Tidy a(n) rcorr object

Tidy summarizes information about the components of a model. A model component might be a single term in a regression, a single hypothesis, a cluster, or a class. Exactly what tidy considers to be a model component varies across models but is usually self-evident. If a model has several distinct types of components, you will need to specify which components to return.

# S3 method for rcorr
tidy(x, diagonal = FALSE, ...)

Arguments

x	An rcorr object returned from Hmisc::rcorr().
diagonal	Logical indicating whether or not to include diagonal elements of the correlation matrix, or the correlation of a column with itself. For the elements, estimate is always 1 and p.value is always NA. Defaults to FALSE.
...	Additional arguments. Not used. Needed to match generic signature only. Cautionary note: Misspelled arguments will be absorbed in ..., where they will be ignored. If the misspelled argument has a default value, the default value will be used. For example, if you pass conf.level = 0.9, all computation will proceed using conf.level = 0.95. Additionally, if you pass newdata = my_tibble to an augment() method that does not accept a newdata argument, it will use the default value for the data argument.

Details

Suppose the original data has columns A and B. In the correlation matrix from rcorr there may be entries for both the cor(A, B) and cor(B, A). Only one of these pairs will ever be present in the tidy output.

See also

tidy(), Hmisc::rcorr()

Value

A tibble::tibble() with columns:

column1

Name or index of the first column being described.

column2

Name or index of the second column being described.

estimate

The estimated value of the regression term.

p.value

The two-sided p-value associated with the observed statistic.

n

Number of observations used to compute the correlation

Examples

library(Hmisc)
#> Loading required package: Formula
#> 
#> Attaching package: ‘Hmisc’
#> The following object is masked from ‘package:psych’:
#> 
#>     describe
#> The following object is masked from ‘package:network’:
#> 
#>     is.discrete
#> The following object is masked from ‘package:survey’:
#> 
#>     deff
#> The following object is masked from ‘package:fixest’:
#> 
#>     errbar
#> The following objects are masked from ‘package:dplyr’:
#> 
#>     src, summarize
#> The following objects are masked from ‘package:base’:
#> 
#>     format.pval, units

mat <- replicate(52, rnorm(100))
# add some NAs
mat[sample(length(mat), 2000)] <- NA
# also column names
colnames(mat) <- c(LETTERS, letters)

rc <- rcorr(mat)

td <- tidy(rc)
td
#> # A tibble: 1,326 x 5
#>    column1 column2 estimate     n p.value
#>    <chr>   <chr>      <dbl> <int>   <dbl>
#>  1 B       A        0.0670     36   0.698
#>  2 C       A        0.196      38   0.239
#>  3 C       B        0.172      37   0.309
#>  4 D       A       -0.0397     36   0.818
#>  5 D       B       -0.00762    31   0.968
#>  6 D       C        0.250      42   0.110
#>  7 E       A        0.224      36   0.189
#>  8 E       B        0.0700     35   0.690
#>  9 E       C        0.211      46   0.159
#> 10 E       D        0.147      40   0.364
#> # … with 1,316 more rows

library(ggplot2)
ggplot(td, aes(p.value)) +
  geom_histogram(binwidth = .1)

ggplot(td, aes(estimate, p.value)) +
  geom_point() +
  scale_y_log10()