6/6/22, 7:55 AM Paired t-Test - DATAtab

Paired sample t-test

The paired samples t-test is a statistical test that
determines whether there is a difference
between two
dependent groups.
The paired samples t-test, or also known as the dependent t-test, tests whether the
mean
values of two dependent groups differ significantly from each other. It tests
whether the
mean values of the two groups differ.

Why do you need the paired t-Test?

You need the paired t-test whenever you survey the same group or sample at two
points in
time. For example, you might be interested in whether a rehabilitation
program has a positive
effect on physical fitness. Since you can't ask all the people
who go to rehab, you use a
random sample. You can then use the paired t-test to
infer the population from the sample.

https://datatab.net/tutorial/paired-t-test 1/9
6/6/22, 7:55 AM Paired t-Test - DATAtab

What are dependent or paired samples?

Before you can
calculate a paired t-test
you need two dependent samples. A
dependent sample is when
two samples affect each other.

For dependent samples, the measured values are available in pairs. The pairs
result from
measurement repetitions, parallelization or matching. This can be the
case, for example, in
longitudinal studies with several measurement points in time
(time series analyses) or in
intervention studies with experimental designs (before
and after measurements).

A simple example of dependent sampling would be to measure the weight of a

group of
people at two points in time. One person can then be uniquely assigned a
weight at the first
and second measurement and the difference between the
measured values can be calculated.

What is the advantage of a dependent t-test over

an independent t-test?
The question of whether to use a dependent t-test or an independent t-test is, of
course,
already determined as part of the study design, and it is not possible to
arbitrarily use
either one test or the other. Therefore, the question is rather which
type of study makes
more sense:

Conducting a study with one group of participants who are measured twice.
To conduct a study with two separate groups of participants, each measured
once.
https://datatab.net/tutorial/paired-t-test 2/9
6/6/22, 7:55 AM Paired t-Test - DATAtab

The major advantage of a repeated-measures design that then uses the dependent
t-test is that
individual differences between participants can be eliminated. This
means that the
probability of detecting a (statistically significant) difference, if one
exists, is higher
with the dependent t-test than with the independent t-test.

Example of a paired sample t-test

The t-test for dependent samples has numerous applications, here are three
examples.

Medical example:
You want to check whether a new drug increases memory performance. You will
test the memory
performance of 40 people before and after they take the medicine.

Technical example:
A screw factory complains about very high downtimes at its 5 production plants.
You are now
to find out whether a newly introduced lubricant has an influence on
the downtimes. For this
you compare the downtimes of the 5 plants before and
after the introduction of the new
lubricant.

Social science example:

You want to find out if there is a change between 2010 and 2015 in terms of health
consciousness of the German population For example you could do this rely on
https://datatab.net/tutorial/paired-t-test 3/9
6/6/22, 7:55 AM Paired t-Test - DATAtab
consciousness of the German population. For example, you could do this rely on
data from the
Socio-Economic Panel (SOEP). The SOEP is a representative repeat
survey of private households
in Germany. The survey will include always asks the
same people at regular intervals about
the same topics. To get your question to
answer you compare the health consciousness of the
persons in the year 2010 and
2015.

Questions and hypotheses

In order to be able to
calculate a t-test for dependent samples, you first need to
define a question and the hypotheses

Question
In a t-test for dependent samples, the general question is: Is there a statistically
significant difference between the mean value of two dependent groups?

The questions for the above examples arise as follows:

Does the new drug help to increase memory performance?

Does the newly introduced lubricant have an influence on downtimes?
Has the health consciousness of the German population changed between
2010 and
2015?

Hypotheses
Now the hypothesis can be derived from the question.
In the hypothesis, a
preliminary, i.e. unsubstantiated, assumption is made which is to be
tested. In the
case of a
t test for dependent samples are the hypotheses:
Null hypothesis H0: The mean value of the two dependent groups is equal.
Alternative hypothesis H1: The mean values of the two dependent groups
are different.

Assumptions paired t-Test

Of course, the prerequisites must be checked before calculating the dependent t-
t t If th i it 2
https://datatab.net/tutorial/paired-t-test d3 t f lfill d th Wil t t tb d 4/9
6/6/22, 7:55 AM Paired t-Test - DATAtab
test. If the
prerequisites 2. and 3. are not fulfilled, the
Wilcoxon test must be used.
The Wilcoxon test is
the
non-parametric counterpart of the paired t-test.

