# meanEffectSize

## Description

specifies options using one or more of the name-value arguments. For example, you can
specify the type of the effect size to compute or the number of bootstrap replicas to use
when computing the bootstrap confidence intervals.`Effect`

= meanEffectSize(`X`

,`Y`

,`Name=Value`

)

## Examples

### Compare Against Known Mean

Load the stock returns data and define the variable for which to compute the mean-difference effect size.

```
load stockreturns
x = stocks(:,1);
```

Compute the mean-difference effect size of the stock returns compared to the default mean value of 0, and compute the 95% confidence intervals for the effect size.

effect = meanEffectSize(x)

`effect=`*1×2 table*
Effect ConfidenceIntervals
________ ______________________
MeanDifference -0.20597 -0.41283 0.00087954

The `meanEffectSize`

function uses the exact method to estimate the confidence intervals when you use the mean-difference effect size.

You can also specify the mean value you want to compare against.

effect = meanEffectSize(x,Mean=-1)

`effect=`*1×2 table*
Effect ConfidenceIntervals
_______ ___________________
MeanDifference 0.79403 0.58717 1.0009

### Compute Median-Difference Effect Size for Two Independent Samples

Load Fisher's iris data and define the variables for which to compute the median-difference effect size.

load fisheriris species2 = categorical(species); x = meas(species2=='setosa'); y = meas(species2=='virginica');

Compute the median-difference effect size of the observations from two independent samples.

`effect = meanEffectSize(x,y,Effect="mediandiff")`

`effect=`*1×2 table*
Effect ConfidenceIntervals
______ ___________________
MedianDifference -1.5 -1.8 -1.3

By default, the `meanEffectSize`

function assumes that the samples are independent (that is, `Paired=false`

). The function uses bootstrapping to estimate the confidence intervals when the effect type is median-difference.

Visualize the median-difference effect size using the Gardner-Altman plot.

`gardnerAltmanPlot(x,y,Effect="mediandiff");`

The Gardner-Altman plot displays the two data samples on the left. The median of the sample `Y`

corresponds to the zero effect size on the effect size axis, which is the yellow axis line on the right. The median of the sample `X`

corresponds to the value of the effect size on the effect size axis. The plot displays the actual median-difference effect size value and the confidence intervals with the vertical error bar.

### Compute Cohen's d Effect Size and Specify Bootstrap Options

Load Fisher's iris data and define the variables for which to compare the Cohen's d effect size.

load fisheriris species2 = categorical(species); x = meas(species2=='setosa'); y = meas(species2=='virginica');

Compute the Cohen's d effect size for the observations from two independent samples, and compute the 95% confidence intervals for the effect size. By default,the `meanEffectSize`

function uses the exact formula based on the noncentral *t-*distribution to estimate the confidence intervals when the effect size type is Cohen's d. Specify the bootstrapping options as follows:

Set

`meanEffectSize`

to use bootstrapping for confidence interval computation.Use parallel computing for bootstrapping computations. You need Parallel Computing Toolbox™ for this option.

Use 3000 bootstrap replicas.

rng(123) % For reproducibility effect = meanEffectSize(x,y,Effect="cohen",ConfidenceIntervalType="bootstrap", ... BootstrapOptions=statset(UseParallel=true),NumBootstraps=3000)

Starting parallel pool (parpool) using the 'Processes' profile ... Connected to the parallel pool (number of workers: 6).

`effect=`*1×2 table*
Effect ConfidenceIntervals
_______ ___________________
CohensD -3.0536 -3.5621 -2.3468

Visualize the Cohen's d effect size using the Gardner-Altman plot with the same options set.

gardnerAltmanPlot(x,y,Effect="cohen",ConfidenceIntervalType="bootstrap", ... BootstrapOptions=statset(UseParallel=true),NumBootstraps=3000);

The Gardner-Altman plot displays the two data samples on the left. The mean of the sample `Y`

corresponds to the zero effect size on the effect size axis, which is the yellow axis line on the right. The mean of the sample `X`

corresponds to the value of the effect size on the effect size axis. The plot displays the Cohen's d effect size value and the confidence intervals with the vertical error bar.

### Compare Paired Sample Means

Load exam grades data and define the variables to compare.

```
load examgrades
x = grades(:,1);
y = grades(:,2);
```

Compute the mean-difference effect size of the grades from the paired samples, and compute the 95% confidence intervals for the effect size.

effect = meanEffectSize(x,y,Paired=true)

`effect=`*1×2 table*
Effect ConfidenceIntervals
________ ___________________
MeanDifference 0.016667 -1.3311 1.3644

The `meanEffectSize`

function uses the exact method to estimate the confidence intervals when you use the mean-difference effect size.

