Skip to content

Fix CIs for paired rank biserial corr with 0s #718

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
mattansb wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix CIs for paired rank biserial corr with 0s #718

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion DESCRIPTION
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
Type: Package
Package: effectsize
Title: Indices of Effect Size
Version: 1.0.3
Version: 1.0.3.1
Authors@R:
c(person(given = "Mattan S.",
family = "Ben-Shachar",
Expand Down
7 changes: 7 additions & 0 deletions NEWS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,10 @@
# effectsize (dev)

## Bug fixes

- `rank_biserial(x, y, paired = TRUE)` gives the same CIs as `rank_biserial(x - y)` (#716)


# effectsize 1.0.3

## Bug fixes
Expand Down
2 changes: 1 addition & 1 deletion R/rank_diff.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -176,7 +176,7 @@ rank_biserial <- function(

rank_f <- atanh(r_rbs)
if (is_paired_or_onesample) {
nd <- sum((x - mu) != 0)
nd <- sum((x - y) - mu != 0)
maxw <- (nd^2 + nd) / 2

# From: https://en.wikipedia.org/wiki/Wilcoxon_signed-rank_test#Historical_T_statistic/
Expand Down
10 changes: 5 additions & 5 deletions tests/testthat/test-rankES.R
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,14 +1,14 @@
test_that("rank_biserial", {
x <- c(1.83, 0.50, 1.62, 2.48, 1.68, 1.88, 1.55, 3.06, 1.30)
y <- c(0.878, 0.647, 0.598, 2.05, 1.06, 1.29, 1.06, 3.14, 1.29)
x <- c(5.1, 6.0, 7.2, 4.8, 6.5, 5.9, 7.0, 6.1, 5.5, 6.3)
y <- c(4.9, 6.0, 6.5, 4.8, 6.8, 5.3, 6.1, 6.1, 5.9, 5.0)

rRB1 <- rank_biserial(x, y, paired = TRUE)
rRB2 <- rank_biserial(x - y)

expect_equal(rRB1, rRB2, ignore_attr = TRUE)
expect_equal(rRB1[[1]], 0.777, tolerance = 0.01)
expect_equal(rRB1$CI_low, 0.2953631, tolerance = 0.01)
expect_equal(rRB1$CI_high, 0.9441559, tolerance = 0.01)
expect_equal(rRB1[[1]], 0.6428571, tolerance = 0.01)
expect_equal(rRB1$CI_low, -0.06511553, tolerance = 0.01)
expect_equal(rRB1$CI_high, 0.9203429, tolerance = 0.01)

A <- c(48, 48, 77, 86, 85, 85, 16)
B <- c(14, 34, 34, 77)
Expand All @@ -27,7 +27,7 @@
x1 <- x[1:5]
x2 <- x[6:15]

expect_equal(

Check warning on line 30 in tests/testthat/test-rankES.R

View workflow job for this annotation

GitHub Actions / lint-changed-files / lint-changed-files 

file=tests/testthat/test-rankES.R,line=30,col=3,[expect_identical_linter] Use expect_identical(x, y) by default; resort to expect_equal() only when needed, e.g. when setting ignore_attr= or tolerance=.
rank_biserial(x1, x2),
rank_biserial(as.numeric(x1), as.numeric(x2))
)
Expand All @@ -52,7 +52,7 @@

expect_equal(E[[1]], 0.05934066, tolerance = 0.01)
expect_equal(E$CI_low, 0.01726463, tolerance = 0.01)
expect_equal(E$CI_high, 1)

Check warning on line 55 in tests/testthat/test-rankES.R

View workflow job for this annotation

GitHub Actions / lint-changed-files / lint-changed-files 

file=tests/testthat/test-rankES.R,line=55,col=3,[expect_identical_linter] Use expect_identical(x, y) by default; resort to expect_equal() only when needed, e.g. when setting ignore_attr= or tolerance=.
})


Expand All @@ -66,7 +66,7 @@

expect_equal(E[[1]], 0.82, tolerance = 0.01)
expect_equal(E$CI_low, 0.78, tolerance = 0.01)
expect_equal(E$CI_high, 1)

Check warning on line 69 in tests/testthat/test-rankES.R

View workflow job for this annotation

GitHub Actions / lint-changed-files / lint-changed-files 

file=tests/testthat/test-rankES.R,line=69,col=3,[expect_identical_linter] Use expect_identical(x, y) by default; resort to expect_equal() only when needed, e.g. when setting ignore_attr= or tolerance=.
})

test_that("kendalls_w", {
Expand Down Expand Up @@ -272,17 +272,17 @@
)

expect_warning(kendalls_w(m, ci = NULL), "contain ties")
expect_warning(W <- kendalls_w(m, ci = NULL), "unique ranking")

Check warning on line 275 in tests/testthat/test-rankES.R

View workflow job for this annotation

GitHub Actions / lint-changed-files / lint-changed-files 

file=tests/testthat/test-rankES.R,line=275,col=18,[implicit_assignment_linter] Avoid implicit assignments in function calls. For example, instead of `if (x <- 1L) { ... }`, write `x <- 1L; if (x) { ... }`.
expect_equal(W[[1]], 0.4666667, tolerance = 0.001)
expect_equal(

Check warning on line 277 in tests/testthat/test-rankES.R

View workflow job for this annotation

GitHub Actions / lint-changed-files / lint-changed-files 

file=tests/testthat/test-rankES.R,line=277,col=3,[expect_identical_linter] Use expect_identical(x, y) by default; resort to expect_equal() only when needed, e.g. when setting ignore_attr= or tolerance=.
kendalls_w(t(m), blocks_on_rows = FALSE, ci = NULL, verbose = FALSE)[[1]],
W[[1]]
)

m[1, 1] <- NA
warns <- capture_warnings(W1 <- kendalls_w(m, ci = NULL))

Check warning on line 283 in tests/testthat/test-rankES.R

View workflow job for this annotation

GitHub Actions / lint-changed-files / lint-changed-files 

file=tests/testthat/test-rankES.R,line=283,col=29,[implicit_assignment_linter] Avoid implicit assignments in function calls. For example, instead of `if (x <- 1L) { ... }`, write `x <- 1L; if (x) { ... }`.
expect_match(warns[1], "dropped")
expect_equal(W1, kendalls_w(m[, -1], ci = NULL, verbose = FALSE))

Check warning on line 285 in tests/testthat/test-rankES.R

View workflow job for this annotation

GitHub Actions / lint-changed-files / lint-changed-files 

file=tests/testthat/test-rankES.R,line=285,col=3,[expect_identical_linter] Use expect_identical(x, y) by default; resort to expect_equal() only when needed, e.g. when setting ignore_attr= or tolerance=.

d <- data.frame(
y = OrchardSprays$decrease,
Expand Down
Loading