t-test and z-

test
INFERENTIAL
S TAT I S T I C S
 - a statistical test that is used
to compare the means of two
groups.

t - test - often used in hypothesis

testing to determine whether
a process or treatment
influences the population of
interest, or whether two
groups are different from one
another.
 used for testing hypotheses regarding the
mean of a small sample taken population
when the standard deviation of the
population is not known.
used to determine if there is a significant
difference between the means of two
groups.
When to used for hypothesis testing to determine
use a t- whether a process influences both
test? samples or if the groups are different from
each
allowsother.
the comparison of the mean of two
sets of data and the determination if the
two sets are derived from the same
population.
it is like other tests like the z-test and f-
test except that t-test is usually performed
in cases where the sample size is small
(n≤30).
 If the groups come from a single
population (e.g. measuring before and
after an experimental treatment), perform
a paired t-test.
What type If the groups come from two different
of t-test populations (e.g. two different species, or
people from two separate cities), perform
should I a two-sample t-
test (a.k.a. independent t-test).
use? If there is one group being compared
against a standard value (e.g. comparing
the acidity of a liquid to a neutral pH of 7),
perform a one-sample t-test.
 If you only care whether
the two populations are
different from one
One-tailed another, perform a two-
and Two - tailed t-test.
If you want to know
tailed whether one population
mean is greater than or
less than the other,
perform a one-tailed t-
test.
Example •Your observations come from two
separate populations (separate species),
so you perform a two-sample t-test.
Determine whether the mean petal •You don’t care about the direction of the
length of iris flowers differs according to
their species. Find two different species difference, only whether there is a
of irises growing in a garden and
measure 25 petals of each species. Test
difference, so you choose to use a two-
the difference between these two tailed t-test.
groups using a t-test.
TESTING HYPOTHESIS
Steps:

• Formulate the null hypothesis. (H0 – null, Ha – alternative)

• Set the desired level of significance (α)
• Determine the appropriate test statistic to be used in testing the null
hypothesis.
• Compute for the value of the statistic to be used.
• Compute for the degrees of freedom.
• Find the tabular value using tables of values for different tests.
• Compare the computed value, CV to the tabular value TV or critical
value
• Make a conclusion using the result of the comparison
• Decision Rule: If the CV is greater than TV, REJECT the H0
Level of Significance

 denoted as alpha or α, is a measure of the strength of the evidence that must be present
in your sample before you will reject the null hypothesis and conclude that the effect is
statistically significant.
 probability of rejecting the null hypothesis when it is true.

For example, a significance level of 0.05 indicates a 5% risk of concluding that a difference
exists when there is no actual difference.
Lower significance levels indicate that you require stronger evidence before you will reject
the null hypothesis.
If the p-value is less than the significance level, REJECT the null hypothesis and conclude
that the effect is statistically significant. In other words, the evidence in your sample is
strong enough to be able to reject the null hypothesis at the population level.
  indicate the number of independent values
that can vary in an analysis without breaking
any constraints.
Degrees of  the number of df required will vary

Freedom depending on the size of distribution

Single group of population - N – 1
(df)
Two groups of population - N1 + N2 – 2 (t –
test) ;
N – 2 (Pearson’s)
p -value

The probability that you would obtain the effect observed in your sample, or
larger, if the null hypothesis is true for the populations.
P-values are calculated based on your sample data and under the assumption
that the null hypothesis is true.
Lower p-values indicate greater evidence against the null hypothesis.
Independent
Samples t-
test

Independent Sample T-
Test
Independent T-Test
Two Sample T-Test
Unpaired Samples T-Test
Student’s T-Test.
Independent t- test
Independent Samples t Test compares the means of
two independent groups in order to determine whether
there is statistical evidence that the associated population
means are significantly different.

Where:
‘x’ bar – mean of the sample
SS – sum of squares
N - number of observations
 Normally Random
Continuous
Distributed Sample

Similar
Enough Spread
Data Between
Groups

Assumptions for an Independent Samples T-Test

 You want to know if two groups
are different on your variable of
interest.
Your variable of interest
When to use is continuous.
an
You have two and only two
Independent groups.
Samples T-
Test? You have independent
samples.
You have a normal variable of
interest.
Independen Group 1: Received the experimental
medical treatment.
t Samples T- Group 2: Received a placebo or
Test control condition.
Variable of interest: Time to
Example recover from the disease in days.
 Male Female
14 12
Sample
18 9
Problem
17 11
The following are the 16 5
scores of 10 male and 10
female AB students in 4 10
spelling. Test the null
hypothesis that there is no 14 3
significant difference
between the performance
12 7
of male and female AB 10 2
students in the said test.
Use t-test at 0.05 level of 9 6
significance.
17 13
Solution
STEPWISE METHOD
I. Problem: Is there a significant difference between the performance of male and female students in
spelling?

II. Hypothesis:

H0 : There is no significant difference between the performance of male and female AB students in
Spelling.

H1 : There is a significant difference between the performance of male and female AB students in
Spelling.

