Chapter 9

Introduction to the t Statistic

PowerPoint Lecture Slides
Essentials of Statistics for the
Behavioral Sciences
Eighth Edition
by Frederick J Gravetter and Larry B. Wallnau
 Chapter 9 Learning Outcomes

• Know when to use t statistic instead of z-

1 score hypothesis test

2 • Perform hypothesis test with t-statistics

• Evaluate effect size by computing Cohen’s d,

3 percentage of variance accounted for (r2)
 Tools You Will Need
• Sample standard deviation (Chapter 4)

• Standard error (Chapter 7)

• Hypothesis testing (Chapter 8)

 9.1 Review Hypothesis Testing
with z-Scores
• Sample mean (M) estimates (& approximates)
population mean (μ)
• Standard error describes how much difference
is reasonable to expect between M and μ.
• either or
• 
M   2

n M 
n
 z-Score Statistic
• Use z-score statistic to quantify inferences about the
population.
M  obtained difference between data and hypothesis
z 
M standard distance between M and 

• Use unit normal table to find the critical region if z-

scores form a normal distribution
– When n ≥ 30 or
– When the original distribution is approximately normally
distributed
 Problem with z-Scores
• The z-score requires more information than
researchers typically have available

• Requires knowledge of the population

standard deviation σ

• Researchers usually have only the sample data

available
 Introducing the t Statistic

• t statistic is an alternative to z
• t might be considered an “approximate” z
• Estimated standard error (sM) is used as in
place of the real standard error when the
value of σM is unknown
 Estimated standard error
• Use s2 to estimate σ2
• Estimated standard error:

s s2
estimated standard error  sM  or
n n

• Estimated standard error is used as estimate

of the real standard error when the value of
σM is unknown.
 The t-Statistic
• The t-statistic uses the estimated standard
error in place of σM
M 
t
sM

• The t statistic is used to test hypotheses about

an unknown population mean μ when the
value of σ is also unknown
 Degrees of freedom
• Computation of sample variance requires
computation of the sample mean first.
– Only n-1 scores in a sample are independent
– Researchers call n-1 the degrees of freedom

• Degrees of freedom
– Noted as df
– df = n-1
 Figure 9.1
Distributions of the t statistic
 The t Distribution
• Family of distributions, one for each value of
degrees of freedom
• Approximates the shape of the normal
distribution
– Flatter than the normal distribution
– More spread out than the normal distribution
– More variability (“fatter tails”) in t distribution
• Use Table of Values of t in place of the Unit
Normal Table for hypothesis tests
 Figure 9.2
The t distribution for df=3
 9.2 Hypothesis tests with
the t statistic
• The one-sample t test statistic (assuming the
Null Hypothesis is true)

sample mean - population mean M  

t  0
estimated standard error sM
Figure 9.3 Basic experimental
situation for t statistic
 Hypothesis Testing: Four Steps
• State the null and alternative hypotheses and
select an alpha level
• Locate the critical region using the t
distribution table and df
• Calculate the t test statistic
• Make a decision regarding H0 (null hypothesis)
 Example of a One-Sample t-test
 One subscale of the GATB assesses manual
dexterity. The mean performance of the normal
population is 3.0 on this scale. We want to test the
hypothesis that the performance of people (n = 6)
who have damage to their somatosensory cortex is
reduced.
 Is the mean performance significantly lower than
the mean performance in the population (α = .05)?
 The scores are as follows: 1.7, 3.0, 0.8, 3.4, 2.7,
2.1
 Example of a One-Sample t-test
Step 1: State hypotheses (note that this is a
directional hypothesis and a one-tailed test)
 null hypothesis = H0: μ > 3
 alternative hypothesis = H1: μ < 3
Step 2: Locate critical region
 α = .05
 df = n − 1 =5
 Critical t = ?
 Look at the critical t table
 t (5) = −2.015
 Example of a One-Sample t-test
Step 3: Collect sample data and compute the test
statistic
t= M − μ .

sM
 Compute the sample mean and variance, and then
compute the estimated standard error…
 Example of a One-Sample t-test
Manual Dexterity Performance
X X2
1.7 2.89
3.0 9
0.8 0.64
3.4 11.56
2.7 7.29
2.1 4.41 .

∑X = 13.7 ∑X2 = 35.79

M = 2.28
 Example of a One-Sample t-test
Here we’ll use the computational formula for sum of
squares, and then calculate the sample variance

(
 X)
2

SS   X  2

n
SS = 4.5083

s2 = SS = 0.902
n-1
 Example of a One-Sample t-test
Then calculate the estimated standard error of the
mean
2
s
sM 
n
sM = 0.388

t= M − μ . = 2.28 − 3.00 = −1.856

sM 0.388
 Example of a One-Sample t-test
tobtained = −1.856 > tcritical = −2.015

The test statistic does not fall in the critical region;

therefore, we do not reject the null hypothesis.

Based on these data, we have no evidence that

the mean manual dexterity of people with damage
to their somatosensory cortex is reduced, t(5) =
−2.015, p > .05.
 Assumptions of the t test
• Values in the sample are independent
observations.

• The population sampled must be normal.

– With large samples, this assumption can be
violated without affecting the validity of the
hypothesis test.
 9.3 Measuring Effect Size
• Hypothesis test determines whether the
treatment effect is greater than chance
– No measure of the size of the effect is included
– A very small treatment effect can be statistically
significant
• Therefore, results from a hypothesis test
should be accompanied by a measure of effect
size
 Cohen’s d
• Original equation included population
parameters
• Estimated Cohen’s d is computed using the
sample standard deviation

mean difference M 
estimated d  
sample standard deviation s
 In the Literature
• Report whether (or not) the test was
“significant”
• “Significant”  H0 rejected
• “Not significant”  failed to reject H0
• Report the t statistic value including df,
e.g., t(12) = 3.65
• Report significance level, either
• p < alpha, e.g., p < .05 or
• Exact probability, e.g., p = .023
 Learning Check
• The results of a hypothesis test are reported as
follows: t(21) = 2.38, p < .05. What was the
statistical decision and how big was the sample?
• The null hypothesis was rejected using a
A sample of n = 21
• The null hypothesis was rejected using a
B sample of n = 22
• The null hypothesis was not rejected using a
C sample of n = 21
• The null hypothesis was not rejected using a
D sample of n = 22
 Learning Check - Answer
• The results of a hypothesis test are reported as
follows: t(21) = 2.38, p < .05. What was the
statistical decision and how big was the sample?
• The null hypothesis was rejected using a
A sample of n = 21
• The null hypothesis was rejected using a
B sample of n = 22
• The null hypothesis was not rejected using a
C sample of n = 21
• The null hypothesis was not rejected using a
D sample of n = 22
 Learning Check
• Decide if each of the following statements
is True or False

• Sample size has a great influence

T/F on measures of effect size

• When the value of the t statistic is

T/F near 0, the null hypothesis should
be rejected
 Learning Check - Answers

• Measures of effect size are not

False influenced to any great extent by
sample size

• When the value of t is near 0, the

False difference between M and μ is
also near 0
 Equations?

Concepts
?

Any
Questions
?