HUBERT KAIRUKI MEMORIAL
UNIVERSITY
DEPARMENT OFEPIDERMIOLOGY
AND BIOSTATICS
TOPIC: HYPOTHESIS TESTING.
PRESENTER:DR. LAMRAT N./
ANNUNCIATA FRANCIS
SUPERVISOR: PROF. INNOCENT
SEMALI
OUTLINES:
Introduction
Types of hypothesis testing
Concepts of Hypothesis Testing
practicals
INTRODUCTION:
A statistical hypothesis test is a
method of statistical inference used
to decide whether the data at hand
sufficient support to a particular
hypothesis.
Hypothesis testing allow us to make
probabilistic statements about
population.
Example
Observe 30% of men drink alcohol as
compared to 20% of women. Interpret,
what may be the best explanation?
Possible explanations
10% difference TRUE DIFFERENCE
DUE TO CHANCE (sampling variation)
BIAS (used men to interview, sensitive
to women, need a better approach)
In statistics
Population
Sample
Inference
Statistic
Parameter
Hypothesis testing allows us to determine
whether enough statistical evidence exists to
conclude that a belief (i.e. hypothesis) about a
parameter is supported by the data.
Concepts of Hypothesis Testing
There are two hypotheses.
One is called the null hypothesis and
the other the alternative or research hypothesis. T
usual notation is:
pronounced
H “nought”
H0: — the ‘null’ hypothesis
H1: — the ‘alternative’ hypothesis
Hypothesis Testing
A hypothesis is a statement of belief
about a population parameter.
e.g., the average weight of-the-shelf
Aspirin is 72 mg
H : μ = 72 mg.
0
H : μ ≠ 72 mg.
a
Concepts of Hypothesis Testing…
whether the mean is different from 72
units. We can rephrase this request into a
test of the hypothesis:
H0: = 72 mg
Thus, our research hypothesis becomes:
H1: ≠ 72 mg This is what we are
interested in determining…
Concepts of Hypothesis Testing (2)…
The testing procedure begins with the
assumption that the null hypothesis is
true.
Thus, until we have further statistical
evidence, we will assume:
H0: = 72 mg (assumed to be TRUE)
Concepts of Hypothesis Testing (3)
…
The goal of the process is to determine
whether there is enough evidence to
infer that the alternative hypothesis is
true.
H1: ≠ 72 mg, is true?
This is what we are
interested in
determining…
Concepts of Hypothesis Testing (4)…
Conclude that there is enough
evidence to support the alternative
hypothesis
Conclude that there is not enough
evidence to support the alternative
hypothesis
NOTE: we do not say that we accept the
null hypothesis…
Concepts of Hypothesis Testing…
Then randomly sample the population and
calculate a test statistic
If the test statistic’s value is inconsistent
with the null hypothesis we reject the null
hypothesis and
infer that the alternative hypothesis is
true.
Non statistical Hypothesis Testing…
In a trial a jury must decide between two
hypotheses. The null hypothesis is
H0: The defendant is innocent
The alternative hypothesis or research
hypothesis is
H1: The defendant is guilty
Non statistical Hypothesis Testing…
In the language of statistics convicting
the defendant is called rejecting the null
hypothesis in favor of the alternative
hypothesis.
If the jury acquits it is stating that there
is not enough evidence to support the
alternative hypothesis.
Hypothesis Testing and The Justice System
The null hypothesis: The hypothesis of no
difference. The straw man.
“Assume for now that the drugs are the same”
Innocent Until Proven Guilty
A standard of judgement: Needed because
you can’t absolutely prove the null hypothesis.
p=0.05 (the arbitrary alpha level)
Proof beyond a reasonable doubt
Hypothesis Testing and The Justice System
The alternative hypothesis: In stats, this is
the research hypothesis investigators wish to
evaluate. In a trial, this is the reason a criminal
is arrested.
“I bet drug A is different from drug B.”
“I bet AZ is guilty”
p-values
Appropriate p-values assess statistical
significance through hypothesis testing
p-value is the exact probability of observing
a test statistic of a given value if the null
hypothesis were true
p = 0.05
The arbitrary value of 0.05 is often chosen as
the yardstick to declare statistical significance.
This is called the study’s alpha level (α)
If p < 0.05, reject null hypothesis, declare statistical
significance
If p > 0.05, fail to reject null hypothesis. Not
enough evidence to reject the null
Relationship between the p-value and
the confidence interval
p-value is the probability of observing a
test statistic of a given magnitude if the
null hypothesis were true
If a 95% confidence interval does not
include the null value, then the p-value for
the test will be <0.05. Reject null
hypothesis.
If the 95% confidence interval includes the
null value, then p will be >0.05; fail to
reject the null. No evidence to reject.
Hypothesis Testing…errors
There are two possible errors.
A Type I error occurs when we reject a
true null hypothesis. That is, a Type I
error occurs when the jury convicts an
innocent person.
A Type II error occurs when we don’t
reject a false null hypothesis. That occurs
when a guilty defendant is acquitted.
Non statistical Hypothesis Testing…
The probability of a Type I error is
denoted as α (Greek letter alpha). The
probability of a type II error is β
(Greek letter beta).
The two probabilities are inversely
related. Decreasing one increases the
other.
Truth (usually
Theunknown)
null The null
hypothesi hypothesis
s is true is false
We decide to Correct
reject the null Type I error,
decision
hypothesis α
We fail to reject Correct Type II error,
the null decision
hypothesis β
Types of Errors…
Back to our example, we would commit a
Type I error if:
Reject H0 when it is TRUE
We would commit a Type II error in the
case where:
Do NOT reject H0 when it is FALSE
Exercise 1
An average age of MD1 class is 16 years .
State the null and alternative hypotheses.
H0:p=16 years
H1:p≠16 years
Exercise 2
A researcher wants to determine if there is
an association between physical activity and
body weight. State the null and alternative
hypotheses.
H0:There is no association between
physical activity and body weight
H1:There is an association between
physical activity and body weight
Exercise 3
Miriam is interested in testing the
claim that banana is the favorite fruit
for more than 80% of the adults at
HKMU. She conducted a survey on a
random sample of 225 adults.
Identify the null hypothesis and the
alternative hypothesis.
Exercise 4
A double-blind, randomized, placebo-controlled trial of
intravenous remdesivir in adults hospitalized with Covid-
19 with evidence of lower respiratory tract involvement.
Patients were randomly assigned to receive either
remdesivir (200 mg loading dose on day 1, followed by
100 mg daily for up to 9 additional days) or placebo for
up to 10 days. The primary outcome was the time to
recovery, defined by either discharge from the hospital
or hospitalization for infection-control purposes only.
State the null and alternative hypothesis
Summary
Two hypotheses: H0 & H1
ASSUME H0 is TRUE
GOAL: determine if there is enough evidence to
infer that H1 is TRUE
Two possible decisions:
Reject H in favor of H
0 1
NOT Reject H0 in favor of H1
Two possible types of errors:
Type I: reject a true H0 [P(Type I)=]
Type II: not reject a false H0 [P(Type II)=]
