Biostatistics & Research Methodology
2021/22
Block 4 – Lecture 2
Hypothesis
Testing
Aktham Osama Abdulazeez, MBChB
Hypothesis: the Purpose
The purpose of hypothesis testing is to help the
researcher or study administrator in reaching a
decision concerning a population by examining a
sample from that population.
The Hypothesis
o It is a statement about one or more population.
o It is usually concerned with the parameter of the population
about which the statement is made.
The Research Hypothesis
o It is the assumption that motivates the research.
o It is usually the result of long observation by the researcher.
o This hypothesis leads directly to the second type of
hypothesis.
The Statistical Hypothesis
The Statistical Hypotheses
o A research hypothesis stated in a way that can be evaluated
by appropriate statistical technique.
o It is of 2 types:
o Null hypothesis( Ho): It is the particular hypothesis under test, and it is
the hypothesis of “no difference”.
o Alternative hypothesis (HA): which disagrees with the null hypothesis
and must be accepted if the null hypothesis is refuted.
Types of Statistical Errors
Types of Statistical Errors: Type 1
o Type 1 error: rejection of the null hypothesis when it is true.
o It is presented by alpha, which is the level of significance,
often the 5%, 1%, and 0.1% (α=0.05, 0.01, and 0.001) levels
are chosen.
o The selection depends on the particular problem being
studied.
o The higher the alpha level, the more lenient we are with the
role of chance in our findings.
Hypothesis Testing
Probability Value (P-value)
o It is the smallest value of the level of significance for which
the Ho can be rejected.
o It gives a more precise statement about probability of
rejection of Ho when it is true than the alpha level.
o Instead of saying the test statistic is significant or not, we will
mention the exact probability of rejecting the Ho when it is
true.
o Example: p = 0.04 -> there is a 4% chance the difference or
change between the population parameter and sample
statistic happened by chance.
Steps of Hypothesis Testing
1. Determine the nature of data
The nature of the data whether it consists of counts, or
measurement will determine the test statistic to be used.
Steps of Hypothesis Testing
2. Write Statistical Hypotheses
• Null Hypothesis (Ho): which is the hypothesis of no
difference.
• Alternative hypothesis (HA): which is the hypothesis accepted
if Ho is rejected.
• If we accept the Ho we will say that the data to be tested
does not provide sufficient evidence to cause rejection.
• If it is rejected we say that the data are not compatible with
Ho and support the alternative hypothesis (HA).
Steps of Hypothesis Testing
3. Calculate the Test Statistic
• It uses the data of the sample to reach a decision to reject or
to accept the null hypothesis.
• The general formula for a test statistic is:
Steps of Hypothesis Testing
3. Calculate the Test Statistic - Examples
Steps of Hypothesis Testing
4. Determine the test statistic distribution
• It is the key for statistical inference.
• Can be a normal distribution curve or otherwise (e.g. chi-
square distribution).
Steps of Hypothesis Testing
5. Determine the Rejection Rule
• It will tell us to reject the null hypothesis if the test statistic
falls in the rejection area, and to accept it if it falls in the
acceptance region.
• The critical values that discriminate between acceptance and
rejection regions depends on alpha level of significance.
• If the value of the test statistic falls in the rejection region
area, it is considered statistically significant.
• If it falls in the acceptance area it is considered not
statistically significant.
Steps of Hypothesis Testing
5. Determine the Rejection Rule
• Critical values: The values of the test statistic that separate
the rejection region from the acceptance region.
• Acceptance region: A set of values of the test statistic leading
to acceptance of the null hypothesis (values of the test
statistic not included in the critical region).
• Rejection region: A set of values of the test statistic leading to
rejection of the null hypothesis.
Steps of Hypothesis Testing
6. Compare Test Statistic to Rejection Rule
• The test statistic should be computed and compared with the
acceptance and rejection regions.
7. Make a Statistical Decision
• It consists of rejecting or not rejecting the Ho.
• It is rejected if the computed value of the test statistic falls in
the rejection area.
• It is not rejected if the computed value of the test statistic falls
in the acceptance region.
Steps of Hypothesis Testing
8. Draw Conclusions
• If Ho is rejected , we conclude that HA is true.
• If Ho is not rejected we conclude that Ho may be true.
One- and Two-Tailed Testing
One- and Two-Tailed Testing
Example question #1: A government official claims that the
dropout rate for local schools is 25%. Last year, 190 out of 603
students dropped out. Is there enough evidence to reject the
government official’s claim?
Example question #2: A government official claims that the
dropout rate for local schools is less than 25%. Last year, 190 out
of 603 students dropped out. Is there enough evidence to reject
the government official’s claim?
Example question #3: A government official claims that the
dropout rate for local schools is greater than 25%. Last year, 190
out of 603 students dropped out. Is there enough evidence to
reject the government official’s claim?
One- and Two-Tailed Testing
The decision to use one- or two-tailed test will
depend on the nature of the research question
being asked by the researcher.
One- and Two-Tailed Testing
• A one-tailed test has the
entire alpha level in one
tail (in either the left, or
the right tail).
• A two-tailed test splits the
alpha level in half.
Steps of Hypothesis Testing - Summary
1. Determine the nature of data (continuous, discrete)
2. Write up statistical hypotheses.
3. Calculate the test statistic (Z values, T values, x2, F value).
4. Determine & plot the test statistic distribution.
5. Determine the rejection rule (level of confidence).
6. Compare test statistic to rejection rule.
7. Reach a statistical decision.
8. Draw conclusions.
Exercise
A certain breed of rats shows a mean weight gain of 65 gm,
during the first 3 months of life. 16 of these rats were fed a new
diet from birth until age of 3 months. The mean was 60.75 gm.
