Paired Samples t Test
The Paired Samples t Test compares two means that are from the same individual,
object, or related units. The two means typically represent two different times
(e.g., pre-test and post-test with an intervention between the two time points) or
two different but related conditions or units (e.g., left and right ears, twins). The
purpose of the test is to determine whether there is statistical evidence that the
mean difference between paired observations on a particular outcome is
significantly different from zero. The Paired Samples t Test is a parametric test.
This test is also known as:
Dependent t Test
Paired t Test
Repeated Measures t Test
The variable used in this test is known as:
Dependent variable, or test variable (continuous), measured at two different
times or for two related conditions or units
Common Uses
The Paired Samples t Test is commonly used to test the following:
Statistical difference between two time points
Statistical difference between two conditions
Statistical difference between two measurements
Statistical difference between a matched pair
Note: The Paired Samples t Test can only compare the means for two (and only
two) related (paired) units on a continuous outcome that is normally distributed.
The Paired Samples t Test is not appropriate for analyses involving the following:
1) unpaired data; 2) comparisons between more than two units/groups; 3) a
continuous outcome that is not normally distributed; and 4) an ordinal/ranked
outcome.
To compare unpaired means between two groups on a continuous outcome
that is normally distributed, choose the Independent Samples t Test.
To compare unpaired means between more than two groups on a continuous
outcome that is normally distributed, choose ANOVA.
To compare paired means for continuous data that are not normally
distributed, choose the nonparametric Wilcoxon Signed-Ranks Test.
To compare paired means for ranked data, choose the nonparametric
Wilcoxon Signed-Ranks Test.
Data Requirements
Your data must meet the following requirements:
1. Dependent variable that is continuous (i.e., interval or ratio level)
1. Note: The paired measurements must be recorded in two separate
variables.
2. Related samples/groups (i.e., dependent observations)
1. The subjects in each sample, or group, are the same. This means that
the subjects in the first group are also in the second group.
3. Random sample of data from the population
4. Normal distribution (approximately) of the difference between the paired
values
5. No outliers in the difference between the two related groups
Note: When testing assumptions related to normality and outliers, you must use a
variable that represents the difference between the paired values - not the original
variables themselves.
Note: When one or more of the assumptions for the Paired Samples t Test are not
met, you may want to run the nonparametric Wilcoxon Signed-Ranks Test instead.
Hypotheses
The hypotheses can be expressed in two different ways that express the same idea
and are mathematically equivalent:
H0: µ1 = µ2 ("the paired population means are equal")
H1: µ1 ≠ µ2 ("the paired population means are not equal")
OR
H0: µ1 - µ2 = 0 ("the difference between the paired population means is equal to 0")
H1: µ1 - µ2 ≠ 0 ("the difference between the paired population means is not 0")
where
µ1 is the population mean of variable 1, and
µ2 is the population mean of variable 2.
Test Statistic
The test statistic for the Paired Samples t Test, denoted t, follows the same formula
as the one sample t test.
The calculated t value is then compared to the critical t value with df = n - 1 from
the t distribution table for a chosen confidence level. If the calculated t value is
greater than the critical t value, then we reject the null hypothesis (and conclude
that the means are significantly different).
Data Set-Up
Your data should include two variables (represented in columns) that will be used
in the analysis. The two variables should represent the paired variables for each
subject (row). If your data are arranged differently (e.g., cases represent repeated
units/subjects), simply restructure the data to reflect this format.
Run a Paired Samples t Test
To run a Paired Samples t Test in SPSS,
click Analyze > Compare Means > Paired-Samples T Test.
The Paired-Samples T Test window opens where you will specify the variables to be
used in the analysis. All of the variables in your dataset appear in the list on the
left side. Move variables to the right by selecting them in the list and clicking the
blue arrow buttons. You will specify the paired variables in the Paired Variables
area.
A Pair: The “Pair” column represents the number of Paired Samples t Tests to
run. You may choose to run multiple Paired Samples t Tests simultaneously by
selecting multiple sets of matched variables. Each new pair will appear on a new
line.
B Variable1: The first variable, representing the first group of matched values.
Move the variable that represents the first group to the right where it will be listed
beneath the “Variable1” column.