You can specify a different effect size type. (Note that you cannot use Glass's delta for paired samples.) Use robust Cohen's d to compare the paired sample means. Compute the 97% confidence intervals for the effect size.

`effect = meanEffectSize(x,y,Paired=true,Effect="robustcohen",Alpha=0.03)`

`effect=`*1×2 table*
Effect ConfidenceIntervals
________ ___________________
RobustCohensD 0.059128 -0.1405 0.26573

The `meanEffectSize`

function uses bootstrapping to estimate the confidence intervals when the effect size type is robust Cohen's d.

Visualize the effect size using the Gardner-Altman plot. Specify robust Cohen's d as the effect size, and compute the 97% confidence intervals.

`gardnerAltmanPlot(x,y,Paired=true,Effect="robustcohen",Alpha=0.03);`

The Gardner-Altman plot displays the paired data on the left. The blue lines show the values that are increasing and the red lines show the values that are decreasing from the first sample to the corresponding values in the paired sample, respectively. Right side of the plot displays the robust Cohen's d effect size with the 97% confidence interval.

## Input Arguments

`X`

— Input data

numeric vector

Input data, specified as a numeric vector.

**Data Types: **`single`

| `double`

`Y`

— Input data

numeric vector

Input data, specified as a numeric vector.

**Data Types: **`single`

| `double`

### Name-Value Arguments

Specify optional pairs of arguments as
`Name1=Value1,...,NameN=ValueN`

, where `Name`

is
the argument name and `Value`

is the corresponding value.
Name-value arguments must appear after other arguments, but the order of the
pairs does not matter.

**Example: **`Effect="cliff",Alpha=0.03,ConfidenceIntervalType="bootstrap",VarianceType=unequal`

specifies to use the Cliff's Delta effect size, compute the 97% confidence intervals using
bootstrapping, and assume the samples come from populations with unequal
variances.

`Alpha`

— Confidence level

0.05 (default) | value from 0 to 1

Confidence level of the confidence intervals for the effect size, specified as a numeric value from 0 to 1. Default value of 0.05 corresponds to the 95% confidence level.

**Example: **`Alpha=0.025`

**Data Types: **`single`

| `double`

`BootstrapOptions`

— Options for computing bootstrap confidence intervals in parallel

structure

Options for computing bootstrap confidence intervals in parallel, specified as a
structure generated by using `statset("bootci")`

.
`meanEffectSize`

uses the following fields.

Field | Description |
---|---|

`Streams` | A You have an open parallel pool. `UseParallel` is`true` .`UseSubstreams` is`false` .
In this case, use a cell array the
same size as the parallel pool. If a parallel pool is not open,
then |

`UseParallel` | The default is `false` , indicating serial
computation. |

`UseSubstreams` | Set to `true` to compute in parallel in a
reproducible fashion. The default is `false` . To
compute reproducibly, set `Streams` to a type
allowing substreams: `"mlfg6331_64"` or
`"mrg32k3a"` . |

Computing bootstrap confidence intervals in parallel requires Parallel Computing Toolbox™.

**Example: **`BootstrapOptions=options`

**Data Types: **`struct`

`ConfidenceIntervalType`

— Type of confidence interval

`"exact"`

| `"bootstrap"`

| `"none"`

Type of confidence interval to compute, specified as `"exact"`

,
`"bootstrap"`

, or `"none"`

. The default value is
`"exact"`

when there is an exact formula for the effect size or
`"bootstrap"`

otherwise. Specify `"none"`

is when
you do not want to compute any confidence intervals.

The default value is `"exact"`

for Cliff's Delta, Glass's delta,
mean-difference, and Cohen's d and `"bootstrap"`

for Kolmogorov-Smirnov
statistic, median-difference, and robust Cohen's d. If you specify confidence interval
type as `"exact"`

for Kolmogorov-Smirnov statistic, median-difference,
and robust Cohen's d, `meanEffectSize`

returns an error.

**Example: **`ConfidenceIntervalType="none"`

**Data Types: **`string`

| `char`

`Effect`

— Effect size type to compute

`"meandiff"`

(default) | `"cohen"`

| `"cliff"`

| `"glass"`

| `"kstest"`

| `"mediandiff"`

| `"robustcohen"`

Effect size type to compute, specified as one of or a cell array of the following built-in options.