III. Level of Significance

◦ df = n1+n2 – 2
◦ = 10 + 10 – 2
◦ = 18
◦ t 0.5 = 2.101
STEPWISE METHOD
IV. Statistics: t-test for two independent samples

V. Decision Rule: If the t-computed value is greater than or beyond the t-

tabular/critical value, REJECT the Ho

VI. Conclusion: Since the t-computed value of 2.88 is greater than t- tabular
value of 2.101 at 0.05 level of significance with 18 degrees of freedom, the null
hypothesis is rejected in favor of the research hypothesis. This means that there
is a significant difference between the performance of male and female AB
students in Spelling. It implies that the male performs better than the female
students considering that the mean score of the male students of 13.1 is greater
compared to the mean score of female students of only 7.8.
Paired
Samples T-
test

Dependent Sample T-
Test Paired T-Test.
 Paired Sample t- test
The Paired Samples t Test compares the means
of two measurements taken from the same
individual, object, or related units.

t=
Where:
‘D’ bar – mean difference
𝚺 – sum of squares of the difference
𝚺D – summation of the difference
N - number of observations/ sample size
 Continuous

Assumptions Normally Distributed

of Paired
Samples T- Random Sample
test
Enough Data
Similar Spread Between
Groups
 You want to know if two measurements
from a group are different on your
variable of interest
Your variable of interest is continuous
When to use
a Paired You have two and only two
Samples T- groups (i.e. two measurements from a
single group)
Test? You have paired samples

You have a normal variable of

interest
 Observation 1: A group of people
Paired were evaluated at baseline.
Samples T- Observation 2: This same group of
people were evaluated after a 12-
Test week exercise program.
Example Variable of interest: Cholesterol
levels.
 pretest posttest
20 25
30 35

Sample 10
15
25
25

Problem 20
10
20
20
18 22

An experimental study 14 20

was conducted on the 15 20

effect of programmed 20 15

materials in English on the 18 30

performance of 20 15 10

selected college students. 15 16

Before the program was 20 25

implemented the pretest 18 10
was administered and 40 45
after 5 months the same 10 15
instrument was used to 10 10
get the post test result. 12 18
20 25
Paired Samples T-test
Conclusion: The t-
computed value of – 3.17 is
beyond the critical value of
-1.73 at 0.05 level of
significance with 19
degrees of freedom, the
null hypothesis is therefore
rejected in favor of the
research hypothesis. This
means that the post test
result is higher than the
pretest result. It implies
that the use of
programmed materials in
English is effective.
One Sample
T- test
Single Sample T-Test

Single Sample Student

T-Test

One-Sample Test of
Means.
One Sample t- test
The one-sample t-test is a statistical
hypothesis test used to determine whether an unknown
population mean is different from a specific value.
 Continuous
Assumptions Normally
for a Single Distributed
Sample T-
Test Random Sample

Enough Data
 You want to know if one group
is different from a known or
hypothesized population value on
your variable of interest

When to use Your variable of interest

is continuous
a Single
Sample T-
Test? You have one group

Your variable of interest is normally

distributed
 A one-tailed test is used to determine if the population is
either lower than or higher than some hypothesized
value.

When to use A one-tailed test is appropriate if the estimated value

might depart from the sample value in either of the
a Single directions, left or right, but not both.

Sample T- For this test, the null hypothesis states that there is no
difference between the true mean and the assumed
Test? value whereas the alternative hypothesis states that
either the assumed value is greater than or less than
the true mean but not both.

For instance, if our H0: µ0 = µ and Ha: µ < µ0, such a test
would be a one-sided test or more precisely, a left-tailed
test.
 Group 1: Received the experimental
Single medical treatment.
Sample T- Population Value: On average in
the population, it takes 12 days to
Test recover from the disease
Example Variable of interest: Time to
recover from the disease in days.
Sample Problem
If a sample of 10 copper wires is found to have a mean breaking strength of 527
kgs, is it feasible to regard the sample as a part of a large population with a mean
breaking strength of 578 kgs and a standard deviation of 12.72 kgs? Test at 5%
level of significance.

H0 = The mean breaking strength of the population is equal to 578 kgs,

H1 = The mean breaking strength of the population is not equal to 578 kgs.
◦ kg.
◦ 𝜇= 578 𝑘𝑔.
◦ 𝛿= 12.72 𝑘𝑔
◦ n = 10
53
53
56
43
48 Seatwork:
63
55
The masses in grams of 18 randomly chosen Okra
56
grown in a commercial greenhouse were as
48 follows:
57
46 Other growers have found that the mean mass of
51 this sort of Okra is 50 g. Perform the t –test to
52 determine whether the mean mass of okra from
48 this greenhouse is different from the expected
55 value. (α=0.05, one-tailed)
49
52
55
 a statistical test to determine
whether two population
means are different when the
One Sample z- test variances are known and the
sample size is large. It can be
used to test hypotheses in
which the z-test follows a
normal distribution.
Level of
Significance 0.00 0.00
(α) 0.10 0.05 0.01 5 2
zα for 1-Tailed Tests − 1.28 − 1.645 − 2.33 − 2.58 − 2.88
or 1.28 or or 2.33 or 2.58 or 2.88
1.645

zα for 2-Tailed Tests − 1.645 − 1.96 − 2.58 − 2.81 − 3.08

and and and and and
1.645 1.96 2.58 2.81 3.08
Two- Samples z-test
T-test vs z- test
 BASIS FOR
Comparison COMPARISON
T-TEST Z-TEST

Chart Meaning T-test refers to a

type of parametric
Z-test implies a
hypothesis test
test that is applied which ascertains if
to identify, how the the means of two
means of two sets datasets are
of data differ from different from each
one another when other when
variance is not variance is given.
given.
Based on Student-t Normal distribution
distribution
Population variance Unknown Known
Sample Size Small Large
 1. A law student who wants to verify the claim of
RTC Judge that convicted illegal gamblers spend
on the average of 10.8 months in jail. A random
sample of 40 cases from court files showed that
the mean is 11.8 months, and the standard
deviation is 3.5 months. Use one-sample z-test to
test the null hypothesis of = 10.8 months against
the alternative hypothesis 10.8 months at 0.05
level of significance.
Seatwork 2. Is there a significant difference between the
average height of males born from two different
countries. A random samples yielded the following
results. Use 0.05 to test the null hypothesis that
the corresponding population means are equal
against the alternative hypothesis that they are
not equal.
N1 = 100 = 63.8 = 2.58
N2 = 120 = 63.1 = 2.62