Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 2

Hypothesis testing

One-tailed test, Two-tailed test, