Hypothesis (Pooled/non-pooled T-

Test)
Biomedical Statistics
Introducing Independent Random Samples
 Let us examine two small populations, one with three men
and the other with four women, as seen in the image below.

 Say we select two samples, one of size two from the male
population and one of size three from the female one.
……
a) Provide all potential independent sample pairs.
b) Assuming random sample selection, find the
probability of receiving any given pair of
independent samples.
a) First table lists potential size 2 samples from the
male population on the left and potential size 3
samples from the female population on the right. As
indicated in second Table, we list every potential
male sample of size 2 along with every potential
female sample of size 3 to determine the potential
pairs of independent samples. Twelve separate
couples of two men and three women are possible.
 (Tables are on next slide)
……
b) There is a similar chance of selecting any of the 12
potential pairs of samples for independent simple random
sampling. Consequently, the likelihood of acquiring a
𝟏
specific pair of independent samples is
𝟏𝟐
Pooled T Test
 Purpose To perform a hypothesis test to compare two
population means, μ1 and μ2.
 Assumptions
 1. Simple random samples
 2. Independent samples
 3. Normal populations or large samples
 4. Equal population standard deviations
Steps
 Step 1 The null hypothesis is H0: μ1 = μ2,
 and the alternative hypothesis is
 Ha: μ1 ≠ μ2 Ha: μ1 <μ 2 Ha: μ1 >μ 2
(Two tailed) (Left tailed) (Right tailed)
 Step 2 Decide on the significance level, α.
 Step 3 Compute the value of the test statistic

Where
……
 Step 4 The critical value(s) are
±tα/2 or −tα or tα
(Two tailed) (Left tailed) (Right tailed)
with df = n1+n2−2. Use Table to find the critical value.
……
 Step 5 If the value of the test statistic falls in the
rejection region, reject H0; otherwise, do not reject H0.
 Step 6 Interpret the results of the hypothesis test.
Example 1
 College professor remuneration is the subject of studies by
the American Academy of University Instructors, which
reports its findings in the Annual Report. Let's say we wish
to determine whether college teacher wages in private and
public institutions stand out.
 ……
 Step 1 State the null and alternative hypotheses.
 The null and alternative hypotheses are, respectively,
 H0: μ1 = μ2 (mean salaries are the same)
 Ha: μ1 ≠ μ2 (mean salaries are different),

 where μ1 and μ2 are the mean salaries of all faculty

in private and public institutions, respectively.
 Note that the hypothesis test is two tailed.
……
 Initially, we identify the data we need statistical
summary for each of the two samples. We then verify
that the four prerequisites for utilizing the pooled t-test
are met.
 x1¯ = 88.19 s1 =26.21 n1 =35
 x2¯ = 73.18 s2 =23.95 n2 =30
……
 The samples are given as simple random samples,
therefore Assumption 1 is satisfied.
 The samples are given as independent samples, therefore
Assumption 2 is satisfied.
 The samples have sizes of 35 and 30, which are both
large; additionally, neither sample appears to have any
outliers, according to Figs. on the following slide. Thus,
Assumption 3 can be deemed satisfied.
……

 The sample standard deviations are 26.21 and 23.95.

These statistics are certainly close enough for us to
consider Assumption 4 satisfied.
 The preceding items suggest that the pooled t-test can be
used to carry out the hypothesis test.
……
 Step 1 State the null and alternative hypotheses
H0: μ1 = μ2 (mean salaries are the same)
Ha: μ1 ≠ μ2 (mean salaries are different)
where μ1 and μ2 are the mean salaries of all faculty in
private and public institutions, respectively. The
hypothesis test is two tailed.
 Step 2 Decide on the significance level, α.
The test is to be performed at the 5% significance level,
or α =0.05.
 Step 3 Compute the value of the test statistic
……
 Step 4 The critical values for a two-tailed test are ±tα/2
with df = n1 + n2 − 2. Use Table to find the critical
values.
 Here n1 =35 and n2 =30, so df=35 + 30 −2 = 63. Also,
from Step 2, we have α =0.05. In Table with df = 63,
we find that the critical values are ±tα/2 = ± t0.05/2
= ±t0.025 = ± 1.998, as shown in Fig.
……
 Step 5 If the value of the test statistic falls in the
rejection region, reject H0; otherwise, do not reject H0.
From Step 3, the value of the test statistic is t =2.395,
which falls in the rejection region. Thus we reject H0.
The test results are statistically significant at the 5%
level.
 Step 6 Interpret the results of the hypothesis test.
Interpretation At the 5% significance level, the data
provide sufficient evidence to conclude that a difference
exists between the mean salaries of faculty in private and
public institutions.
Nonpooled t-Test
 Purpose To perform a hypothesis test to compare two
population means, μ1 and μ2.
 Assumptions
1. Simple random samples
2. Independent samples
3. Normal populations or large samples
 Steps
 Step 1 The null hypothesis is H0: μ1 = μ2, and the
alternative hypothesis is
Ha: μ1 ≠ μ2 or Ha: μ1 < μ 2 or Ha: μ1 > μ 2
(Two tailed) (Left tailed) (Right tailed)
Step 2 Decide on the significance level, α.
Step 3 Compute the value of the test statistic
……
 Step 4 The critical value(s) are
±tα/2 or −tα or tα
(Two tailed) (Left tailed) (Right tailed)
with df = ∆,where

 rounded down to the nearest integer. Use Table to find

the critical value.
……

 Step 5 If the value of the test statistic falls in the

rejection region, reject H0; otherwise, do not reject H0.
 Step 6 Interpret the results of the hypothesis test.
 Example 2

 Several neurosurgeons wanted to determine whether a

dynamic system reduced the operative time relative to
a static system. Prof. Robert, a University professor,
and other neurosurgeons obtained the data displayed
in Table on operative times, in minutes, for the two
systems. At the 5% significance level, do the data
provide sufficient evidence to conclude that the mean
operative time is less with the dynamic system than
with the static system?
 First, we find the required summary statistics for the
two samples
 x¯1 = 394.6 s1 = 84.7 n1 = 14
 x¯2 = 468.3 s2 = 38.2 n2 = 6
 Because the two sample standard deviations are
considerably different, the pooled t-test is
inappropriate here.
 Step 1 State the null and alternative hypotheses.
 Let μ1 and μ2 denote the mean operative times for the
dynamic and static systems, respectively.
 Then the null and alternative hypotheses are,
respectively,
 H0: μ1 = μ2 (mean dynamic time is not less than mean
static time)
 Ha: μ1 < μ2 (mean dynamic time is less than mean
static time).
 Step 2 Decide on the significance level, α. The test is
to be performed at the 5% significance level, or α =
0.05.
 Step 3 Compute the value of the test statistic
……
 Step 4 The critical value for a left-tailed test is −tα with
df = ∆. Use Table to find the critical value.

 which equals 17 when rounded down. From Table with

df = 17, we find that the critical value is −tα = −t0.05 =
−1.740, as shown in Fig.
……
 Step 5 If the value of the test statistic falls in the
rejection region, reject H0; otherwise, do not reject H0.
 From Step 3, the value of the test statistic is
t = −2.681, falls in the rejection region. Thus we reject
H0. The test results are statistically significant at the
5% level.
 Step 6 Interpret the results of the hypothesis test.
Interpretation At the 5% significance level, the data
provide sufficient evidence to conclude that the mean
operative time is less with the dynamic system than
with the static system.