If the population variance is 10 gm , is there a reason to believe
at the 5% level of significance that the new diet causes a change
in the average amount of weight gained?
Exercise
Exercise
In a study two types of dental cements were used to hold a
crown on tooth cast. The amount of force in foot pounds
required to pull each cemented crown from the cast was
reported:
Test the hypothesis that μ1= μ2 at α=0.05.
Exercise
Exercise
In a dental clinic, it is hypothesized that 90% of all 4-years old
children give no evidence of dental caries. In a study of 100
children 82 gave no such evidence, would you accept the
quoted value of the 90% ? Use α=0.05
Exercise
Review
Time
Previous Years
Question 1
The point where the null hypothesis gets rejected is called:
A. Acceptance value
B. Significant value
C. Rejection value
D. Critical value
Previous Years
Question 1
The point where the null hypothesis gets rejected is called:
A. Acceptance value
B. Significant value
C. Rejection value
D. Critical value
Previous Years
Question 2
Type 1 statistical error is a direct result of:
A. Rejecting the H0 when it is False
B. Rejecting the H0 when it is True
C. Accepting the H0 when it is False
D. Accepting the h0 when it is True
Previous Years
Question 2
Type 1 statistical error is a direct result of:
A. Rejecting the H0 when it is False
B. Rejecting the H0 when it is True
C. Accepting the H0 when it is False
D. Accepting the h0 when it is True
Previous Years
Question 3
When the critical region is evenly distributed, we refer to the
statistical test as:
A. Zero tailed
B. One tailed
C. Two tailed
D. Three tailed
Previous Years
Question 3
When the critical region is evenly distributed, we refer to the
statistical test as:
A. Zero tailed
B. One tailed
C. Two tailed
D. Three tailed
Previous Years
Question 4
The alternative hypothesis is synonymous with:
A. Null hypothesis
B. Simple hypothesis
C. Hypothesis of no difference
D. Research hypothesis
Previous Years
Question 4
The alternative hypothesis is synonymous with:
A. Null hypothesis
B. Simple hypothesis
C. Hypothesis of no difference
D. Research hypothesis
Previous Years
Question 5
When writing the statistical hypotheses, which of the following
is FALSE?
A. The null hypothesis refers to the absence of difference or
association
B. The alternative hypothesis usually challenges or
contradicts the research hypothesis
C. They are always 2 in number and contradict each other
D. The research hypothesis refers to the presence of an
association or difference in the parameters under study
Previous Years
Question 5
When writing the statistical hypotheses, which of the following
is FALSE?
A. The null hypothesis refers to the absence of difference or
association
B. The alternative hypothesis usually challenges or
contradicts the research hypothesis
C. They are always 2 in number and contradict each other
D. The research hypothesis refers to the presence of an
association or difference in the parameters under study
Previous Years
Question 6
Which is true regarding the null hypothesis?
A. It’s the assumption that motivates the research
B. Is usually the result of long observation by the researcher
C. It’s usually stated in a negative (or indirect) type of
language
D. It directly correlates with the research hypothesis
Previous Years
Question 6
Which is true regarding the null hypothesis?
A. It’s the assumption that motivates the research
B. Is usually the result of long observation by the researcher
C. It’s usually stated in a negative (or indirect) type of
language
D. It directly correlates with the research hypothesis
Previous Years
Question 7
In a certain statistical test where the alpha level of significance
was set at 0.05, the p-value was equal to 0.1
How would you interpret the results of this test?
A. Reject the null hypothesis
B. Accept the null hypothesis
C. The p-value will not affect our decision whether to accept
or reject the null hypothesis
D. There is enough evidence to support the research
hypothesis that the population proportion is different
from a hypothesized parameter
Previous Years
Question 7
In a certain statistical test where the alpha level of significance
was set at 0.05, the p-value was equal to 0.1
How would you interpret the results of this test?
A. Reject the null hypothesis
B. Accept the null hypothesis
C. The p-value will not affect our decision whether to accept
or reject the null hypothesis
D. There is enough evidence to support the research
hypothesis that the population proportion is different
from a hypothesized parameter
Previous Years
Question 8
Which of the following p-values indicates the highest level of
STATISTICAL significance:
A. P-value < 0.001
B. P-value < 0.05
C. P-value < 0.1
D. P-value is irrelevant to statistical significance
Previous Years
Question 8
Which of the following p-values indicates the highest level of
STATISTICAL significance:
A. P-value < 0.001
B. P-value < 0.05
C. P-value < 0.1
D. P-value is irrelevant to statistical significance
Summary : Hypothesis Testing
1. Understand the data type, use it to determine the test statistic:
• Continuous data: Z test, t test
• Proportions: Z test
• Counts: Chi square test
2. Write up the statistical hypotheses:
o Questions with a single statistic (single mean, single proportion):
o The null hypothesis equals the provided population parameter
o Questions with 2 statistics (difference between means, difference between statistics)
o The null hypothesis (no difference) is that the difference between the 2 parameters equals zero
o The alternative hypothesis is always the opposite of null hypothesis
3. Determine & calculate the test statistic (Z, t, x2, F, etc..)
4. Draw a distribution curve
5. Plot the critical values on the distribution curve
• For Z test, you have fixed numbers for known levels of significance
• For t test, use the alpha level and the degrees of freedom to calculate the t value
6. Compare the test statistic with the critical values
• If it falls in the acceptance zone, accept the null hypothesis
• If it falls in the rejection zone (tails), reject the null and accept the alternative hypothesis
Thank You
Questions? Ask in the group or note it down for our next
live session!
Hope to see you next time ☺
