Effect Size > Cohen’s D

You may find it helpful to read the precious article first: What is Effect Size?

## What is Cohen’s D?

**Cohen’s D **is one of the most common ways to measure effect size. An effect size is how large an effect of something is. For example, medication A has a better effect than medication B.

## Formula

The formula for Cohen’s D is:

d = M_{1}– M_{2}/ s_{pooled}

Where:

- M
_{1}= mean of group 1 - M
_{2}= mean of group 2 - s
_{pooled}= pooled standard deviations for the two groups. The formula is: √[(s_{1}^{2}+ s_{2}^{2}) / 2]

**Cohen’s D works best for larger sample sizes (> 50).** For smaller sample sizes, it tends to over-inflate results. A correction factor is available, which reduces effect sizes for small samples by a few percentage points:

**Note**: The bias towards small samples bias is slightly smaller for an alternative method, Hedges’ g, which uses n-1 for each sample.

## Interpreting Results

A d of 1 indicates the two groups differ by 1 standard deviation, a d of 2 indicates they differ by 2 standard deviations, and so on. Standard deviations are equivalent to z-scores (1 standard deviation = 1 z-score).

## Rule of Thumb Interpretation

If you aren’t familiar with the meaning of standard deviations and z-scores, or have trouble visualizing what the result of Cohen’s D means, use these general “**rule of thumb**” guidelines (which Cohen said should be used cautiously):

- Small effect = 0.2
- Medium Effect = 0.5
- Large Effect = 0.8

“Small” effects are difficult to see with the naked eye. For example, Cohen reported that the height difference between 15-year-old and 16-year-old girls in the US is about this effect size. “Medium” is probably big enough to be discerned with the naked eye, while **effects that are “large” can definitely be seen with the naked eye** (Cohen calls this “grossly perceptible and therefore large”). For example, the difference in heights between 13-year-old and 18-year-old girls is 0.8. An effect under 0.2 can be considered trivial, even if your results are statistically significant.

Bear in mind that a “large” effect isn’t necessarily better than a “small” effect, **especially in settings where small differences can have a major impact**. For example, an increase in academic scores or health grades by an effect size of just 0.1 can be very significant in the real world. Durlak (2009) suggests referring to prior research in order to get an idea of where your findings fit into the bigger context.

## Transforming into other measures

To transform Cohen’s D into Hedge’s g, use the following equation:

Where:

- N = sample size,
- df = degrees of freedom.

To transform d into the correlation coefficient, r, use this formula:

**References:**

Cohen, J. (1977). Statistical power analysis for the behavioral sciences. Routledge.

Durlak, J. (2009) How to Select, Calculate, and Interpret Effect Sizes. Journal of Pediatric Psychology. March: 34(9):917-28.

**Need help with a homework or test question?** With Chegg Study, you can get step-by-step solutions to your questions from an expert in the field. If you rather get 1:1 study help, Chegg Tutors offers 30 minutes of free tutoring to new users, so you can try them out before committing to a subscription.

If you prefer an **online interactive environment** to learn R and statistics, this *free R Tutorial by Datacamp* is a great way to get started. If you're are somewhat comfortable with R and are interested in going deeper into Statistics, try *this Statistics with R track*.

**Comments? Need to post a correction?** Please post a comment on our *Facebook page*.

Check out our updated Privacy policy and Cookie Policy