C Variable2: The second variable, representing the second group of matched
values. Move the variable that represents the second group to the right where it
will be listed beneath the “Variable2” column.
D Options: Clicking Options will open a window where you can specify
the Confidence Interval Percentage and how the analysis will address Missing
Values (i.e., Exclude cases analysis by analysis or Exclude cases listwise).
Click Continue when you are finished making specifications.
Click OK to run the Paired Samples t Test.
Example
PROBLEM STATEMENT
The sample dataset has placement test scores (out of 100 points) for four subject
areas: English, Reading, Math, and Writing. Suppose we are particularly interested
in the English and Math sections, and want to determine whether English or Math
had higher test scores on average. We could use a paired t test to test if there was
a significant difference in the average of the two tests.
BEFORE THE TEST
Variable English has a high of 101.95 and a low of 59.83, while variable Math has a
high of 93.78 and a low of 35.32 (Analyze > Descriptive Statistics >
Descriptives). The mean English score is much higher than the mean Math score
(82.79 versus 65.47). Additionally, there were 409 cases with non-missing English
scores, and 422 cases with non-missing Math scores, but only 398 cases with non-
missing observations for both variables. (Recall that the sample dataset has 435
cases in all.)
Let's create a comparative boxplot of these variables to help visualize these
numbers. Click Analyze > Descriptive Statistics > Explore. Add English and
Math to the Dependents box; then, change the Display option to Plots. We'll also
need to tell SPSS to put these two variables on the same chart. Click
the Plots button, and in the Boxplots area, change the selection to Dependents
Together. You can also uncheck Stem-and-leaf. Click Continue. Then
click OK to run the procedure.
We can see from the boxplot that the center of the English scores is much higher
than the center of the Math scores, and that there is slightly more spread in the
Math scores than in the English scores. Both variables appear to be symmetrically
distributed. It's quite possible that the paired samples t test could come back
significant.
RUNNING THE TEST
1. Click Analyze > Compare Means > Paired-Samples T Test.
2. Double-click on variable English to move it to the Variable1 slot in the Paired
Variables box. Then double-click on variable Math to move it to the Variable2
slot in the Paired Variables box.
3. Click OK.
SYNTAX
T-TEST PAIRS=English WITH Math (PAIRED)
/CRITERIA=CI(.9500)
/MISSING=ANALYSIS.
OUTPUT
TABLES
There are three tables: Paired Samples Statistics, Paired Samples
Correlations, and Paired Samples Test. Paired Samples Statistics gives
univariate descriptive statistics (mean, sample size, standard deviation, and
standard error) for each variable entered. Notice that the sample size here is 398;
this is because the paired t-test can only use cases that have non-missing values for
both variables. Paired Samples Correlations shows the bivariate Pearson
correlation coefficient (with a two-tailed test of significance) for each pair of
variables entered. Paired Samples Test gives the hypothesis test results.
The Paired Samples Statistics output repeats what we examined before we ran the
test. The Paired Samples Correlation table adds the information that English and
Math scores are significantly positively correlated (r = .243).
Why does SPSS report the correlation between the two variables when you run a
Paired t Test? Although our primary interest when we run a Paired t Test is finding
out if the means of the two variables are significantly different, it's also important
to consider how strongly the two variables are associated with one another,
especially when the variables being compared are pre-test/post-test measures.
Reading from left to right:
First column: The pair of variables being tested, and the order the
subtraction was carried out. (If you have specified more than one variable
pair, this table will have multiple rows.)
Mean: The average difference between the two variables.
Standard deviation: The standard deviation of the difference scores.
Standard error mean: The standard error (standard deviation divided by
the square root of the sample size). Used in computing both the test statistic
and the upper and lower bounds of the confidence interval.
t: The test statistic (denoted t) for the paired T test.
df: The degrees of freedom for this test.
Sig. (2-tailed): The p-value corresponding to the given test statistic t with
degrees of freedom df.
DECISION AND CONCLUSIONS
From the results, we can say that:
English and Math scores were weakly and positively correlated (r =
0.243, p < 0.001).
There was a significant average difference between English and Math scores
(t397 = 36.313, p < 0.001).
On average, English scores were 17.3 points higher than Math scores (95%
CI [16.36, 18.23]).