add_sig_cor {quest}

Add Significance Symbols to a Correlation Matrix

Description

add_sig_cor adds symbols for various p-values cutoffs of statistical significance. The function inputs a correlation matrix and a numeric matrix of p-values that correspond to the correlations (i.e., each row and column match) and then returns a data.frame of correlations with appended significance symbols. One of the primary applications of this function is use within corp corp_by, and corp_ml for correlation matrices.

Usage

add_sig_cor(
  r,
  p,
  digits = 3,
  p.10 = "",
  p.05 = "*",
  p.01 = "**",
  p.001 = "***",
  lead.zero = FALSE,
  trail.zero = TRUE,
  plus = FALSE,
  diags = FALSE,
  lower = TRUE,
  upper = FALSE
)

Arguments

r

double numeric matrix of correlation coefficients for which statistical significance is available. Since its a correlation matrix, it must be symmetrical and is expected to be a full matrix with all elements included (not just lower or upper diagonals values included).

p

double matrix of p-values for the correlations in r that are matched by row and column index. For example, the p-value in the first row and second column of p is associated with the correlation in the first row and second column of r. If r and p do not have the same dimensions, an error is returned.

digits

integer vector of length 1 specifying the number of decimals to round to.

p.10

character vector of length 1 specifying which symbol to append to the end of any correlation significant at the p < .10 level.

p.05

character vector of length 1 specifying which symbol to append to the end of any correlation significant at the p < .05 level.

p.01

character vector of length 1 specifying which symbol to append to the end of any correlation significant at the p < .01 level.

p.001

character vector of length 1 specifying which symbol to append to the end of any correlation significant at the p < .001 level.

lead.zero

logical vector of length 1 specifying whether to retain a zero in front of the decimal place.

trail.zero

logical vector of length 1 specifying whether to retain zeros after the decimal place (due to rounding).

plus

logical vector of length 1 specifying whether to include a plus sign in front of positive correlations (minus signs are always in front of negative correlations).

diags

logical vector of length 1 specifying whether to retain the values in the diagonal of the correlation matrix. If TRUE, then the diagonal will be 1s with digits number of zeros after the decimal place (and no significant symbols). If FALSE, then the diagonal will be NA.

lower

logical vector of length 1 specifying whether to retain the lower triangle of the correlation matrix. If TRUE, then the lower triangle correlations and their significance symbols are retained. If FAlSE, then the lower triangle will all be NA.

upper

logical vector of length 1 specifying whether to retain the upper triangle of the correlation matrix. If TRUE, then the upper triangle correlations and their significance symbols are retained. If FAlSE, then the upper triangle will all be NA.

Details

There are several functions out there that do similar things. Here is one posted to R-bloggers that uses the corr function from the Hmisc package: https://www.r-bloggers.com/2020/07/create-a-publication-ready-correlation-matrix-with-significance-levels-in-r/.

Value

data.frame with the same dimensions as r containing the correlations and their significance symbols. Elements may or may not contain NA values depending on the arguments diags, lower, and upper.

Examples

corr_test <- psych::corr.test(mtcars[1:5])
r <- corr_test[["r"]]
p <- corr_test[["p"]]
add_sig_cor(r = r, p = p)
add_sig_cor(r = r, p = p, digits = 2)
add_sig_cor(r = r, p = p, diags = TRUE)
add_sig_cor(r = r, p = p, lower = FALSE, upper = TRUE)
add_sig_cor(r = r, p = p, lead.zero = TRUE, trail.zero = FALSE)
add_sig_cor(r = r, p = p, plus = TRUE)