Deliverable 05 – Worksheet

Instructions: The following worksheet describes two examples – one is an example for
independent samples and the other one for dependent samples. Your job is to demonstrate the
solution to each scenario by showing how to work through each example in detail. You are
expected to explain all of the steps in your own words.

Independent samples:
One of our researchers wishes to determine whether people with high blood pressure can reduce
their systolic blood pressure by taking a new drug we have developed. The sample data is shown
below, where x́ 1 represents the mean blood pressure of the treatment group and x́ 2 represents the
mean for the control group. Use a significance level of 0.01 and the critical value method to test
the claim that the drug reduces the blood pressure. We do not know the values of the population
standard deviations.

TREATMEN
CONTROL GROUP
T GROUP
n1 78 n2 70
x́ 1 186.7 x́ 2 201.9
s1 38.5 s2 39.8

1. Write the hypotheses in symbolic form, determine if the test is right-tailed, left-
tailed, or two tailed and explain why.

Answer and Explanation

Hypotheses

H0: x́ 1 = x́ 2

H1: x́ 1 < x́ 2

α = 0.01

As can be seen, the alternate hypothesis has a ‘less than sign’, which was decided on
because it is claimed that the new drug reduces patients’ systolic blood pressure.
Therefore, this is a left-tailed test by virtue of the ‘less than’ sign in the alternate
hypothesis stated above. In other words, it is expected that the rejection region will
fall to the extreme left of the distribution.
 2. Calculate the critical value and the test statistic.

Answer and Explanation

Critical Value

Given α = 0.01, the area in the middle is 0.99 (1 – 0.01). Looking up this value from
the z-tables, it is determined that the area is (zc = -2.33) because it is a left-tailed test.

Test Statistic

( x́ 1− x́ 2)
z=
s / √n
(186.7−201.9)
z=
38.5/ √78
z = -3.49

3. Make a decision about the null hypothesis and explain your reasoning, then make a
conclusion about the claim in nontechnical terms.

Answer and Explanation

 Decision rule: reject the null (H0) if the test statistic (z = -3.49) is less than the critical
value (zc-2.33) because this is a left-tailed test. Therefore, we reject H0 because -3.49
< -2.33. There is a statistically significant (α=0.01) difference between the mean
blood pressure of the two groups. As such, it can be concluded that the new drug
reduces systolic blood pressure.

Dependent samples
This same new drug was tested on another group, but this time the test was done before the drug
was administered, and then tested after the drug was given to the same group. The results are
shown in the table below:

Subject Before After

1 199 189

2 174 170

3 195 177

4 171 167

5 179 159

6 182 151

7 193 176

8 208 183

9 185 159

10 155 145

11 169 146

12 208 177
Use the data above with a significance level of 0.05 to test the claim that for the populations of
blood pressures before and after the drug, the differences have a mean greater than 0 mm Hg (so
the claim is that the drug helps lower the blood pressure). Use the P-Value method to determine
whether or not to reject the null hypothesis and state your conclusion.

4. Write the hypotheses in symbolic form, determine if the test is right-tailed, left-tailed,
or two tailed and explain why.

Answer and Explanation

Hypotheses

H0: μB - μA ≤ 0

H1: μB - μA > 0

α = 0.05

The above hypotheses explain a right-tailed test by virtue of the ‘greater than sign’ in
the alternate hypothesis stated above. This is because the claim is that the mean
difference between the populations blood pressure before and after the treatment is
greater than 0 mm Hg.

5. Calculate the test statistic and the P-Value.

Answer and Explanation

Test statistic

Since the samples are dependent, then a two-sample t test was the appropriate
method of determining the test statistic and the p-value, t (11) = 2.88, p = 0.004.

Therefore, the test statistic is (t = 2.88) and the p-value is (p = 0.004).

6. Make a decision about the null hypothesis and explain your reasoning, then make a
conclusion about the claim in nontechnical terms.

Answer and Explanation

Decision rule: reject the null (H0) if the p-value is less than the assumed level of
significance (α = 0.05). This is because if the p-value is less than the assumed level
of significance, α, the null hypothesis is unlikely. Since, the p-value (p = 0.004) is less
than the assumed level of significance (α = 0.05), we reject the null hypothesis. There
is significant statistical evidence that the mean difference between the population
blood pressure before and after the treatment is greater than 0 mm Hg.