Converting Between r, d, and Odds Ratios"
In effectsize: Indices of Effect Size

library(knitr)
options(knitr.kable.NA = "")
knitr::opts_chunk$set(comment = ">")
options(digits = 3)

.eval_if_requireNamespace <- function(...) {
  pkgs <- c(...)
  knitr::opts_chunk$get("eval") && all(sapply(pkgs, requireNamespace, quietly = TRUE))
}

The effectsize package contains function to convert among indices of effect size. This can be useful for meta-analyses, or any comparison between different types of statistical analyses.

Converting Between d and r

The most basic conversion is between r values, a measure of standardized association between two continuous measures, and d values (such as Cohen's d), a measure of standardized differences between two groups / conditions.

Let's looks at some (simulated) data:

library(effectsize)
data("hardlyworking")
head(hardlyworking)

We can compute Cohen's d between the two groups:

cohens_d(salary ~ is_senior, data = hardlyworking)

But we can also compute a point-biserial correlation, which is Pearson's r when treating the 2-level is_senior variable as a numeric binary variable:

correlation::cor_test(hardlyworking, "salary", "is_senior")

But what if we only have summary statistics? Say, we only have $d=-0.72$ and we want to know what the r would have been? We can approximate r using the following formula

$$ r \approx \frac{d}{\sqrt{d^2 + 4}} $$ And indeed, if we use d_to_r(), we get a pretty decent approximation:

d_to_r(-0.72)

(Which also works in the other way, with r_to_d(0.12) gives r round(r_to_d(0.34),3))

As we can see, these are rough approximations, but they can be useful when we don't have the raw data on hand.

In multiple regression

Although not exactly a classic Cohen's d, we can also approximate a partial-d value (that is, the standardized difference between two groups / conditions, with variance from other predictors partilled out). For example:

fit <- lm(salary ~ is_senior + xtra_hours, data = hardlyworking)

parameters::model_parameters(fit)

# A couple of ways to get partial-d:
1683.65 / sigma(fit)
t_to_d(5.31, df_error = 497)[[1]]

We can convert these semi-d values to r values, but in this case these represent the partial correlation:

t_to_r(5.31, df_error = 497)

correlation::correlation(hardlyworking[, c("salary", "xtra_hours", "is_senior")],
  include_factors = TRUE,
  partial = TRUE
)[2, ]

# all close to:
d_to_r(0.47)

Converting Between OR and d

In binomial regression (more specifically in logistic regression), Odds ratios (OR) are themselves measures of effect size; they indicate the expected change in the odds of a some event.

In some fields, it is common to dichotomize outcomes in order to be able to analyze them with logistic models. For example, if the outcome is the count of white blood cells, it can be more useful (medically) to predict the crossing of the threshold rather than the raw count itself. And so, where some scientists would maybe analyze the above data with a t-test and present Cohen's d, others might analyze it with a logistic regression model on the dichotomized outcome, and present OR. So the question can be asked: given such a OR, what would Cohen's d have been?

Fortunately, there is a formula to approximate this [@sanchez2003effect]:

$$ d = log(OR) \times \frac{\sqrt{3}}{\pi} $$

which is implemented in the oddsratio_to_d() function.

Let's give it a try:

# 1. Set a threshold
thresh <- 22500

# 2. dichotomize the outcome
hardlyworking$salary_high <- hardlyworking$salary < thresh

# 3. Fit a logistic regression:
fit <- glm(salary_high ~ is_senior,
  data = hardlyworking,
  family = binomial()
)

parameters::model_parameters(fit)

# Convert log(OR) (the coefficient) to d
oddsratio_to_d(-1.22, log = TRUE)