**Options for single-sample input**

Effect size option | Definition |
---|---|

`"cohen"` | Cohen's d for single-sample input. |

`"meandiff"` | Mean difference. |

`"robustcohen"` | Robust Cohen's d for single-sample input. |

**Options for two-sample input**

Option | Definition |
---|---|

`"cohen"` | Cohen's d for two-sample input |

`"cliff"` | Cliff's Delta |

`"glass"` | Glass's delta; not supported by |

`"kstest"` | Kolmogorov-Smirnov statistic |

`"mediandiff"` | Median difference |

`"meandiff"` | Mean difference |

`"robustcohen"` | Robust Cohen's d for two-sample input |

For more information on the effect sizes, see Algorithms.

**Example: **`Effect="glass"`

**Data Types: **`string`

| `char`

| `cell`

`Mean`

— Known population mean value

scalar value

Known population mean value to compare against, specified as a scalar value. This option is only for single-sample data.

**Example: **`Mean=10`

**Data Types: **`single`

| `double`

`NumBootstraps`

— Number of bootstrap replicas

1000 (default) | positive integer

Number of bootstrap replicas to use when computing the bootstrap confidence intervals, specified as a positive integer.

**Example: **`NumBootstraps=1500`

**Data Types: **`single`

| `double`

`Paired`

— Indicator for paired samples

`false`

(default) | `true`

Indicator for paired samples, specified as `false`

or
`true`

.

If

`Paired`

is`true`

, then`VarianceType`

must be`"equal"`

.If

`Paired`

is`true`

, then`Effect`

cannot be`"glass"`

.

**Example: **`Paired=true`

**Data Types: **`logical`

`VarianceType`

— Population variance assumption for two samples

`"equal"`

(default) | `"unequal"`

Population variance assumption for two samples, specified as `"equal"`

or
`"unequal"`

. If `Paired`

is
`"true"`

, then `VarianceType`

must be
`"equal"`

.

**Example: **`VarianceType="unequal"`

**Data Types: **`string`

| `char`

## Output Arguments

`Effect`

— Effect size information

table

Effect size information, returned as a table. `Effect`

has a row
for each effect size computed and a column for the value of the effect size, and a
column for the confidence intervals for that effect size, if they are computed.

**Data Types: **`table`

## Algorithms

### Effect Size

*Cliff's Delta*Unpaired data

$$\delta =\frac{{\displaystyle \sum _{i,j=1}^{{n}_{1},{n}_{2}}\left({x}_{i}>{y}_{j}\right)-\left({x}_{i}<{y}_{j}\right)}}{{n}_{1}*{n}_{2}},$$

where

*n*is the size of the first sample, and_{1}*n*is the size of the second sample._{2}Paired data

`meanEffectSize`

uses the between-group delta, which compares the differences between`x`

and`y`

, but excludes comparisons of paired data. For*n*paired samples, the result is*n*(*n*–1) comparisons [3].

*Cohen's d*`meanEffectSize`

computes the unbiased estimate of Cohen's d, which is also known as Hedge's g.One-sample

$$d=J\left(df\right)*\frac{\left(\overline{x}-\mu \right)}{s}$$

Two-sample

$$d=J\left(df\right)*\frac{\left(\overline{x}-\overline{y}\right)}{s}$$

where

*df*is the degrees of freedom,*μ*is the known population mean to compare against,*s*is the pooled standard deviation, and*J(df)*is the bias correction term. The pooled standard deviation is defined as$$s=\sqrt{\frac{\left({n}_{1}-1\right){s}_{1}^{2}+\left({n}_{2}-1\right){s}_{2}^{2}}{{n}_{1}+{n}_{2}-2}},$$

where

*n*is the size of the first sample and_{1}*n*is the size of the second sample._{2}The bias correction term are defined as

$$J\left(df\right)=\frac{\Gamma \left(df/2\right)}{\sqrt{df/2}\Gamma \left(\left(df-1\right)/2\right)},$$

where $$\Gamma \left(\right)$$ is the gamma function.

Cohen's d follows a noncentral

*t*-distribution and uses it to derive the confidence intervals. So, by default,`meanEffectSize`

uses`"exact"`

to compute the confidence intervals for the effect size. See [1] and [4] to see the derivation of the confidence intervals for paired versus unpaired input data.*Glass's Delta*$$D=\frac{\overline{x}-\overline{y}}{{s}_{x}},$$

where

*s*is the standard deviation of the control group._{x}`meanEffectSize`

uses the data in`x`

as the control group. If you wish to use the other sample as the control group, you can swap the data in`x`

and`y`

and swap the sign of the test result.Similar to Cohen's d, Glass's delta also follows a noncentral

*t*-distribution and uses it to derive the confidence intervals. So, by default,`meanEffectSize`

uses`"exact"`

to compute the confidence intervals for the effect size [4]. You cannot use this effect size for paired samples.*Kolmogorov-Smirnov Test Statistic*This two-sample test statistic is the same as given in Two-Sample Kolmogorov-Smirnov Test.

