colnames(x)
colnames(Rnew) <- paste(colnames(x), "", sep =" ")
# replace undesired values
if (use == 'upper') {
Rnew[lower.tri(Rnew, diag = replace_diagonal)] <- replacement
} else if (use == 'lower') {
Rnew[upper.tri(Rnew, diag = replace_diagonal)] <- replacement
} else if (replace_diagonal) {
diag(Rnew) <- replacement
}
return(Rnew)
}
aggregate data to level 2 (e.g., average across people or across teams)
correlate using “lower”
save to csv
word table (delete 1 star)
take raw level 1 data and remove level 2 variables
correlate using “upper”
save to csv
word table (delete 1 star)
Bo\(^2\)m =)