Shows the results of a computed correlation as HTML table. Requires either a data.frame or a matrix with correlation coefficients as returned by the cor-function.

sjt.corr(data, na.deletion = c("listwise", "pairwise"),
  corr.method = c("pearson", "spearman", "kendall"), title = NULL,
  var.labels = NULL, wrap.labels = 40, show.p = TRUE, p.numeric = FALSE,
  fade.ns = TRUE, val.rm = NULL, digits = 3, triangle = "both",
  string.diag = NULL, CSS = NULL, encoding = NULL, file = NULL,
  use.viewer = TRUE, no.output = FALSE, remove.spaces = TRUE)



A vector or a data frame, for which frequencies should be printed as table.


Indicates how missing values are treated. May be either "listwise" (default) or "pairwise". May be abbreviated.


Indicates the correlation computation method. May be one of "spearman" (default), "pearson" or "kendall". May be abbreviated.


Table caption, as character vector.


Character vector with variable names, which will be used to label variables in the output.


numeric, determines how many chars of the value, variable or axis labels are displayed in one line and when a line break is inserted.


Logical, adds significance levels to values, or value and variable labels.


Logical, if TRUE, the p-values are printed as numbers. If FALSE (default), asterisks are used.


Logical, if TRUE (default), non-significant correlation-values appear faded (by using a lighter grey text color). See 'Note'.


Specify a number between 0 and 1 to suppress the output of correlation values that are smaller than val.rm. The absolute correlation values are used, so a correlation value of -.5 would be greater than val.rm = .4 and thus not be omitted. By default, this argument is NULL, hence all values are shown in the table. If a correlation value is below the specified value of val.rm, it is still printed to the HTML table, but made "invisible" with white foreground color. You can use the CSS argument ("css.valueremove") to change color and appearance of those correlation value that are smaller than the limit specified by val.rm.


Numeric, amount of digits after decimal point when rounding estimates and values.


Indicates whether only the upper right (use "upper"), lower left (use "lower") or both (use "both") triangles of the correlation table is filled with values. Default is "both". You can specifiy the inital letter only.


A vector with string values of the same length as ncol(data) (number of correlated items) that can be used to display content in the diagonal cells where row and column item are identical (i.e. the "self-correlation"). By defauilt, this argument is NULL and the diagnal cells are empty.


A list with user-defined style-sheet-definitions, according to the official CSS syntax. For more details, see this package-vignette, or 'Details' in sjt.frq.


String, indicating the charset encoding used for variable and value labels. Default is NULL, so encoding will be auto-detected depending on your platform (e.g., "UTF-8" for Unix and "Windows-1252" for Windows OS). Change encoding if specific chars are not properly displayed (e.g. German umlauts).


Destination file, if the output should be saved as file. If NULL (default), the output will be saved as temporary file and openend either in the IDE's viewer pane or the default web browser.


Logical, if TRUE, the HTML table is shown in the IDE's viewer pane. If FALSE or no viewer available, the HTML table is opened in a web browser.


Logical, if TRUE, the html-output is neither opened in a browser nor shown in the viewer pane and not even saved to file. This option is useful when the html output should be used in knitr documents. The html output can be accessed via the return value.


Logical, if TRUE, leading spaces are removed from all lines in the final string that contains the html-data. Use this, if you want to remove parantheses for html-tags. The html-source may look less pretty, but it may help when exporting html-tables to office tools.


Invisibly returns

  • the web page style sheet (,

  • the web page content (page.content),

  • the complete html-output (page.complete) and

  • the html-table with inline-css for use with knitr (knitr)

for further use.


See 'Details' in sjt.frq.


If data is a matrix with correlation coefficients as returned by the cor-function, p-values can't be computed. Thus, show.p, p.numeric and fade.ns only have an effect if data is a data.frame.

Additionally, see 'Note' in sjt.frq.

See also


# plot correlation matrix using circles

# Data from the EUROFAMCARE sample dataset

# retrieve variable and value labels
varlabs <- get_label(efc)

# recveive first item of COPE-index scale
start <- which(colnames(efc) == "c83cop2")
# recveive last item of COPE-index scale
end <- which(colnames(efc) == "c88cop7")

# create data frame with COPE-index scale
mydf <- data.frame(efc[, c(start:end)])
colnames(mydf) <- varlabs[c(start:end)]

# we have high correlations here, because all items
# belong to one factor. See example from "sjp.pca".
sjt.corr(mydf, p.numeric = TRUE)

# auto-detection of labels, only lower triangle
sjt.corr(efc[, c(start:end)], triangle = "lower")

# auto-detection of labels, only lower triangle, all correlation
# values smaller than 0.3 are not shown in the table
sjt.corr(efc[, c(start:end)], triangle = "lower", val.rm = 0.3)

# auto-detection of labels, only lower triangle, all correlation
# values smaller than 0.3 are printed in blue
sjt.corr(efc[, c(start:end)], triangle = "lower",val.rm = 0.3,
         CSS = list(css.valueremove = 'color:blue;'))
# }