`meanEffectSize`

uses bootstrapping to compute the confidence intervals.*Mean Difference*One-sample

$$m=\left(\overline{x}-\mu \right)$$

Two-sample

$$m=\left(\overline{x}-\overline{y}\right)$$

`meanEffectSize`

computes the confidence intervals using the*t*-distribution with pooled standard deviation in the two-sample case. (In the case of unequal variance assumption for two samples, the confidence intervals are called Welch-Satterthwaite confidence intervals). By default, the function uses`"exact"`

to compute the confidence intervals for the effect size.*Median Difference*$$M\text{=}median\left(x\right)-median\left(y\right)$$

`meanEffectSize`

computes the confidence intervals using bootstrapping for the effect size.*Robust Cohen's d*$$d=0.643*J\left(df\right)*\frac{\left({\overline{x}}_{t}-{\overline{y}}_{t}\right)}{{s}_{w}},$$

where $${\overline{x}}_{t}$$ and $${\overline{y}}_{t}$$ are the 20% trimmed means of data in

`x`

and`y`

, respectively. $${\text{s}}_{w}$$ is the pooled 20% Winsorized variance [2].`meanEffectSize`

computes the confidence intervals using bootstrapping for the effect size.

## References

[1] Cousineau, Denis, and
Jean-Christophe Goulet-Pelletier. "A Study of Confidence Intervals for Cohen's d in
Within-Subject Designs with New Proposals." *The Quantitative Methods for
Psychology* 17, no. 1 (March 2021): 51--75. https://doi.org/10.20982/tqmp.17.1.p051.

[2] Algina, James, H. J. Keselman, and
R. D. Penfield. "An Alternative to Cohen's Standardized Mean Difference Effect Size: A Robust
Parameter and Confidence Interval in the Two Independent Groups Case."
*Psychological Methods* 10, no. 3 (Sept 2005): 317–28. https://doi.org/10.1037/1082-989X.10.3.317.

[3] Hess, Melinda, and Jeffrey
Kromrey. "Robust Confidence Intervals for Effect Sizes: A Comparative Study of Cohen's d and
Cliff's Delta Under Non-normality and Heterogeneous Variances." *Annual Meeting of
the American Educational Research Association*. 2004.

[4] Delacre, Marie, Daniel Lakens, Christophe Ley, Limin Liu, and Christophe Leys. "Why Hedges G's Based on the Non-pooled Standard Deviation Should Be Reported with Welch's T-test." 2021.

[5] Gardner, M. J., and D. G. Altman.
Confidence Intervals Rather Than P Values; Estimation Rather Than Hypothesis Testing."
*BMJ*, 292 no. 6522 (March 1986): 746–50. https://doi.org/10.1136/bmj.292.6522.746.

## Extended Capabilities

### Automatic Parallel Support

Accelerate code by automatically running computation in parallel using Parallel Computing Toolbox™.

To run in parallel, specify the `Options`

name-value argument in the call to
this function and set the `UseParallel`

field of the
options structure to `true`

using
`statset`

:

`"Options",statset("UseParallel",true)`

For more information about parallel computing, see Run MATLAB Functions with Automatic Parallel Support (Parallel Computing Toolbox).

## Version History

**Introduced in R2022a**

## See Also

## Open Example

You have a modified version of this example. Do you want to open this example with your edits?

## MATLAB Command

You clicked a link that corresponds to this MATLAB command:

Run the command by entering it in the MATLAB Command Window. Web browsers do not support MATLAB commands.

Select a Web Site

Choose a web site to get translated content where available and see local events and offers. Based on your location, we recommend that you select: .

You can also select a web site from the following list:

## How to Get Best Site Performance

Select the China site (in Chinese or English) for best site performance. Other MathWorks country sites are not optimized for visits from your location.

### Americas

- América Latina (Español)
- Canada (English)
- United States (English)

### Europe

- Belgium (English)
- Denmark (English)
- Deutschland (Deutsch)
- España (Español)
- Finland (English)
- France (Français)
- Ireland (English)
- Italia (Italiano)
- Luxembourg (English)

- Netherlands (English)
- Norway (English)
- Österreich (Deutsch)
- Portugal (English)
- Sweden (English)
- Switzerland
- United Kingdom (English)