# ttest2

Two-sample *t*-test

## Description

returns
a test decision for the null hypothesis that the data in vectors `h`

= ttest2(`x`

,`y`

)`x`

and `y`

comes
from independent random samples from normal distributions with equal
means and equal but unknown variances, using the two-sample *t*-test.
The alternative hypothesis is that the data in `x`

and `y`

comes
from populations with unequal means. The result `h`

is `1`

if
the test rejects the null hypothesis at the 5% significance level,
and `0`

otherwise.

returns
a test decision for the two-sample `h`

= ttest2(`x`

,`y`

,`Name,Value`

)*t*-test with
additional options specified by one or more name-value pair arguments.
For example, you can change the significance level or conduct the
test without assuming equal variances.

## Examples

### Two-Sample *t*-Test for Equal Means

Load the data set. Create vectors containing the first and second columns of the data matrix to represent students’ grades on two exams.

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

Test the null hypothesis that the two data samples are from populations with equal means.

[h,p,ci,stats] = ttest2(x,y)

h = 0

p = 0.9867

`ci = `*2×1*
-1.9438
1.9771

`stats = `*struct with fields:*
tstat: 0.0167
df: 238
sd: 7.7084

The returned value of `h = 0`

indicates that `ttest2`

does not reject the null hypothesis at the default 5% significance level.

*t*-Test for Equal Means Without Assuming Equal Variances

Load the data set. Create vectors containing the first and second columns of the data matrix to represent students’ grades on two exams.

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

Test the null hypothesis that the two data vectors are from populations with equal means, without assuming that the populations also have equal variances.

[h,p] = ttest2(x,y,'Vartype','unequal')

h = 0

p = 0.9867

The returned value of `h = 0`

indicates that `ttest2`

does not reject the null hypothesis at the default 5% significance level even if equal variances are not assumed.

### One-Sided, Two-Sample *t*-Test

Load the sample data. Create a categorical vector to label the vehicle mileage data according to the vehicle year.

load carbig.mat; decade = categorical(Model_Year < 80,[true,false],["70s","80s"]);

Create box plots of the mileage data for each decade.

boxchart(decade,MPG) xlabel("Decade") ylabel("Mileage")

Create vectors from the mileage data for each decade. Use a left-tailed, two-sample *t*-test to test the null hypothesis that the data comes from populations with equal means. Use the alternative hypothesis that the population mean for the mileage of cars made in the 1970s is less than the population mean for the mileage of cars made in the 1980s.

MPG70s = MPG(decade == "70s"); MPG80s = MPG(decade == "80s"); [h,~,~,stats] = ttest2(MPG70s,MPG80s,"Tail","left")

h = 1

`stats = `*struct with fields:*
tstat: -14.0630
df: 396
sd: 6.3910

The returned value of` h = 1`

indicates that `ttest2`

rejects the null hypothesis at the default significance level of 5%, in favor of the alternative hypothesis that the population mean for the mileage of cars made in the 1970s is less than the population mean for the mileage of cars made in the 1980s.

Plot the corresponding Student's *t*-distribution, the returned *t*-statistic, and the critical *t*-value. Calculate the critical *t*-value at the default confidence level of 95% by using `tinv`

.

nu = stats.df; k = linspace(-15,15,300); tdistpdf = tpdf(k,nu); tval = stats.tstat

tval = -14.0630

tvalpdf = tpdf(tval,nu); tcrit = -tinv(0.95,nu)

tcrit = -1.6487

plot(k,tdistpdf) hold on scatter(tval,tvalpdf,"filled") xline(tcrit,"--") legend(["Student's t pdf","t-statistic", ... "Critical Cutoff"])

The orange dot represents the *t*-statistic and is located to the left of the dashed black line that represents the critical *t*-value.

## Input Arguments

`x`

— Sample data

vector | matrix | multidimensional array

Sample data, specified as a vector, matrix, or multidimensional
array. `ttest2`

treats `NaN`

values
as missing data and ignores them.

If

`x`

and`y`

are specified as vectors, they do not need to be the same length.If

`x`

and`y`

are specified as matrices, they must have the same number of columns.`ttest2`

performs a separate*t*-test along each column and returns a vector of results.If

`x`

and`y`

are specified as multidimensional arrays, they must have the same size along all but the first nonsingleton dimension.

**Data Types: **`single`

| `double`

`y`

— Sample data

vector | matrix | multidimensional array

Sample data, specified as a vector, matrix, or multidimensional
array. `ttest2`

treats `NaN`

values
as missing data and ignores them.

If

`x`

and`y`

are specified as vectors, they do not need to be the same length.If

`x`

and`y`

are specified as matrices, they must have the same number of columns.`ttest2`

performs a separate*t*-test along each column and returns a vector of results.If

`x`

and`y`

are specified as multidimensional arrays, they must have the same size along all but the first nonsingleton dimension.`ttest2`

works along the first nonsingleton dimension.

**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.

*
Before R2021a, use commas to separate each name and value, and enclose*
`Name`

*in quotes.*

**Example: **`'Tail','right','Alpha',0.01,'Vartype','unequal'`

specifies
a right-tailed test at the 1% significance level, and does not assume
that `x`

and `y`

have equal population
variances.