1. There are two dependent groups or samples

As the name paired t-test already suggests the groups must be dependent, i.e. a
value of one
group must belong to a value of the other group.
 The weight of one and the same person is measured before and after a diet.
 Researchers measure the weight of people who have been on a diet and
people who have not.

2. The variables must be interval scaled

In the t-test for dependent samples, the difference between the two dependent
values is
calculated and then the mean value. This only makes sense if the values
are
metric
 The salary of a person (in Euro)
 The educational level of a person

3. The differences of the paired values are normally distributed.

The difference between the paired values
must be normally distributed.
 The difference from the weight of one person at two points in time.
 The difference in the number of points after throwing two dice.

How does a dependent t-test works?

In the dependent t-test, the difference is calculated from each paired case. The
mean value
is then calculated from these differences. Depending on how large the
mean value is and how
large the standard error of the mean value is, a statement is
then made as to how likely it
is that this result has arisen by chance.

Calculate t-test for dependent samples

For the calculation of the t-test for dependent samples, the difference of each
pair
from the two groups is first formed. From the resulting differences, the mean
value
x̄ diff is then calculated.
https://datatab.net/tutorial/paired-t-test 5/9
6/6/22, 7:55 AM Paired t-Test - DATAtab

The calculation of the test statistics t is now equal to the

t test for one sample. If
there is no
difference between the two groups, the mean value of the difference
x̄ diff
is zero. So the question is, is there a difference between
x̄ diff and zero. The test
statistic t for the t-test for
dependent samples is then calculated as

where

is the standard error of the mean value

= Difference between the groups

= Mean value of the difference between the two groups

= Sample size

= Standard deviation

= Estimated standard error of mean

Example in DATAtab
https://datatab.net/tutorial/paired-t-test 6/9
6/6/22, 7:55 AM Paired t-Test - DATAtab
Example in DATAtab
In the paired t-test example it is examined whether the summer holidays have an
effect
on the physical fitness of students.

So the question is: Do the summer holidays have an effect on the physical fitness
of
statistics students? For this purpose, a fitness test is carried out once before and
once
after the holidays for 10 statistics students (2 measurement points).

The average difference of the measured value pairs (before and after the
holidays) is zero.
 The semester break has no influence on the
physical
fitness of the students.

Since two test results always come from one student, there is a dependency
between the two
samples. Therefore the paired t-test is used.

Statistics student Points before holidays Points after holidays

1 60 61

2 70 71

3 40 38

4 41 39

5 40 38

6 40 33

7 45 55

8 48 56

9 30 38

10 50 68

After copying the upper table into the

t-test calculator
you can calculate the t-test.
The results are as follows:
Statistics
https://datatab.net/tutorial/paired-t-test 7/9
6/6/22, 7:55 AM Paired t-Test - DATAtab
Statistics
n Mean value Standard deviation Standard error of the mean

Points before holidays 10 46.4 11.452 3.622

Points after holidays 10 49.7 14.095 4.457

Correlation
n Correlation

before holidays - after holidays 10 0,847

Paired t-test
t df p-value (2-tailed)

before holidays - after holidays -1.39 9 0,197

95% confidence interval of the difference

Standard Standard error of the
Mean deviation mean Lower Upper

Points before -3.3 7.5 2.37 -8.66 2.06

holidays

Points after holidays

Interpret t-test for dependent samples

The score of the variable before the vacations had lower values (M = 46.4, SD =
11.452) than the score of the variable after the vacations (M = 49.7, SD =
14.095).
A t-test for dependent samples showed that this difference was not statistically
significant, t(9) = -1.392 p = .197, 95% confidence interval [-8.664, 2.064].

This results in a p-value of 0.197 which is above the defined significance level of
0.05. The
t-test result is therefore not significant and the null hypothesis is
maintained. It is
therefore assumed that both samples are from the same
population.

https://datatab.net/tutorial/paired-t-test 8/9
6/6/22, 7:55 AM Paired t-Test - DATAtab

Effect size dependent t-test

The indication of the effect size is very important for empirical studies. To make a
statement about the effect size in a t-test for dependent samples, the following
formula can be used

In general, it can be said about the effect size:

Effect size r: 0,2  small Effect

Effect size r: 0,5  medium Effect
Effect size r: 0,8  large Effect

Cite DATAtab: DATAtab Team (2022). DATAtab: Online Statistics Calculator. DATAtab
e.U. Graz,
Austria. URL https://datatab.net

https://datatab.net/tutorial/paired-t-test 9/9