STATISTICS

&
PROBABILIT
The Hypothesis Testing

Y Procedure
 Agustinian Prayers
Opening Prayer
Leader: When we live in unity;
Response: How good and how pleasant it is.
Leader: Pray for us Holy Father Augustine;
Response: That we may dwelt together in peace.
Leader: Let us pray.
Response: God, our Father, your son promised to be present in the midst of all who come
together in his name. Help us to recognize his presence among us and experience in our hearts,
the abundance of your grace, your mercy and your peace, in truth and in love. We ask this
through Christ our Lord. Amen.
Leader: Our Lady of Grace
Response: Pray for us
 Statistical Hypothesis
Statistical hypothesis
A statistical hypothesis is either a statement about the value of a population parameter or a
statement about the probability distribution that a certain random variable follows.

Hypothesis

A hypothesis is a proposed explanation, assertion, or assumption about a population parameter

or the distribution of a random variable. It is a supposition advanced as a basis for an
argument. It is tested using statistical methods, generally using experimental samples.
Testing a Statistical Hypothesis
State the null and alternative Formulate the decision rule
hypotheses.
1 4

Compute the value of the test

Select a level of significance statistic
2 5

Select the test statistic Make a decision

3 6
 State the null and alternative hypotheses.
1
Null Hypothesis
 a statement about the value of a population parameter formulated with the hope of
being rejected.
 Assumes that there is no difference between the two means or variables being
compared.
 Denoted by .

Null hypothesis always involves equality symbols. Thus we will use the .

Example:
H0: There is no relationship between height and shoe size.
 State the null and alternative hypotheses.
1
Alternative hypothesis
 A statement that assumes that there is a significant difference between the two means
or variables under test or observation.
 Denoted by .

The alternative contains the inequality symbols or .

Example:
Ha: There is a relationship between height and shoe
size.
 State the null and alternative hypotheses.
1
Example 1:

A common problem in many public schools is the large class size. Suppose that the
average number of students in a class in a certain city was 65. We wish to know whether the
classrooms built over the years have succeeded in reducing this class size.
Example 1:

A common problem in many public schools is the large class size. Suppose that the
average number of students in a class in a certain city was 65. We wish to know whether the
classrooms built over the years have succeeded in reducing this class size.

• Since we wish to test whether the mean class size has been reduced to less than 65,
the alternative hypothesis must contain the symbol <.
• That is;
or The average class size is 65.
or The average class size is less than 65.
 State the null and alternative hypotheses.
1
Example 2:

A Pulse Asia Survey conducted from 2-8 July 2016

reported that 44% of Filipinos believe that the Constitution
should not be amended at the moment. An anti-charter change
group may claim the percentage is too low, and verify this
claim by conducting a survey of their own.
Example 2:

A Pulse Asia Survey conducted from 2-8 July 2016 reported that 44% of Filipinos believe
that the Constitution should not be amended at the moment. An anti-charter change group may
claim the percentage is too low, and verify this claim by conducting a survey of their own.

• Th group wishes to test the hypothesis that the proportion of Filipinos opposed to
charter change is higher than 0.44. The parameter we are testing is the population
proportion p, and the null and alternative hypothesis are the following;
or The population proportion of Filipinos who opposes to charter change is 0.44.
or The population proportion of Filipinos who opposes to charter change is
greater than 0.44.
 State the null and alternative hypotheses.
1
Example 3:

Suppose that the turnover rate of a 200-tablet bottle of

multivitamins follows the normal distribution with a mean of
6.0 and a standard deviation of 0.50. We would like to know if
the mean turnover has changed and is no longer 6.0.
Example 3:
Suppose that the turnover rate of a 200-tablet bottle of multivitamins follows the normal
distribution with a mean of 6.0 and a standard deviation of 0.50. We would like to know if the
mean turnover has changed and is no longer 6.0.