`Alpha`

— Significance level

`0.05`

(default) | scalar value in the range (0,1)

Significance level of the hypothesis test, specified as the
comma-separated pair consisting of `'Alpha'`

and
a scalar value in the range (0,1).

**Example: **`'Alpha',0.01`

**Data Types: **`single`

| `double`

`Dim`

— Dimension

first nonsingleton dimension (default) | positive integer value

Dimension of the input matrix along which to test the means,
specified as the comma-separated pair consisting of `'Dim'`

and
a positive integer value. For example, specifying `'Dim',1`

tests
the column means, while `'Dim',2`

tests the row means.

**Example: **`'Dim',2`

**Data Types: **`single`

| `double`

`Tail`

— Type of alternative hypothesis

`'both'`

(default) | `'right'`

| `'left'`

Type of alternative hypothesis to evaluate, specified as the comma-separated pair consisting
of `'Tail'`

and one of:

`'both'`

— Test against the alternative hypothesis that the population means are not equal.`'right'`

— Test against the alternative hypothesis that the population mean of`x`

is greater than the population mean of`y`

.`'left'`

— Test against the alternative hypothesis that the population mean of`x`

is less than the population mean of`y`

.

`ttest2`

tests the null hypothesis that the
population means are equal against the specified alternative
hypothesis.

**Example: **`'Tail','right'`

`Vartype`

— Variance type

`'equal'`

(default) | `'unequal'`

Variance type, specified as the comma-separated pair consisting
of `'Vartype'`

and one of the following.

`'equal'` | Conduct test using the assumption that `x` and `y` are
from normal distributions with unknown but equal variances. |

`'unequal'` | Conduct test using the assumption that `x` and `y` are
from normal distributions with unknown and unequal variances. This
is called the Behrens-Fisher problem. `ttest2` uses
Satterthwaite’s approximation for the effective degrees of
freedom. |

`Vartype`

must be a single variance type, even
when `x`

is a matrix or a multidimensional array.

**Example: **`'Vartype','unequal'`

## Output Arguments

`h`

— Hypothesis test result

`1`

| `0`

Hypothesis test result, returned as `1`

or `0`

.

A value of

`1`

indicates the rejection of the null hypothesis at the`Alpha`

significance level.A value of

`0`

indicates a failure to reject the null hypothesis at the`Alpha`

significance level.

`p`

— *p*-value

scalar value in the range [0,1]

*p*-value of the test, returned as a scalar value in the range [0,1].
`p`

is the probability of observing a test statistic that is as
extreme as, or more extreme than, the observed value under the null hypothesis. A small
value of `p`

indicates that the null hypothesis might not be
valid.

`stats`

— Test statistics

structure

Test statistics for the two-sample *t*-test,
returned as a structure containing the following:

`tstat`

— Value of the test statistic.`df`

— Degrees of freedom of the test.`sd`

— Pooled estimate of the population standard deviation (for the equal variance case) or a vector containing the unpooled estimates of the population standard deviations (for the unequal variance case).

## More About

### Two-Sample *t*-test

The two-sample *t*-test is
a parametric test that compares the location parameter of two independent
data samples.

The test statistic is

$$t=\frac{\overline{x}-\overline{y}}{\sqrt{\frac{{s}_{x}^{2}}{n}+\frac{{s}_{y}^{2}}{m}}},$$

where $$\overline{x}$$ and $$\overline{y}$$ are the sample means, *s _{x}* and

*s*are the sample standard deviations, and

_{y}*n*and

*m*are the sample sizes.

In the case where it is assumed that the two data samples are
from populations with equal variances, the test statistic under the
null hypothesis has Student's *t* distribution
with *n* + *m* –
2 degrees of freedom, and the sample standard
deviations are replaced by the pooled standard deviation

$$s=\sqrt{\frac{\left(n-1\right){s}_{x}^{2}+\left(m-1\right){s}_{y}^{2}}{n+m-2}.}$$

In the case where it is not assumed that the two data samples
are from populations with equal variances, the test statistic under
the null hypothesis has an approximate Student's *t* distribution
with a number of degrees of freedom given by Satterthwaite's approximation.
This test is sometimes called Welch’s *t*-test.

### Multidimensional Array

A multidimensional array has more than two
dimensions. For example, if `x`

is a 1-by-3-by-4
array, then `x`

is a three-dimensional array.

### First Nonsingleton Dimension

The first nonsingleton dimension is the first
dimension of an array whose size is not equal to 1. For example, if `x`

is
a 1-by-2-by-3-by-4 array, then the second dimension is the first nonsingleton
dimension of `x`

.

## Tips

Use

`sampsizepwr`

to calculate:The sample size that corresponds to specified power and parameter values;

The power achieved for a particular sample size, given the true parameter value;

The parameter value detectable with the specified sample size and power.

## Extended Capabilities

### GPU Arrays

Accelerate code by running on a graphics processing unit (GPU) using Parallel Computing Toolbox™.

This function fully supports GPU arrays. For more information, see Run MATLAB Functions on a GPU (Parallel Computing Toolbox).

## Version History

**Introduced before R2006a**

## See Also

`ttest`

| `ztest`

| `sampsizepwr`

## 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)