T Test

PAIRED-
SAMPLES T-
TEST
 to determine whether the mean difference
between paired observations is statistically
significantly different from zero.
 same individuals tested at two time points or
 under two different conditions on the same
dependent variable
 The paired-samples t-test is also referred to as
 dependent t-test,
 repeated measures t-test, or
 simply abbreviated to the paired t-test.
Examples
 whether there was a mean difference in dieters'

daily calorie consumption before and after a six
week hypnotherapy programme
 whether there was a mean difference in reaction
times under two different lighting conditions.
Health professionals want to investigate the
medium-term effect of a hypnotherapy
programme on the daily cigarette use of
heavy smokers
 Research question
Is there a difference in daily cigarette use
amongst heavy smokers six months after a
hypnotherapy programme?
 Null hypothesis
There is no difference in daily cigarette use
hypnotherapy programme.
Alternative hypothesis
There is a difference in daily cigarette use
hypnotherapy programme.
 Dependent variable
Cigarette consumption (measured in terms of the
number of cigarettes smoked daily)
Independent variable
Time, which has two levels:
Time point #1: Immediately before the start of the
hypnotherapy programme
Time point #2: 6 months after completion of the
hypnotherapy programme
Determine if there are differences
between conditions
the same participants are being measured on the same dependent

variable but under two different conditions (linear approach)
Determine if there are differences
between conditions
the same participants are being measured on the same dependent

variable but under two different conditions (cross over approach)
An online retailer wants to know whether using
background music in their order fulfilment
centre would lead to greater productivity
amongst packers
Is there a difference in productivity amongst
packers based on the use of background music?
Null hypothesis
There is no difference in productivity amongst
packers based on the use of background music.
Alternative hypothesis
There is a difference in productivity amongst
packers based on the use of background music
Productivity (measured in terms of packages
processed per hour)
Background music
Group 1: No Music (the "control")
Group 2: Music (the "treatment") Dependent variable
Productivity (measured in terms of packages
processed per hour)
Background music
Group 1: No Music (the "control")
Group 2: Music (the "treatment")
Basic requirements of the paired-
samples
 t-test
You have one dependent variable that is measured
atcontinuous (i.e., ratio or interval) level.
 Pretest and posttest scores must be normally
distributed
 You have one independent variable that consists of two
categorical, related groups or matched pairs (i.e.,
a dichotomous variable).
 "Related groups" indicates that the two groups are not
independent.
Hypothesis
 The null hypothesis (H0) for a paired-samples t-test

is:
 H0: the population mean difference between the
paired values is equal to zero (i.e., µdiff = 0).
 And the alternative hypothesis (HA) is:
 HA: the population mean difference between the
paired values is not equal to zero (i.e., µdiff ≠ 0).
Example
 Refer to your putrablast data:

 A researcher wants to test a new formula for a
sports drink that improves running performance.
Instead of a regular, carbohydrate-only drink, this
new sports drink contains a new carbohydrate-
protein mixture.
 The researcher would like to know whether this
new carbohydrate-protein drink leads to a
difference in performance compared to the
carbohydrate-only sports drink.
 20 participants who each performed two trials in
which they had to run as far as possible in 2 hours
on a treadmill.
 In one of the trials they drank the carbohydrate-
only drink and in the other trial they drank the
carbohydrate-protein drink.
 The order of the trials was counterbalanced and
the distance they ran in both trials was recorded.
 For a paired-samples t-test, you will have two
variables. In this example, these are:
 1) carb, which is the distance run (in km) in two
hours for the carbohydrate-only trial;
and
 2) carb_protein, which is the distance run (in km) in
two hours for the carbohydrate-protein trial.

By default, SPSS Statistics uses 95% confidence intervals (expressed as the Confidence
Interval Percentage in SPSS Statistics). This equates to setting statistical significance at
the p < .05 level. If you wish to change this level, you can enter any value from 1 to 99.
For example, a 99% confidence interval would equate to declaring statistical
significance at the p< .01 level. The calculated confidence intervals would also be
different.
The columns of the table above have the following meaning:
Interpreting Results
Column Name Meaning

1 Mean Mean/average
2 N Number of cases (e.g.,
participants)
3 Std. Deviation •(Sample) Standard
deviation
4 Std. Error Mean Standard error of the
mean
.
The carbohydrate-protein drink elicited an increase of
0.136 (95% CI, 0.091 to 0.180) km in the distance run
in two hours compared to a carbohydrate-only drink.
The carbohydrate-protein drink elicited a statistically significant
increase in distance run in two hours compared to a
carbohydrate-only drink, t(19) = 6.352, p < .001.
There was a statistically significant difference between means

(p < .05), and therefore, we can reject the null hypothesis and
accept the alternative hypothesis.
effect size
 Effect size is a simple way of quantifying the difference
between two groups
 Provides a measure of size of the difference between the two
group means
Where M is the mean difference between the two related

groups and SD is the standard deviation of this difference
Therefore, the effect size, d, can be calculated as:
An effect size is an attempt to provide a measure of the practical
significance of the result. The importance of the value of
Cohen's d (as reported by Cohen (1998) is as follows:
Effect
Strength
Size
.2 small
.5 medium
.8 large
As the effect size, d, is 1.42 you can conclude that there is a

large effect.
Exercise
Are there differences between the pretest and the
posttest in height and flexibility (sr) among boys and
girls in the ordinary schools?
 Null hypothesis
 Alternative hypothesis
 Independent variable
 Results
 Decision
 Effect size

T Test

Uploaded by

Copyright:

Available Formats

T Test

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

T Test

Uploaded by

Copyright:

Available Formats

PAIRED-

 whether there was a mean difference in dieters'

the same participants are being measured on the same dependent

the same participants are being measured on the same dependent

 The null hypothesis (H0) for a paired-samples t-test

 Refer to your putrablast data:

Column Name Meaning

There was a statistically significant difference between means

Where M is the mean difference between the two related

As the effect size, d, is 1.42 you can conclude that there is a

You might also like