• We wish to test a statement on the population mean . The following are the null and
the alternative hypothesis;
or The average turnover rate of a 200-tablet bottle of multivitamins is 6.0.
or The average turnover rate of a 200-tablet bottle of multivitamins is not 6.0.
 Select a level of significance
2
• To test a hypothesis, we take a sample from a population and use the information
obtained in the sample to decide whether the hypothesis is likely to be true or false.
If the evidence from the sample is inconsistent with the hypothesis, we reject it.
Otherwise, we accept it.
• If the sample data have results which are quite far from our null hypothesis, then
we can be quite confident that we are not making a mistake by rejecting the . This
level of confidence is captured by the level of significance of a hypothesis test.
 Select a level of significance
2
Null Hypothesis

The level of significance () of a test is the probability of rejecting the null hypothesis
when it is true.
• The smaller the value of , the surer we are that we are not making an error if we end up rejecting .
Thus, a smaller leads to a higher amount of "evidence" needed before we reject in favor of .
• There is no fixed value of to use in any hypothesis test. While = 0.05 tends to be chosen as a default
value, the choice may differ depending on the application.

Consumer Research Project

Quality Assurance
Political Polling
 Select the test statistic
3
Test statistic
any function of the observed data whose numerical value dictates whether the
null hypothesis is accepted or rejected.

Formulate the decision rule

4
Decision rule

indicates the condition(s) where the null hypothesis is rejected. It depends on

whether the alternative hypothesis is one-sided (one-tailed test with an inequality
symbol > or < ) or two-sided (two-tailed test with an inequality symbol ).
• In a one-tailed test, the set of values which lead to the rejection of the null hypothesis, also called the rejection
region, is in either the upper or the lower tail of the sampling distribution of the statistic.
 The following are the conditions to follow to reject
the .
Left-tailed

occurs when the alternative hypothesis contains the

symbol <. In this case, we reject the null hypothesis if the
value of the test statistic based on the sample is too small as
compared to the value given in the null hypothesis.
 The following are the conditions to follow to reject
the .
Right-tailed

case occurs when the alternative hypothesis contains

the symbol >. In this case, we reject the null hypothesis if the
value of the test is statistic using sample information is too
large as compared to the value specified in the null
hypothesis.
• In a two-tailed test, the rejection region is divided into two parts and is found in both the upper and lower tails.
Two-tailed test
the rejection region is divided into two parts and is found on both upper and lower tails. Two-tailed
case occurs when the alternative hypothesis is contains the inequality symbol . In this case, we reject
the null hypothesis if the values are either too big or too small as compared to the hypothesized
value.

Critical Region
The set of values of the test statistic that results in the rejection of the null hypothesis is
called the critical region or the region of rejection. The particular point in the critical
region that separates the rejection region from the acceptance region is called the critical
value.
 Compute the value of the test statistic
5
Using the given information in the sample, one must then substitute these numbers to
the test statistic and compute its value.

Make a decision
6 If the value of the test statistic falls with in the critical region, we reject in favor of the
alternative hypothesis. Otherwise, we do not reject .
• In some cases, sometimes say that there is insufficient evidence to reject
• In the second case, note that we do not say that we are "accepting" . This is because by not rejecting , we
are not saying that is true; it only means that there is insufficient evidence to say that it is false.
• In contrast, when we reject , we are saying that, based on the sample data, there is only a small probability
(specifically, a) of mistakenly rejecting it.
Exercises:

1. The data below shows the mean scores in the post-test of two sample groups
of students taught using two different methods of teaching Mathematics.

Method A
Method B
a. Formulate a null hypothesis about the population mean.
b. Formulate an alternative hypothesis for a two-tailed test and a one-
tailed test.
Exercises:

1. A store manager of air conditioners tells the higher management that around
90% of its costumers are “fully satisfied” with their overall purchase
performance. The CEO would like to verify this claim is true.
a. Formulate a null hypothesis about the population mean.
b. Formulate an alternative hypothesis for a two-tailed test and a one-
tailed test.
c. Identify the parameter being tested.
 Agustinian Prayers
Closing Prayer
Leader: Our help is in the name of the Lord;
Response: Who made heaven and earth.
Response: Let us pray;
Response: God, the desire of every human heart, you moved St. Augustine to seek
restlessly for truth and peace. Touch our hearts with his burning desire for wisdom, for the
word made flesh. We ask this through Christ our Lord.
All: Amen
Leader: Our Lady of Grace
Response: Pray for us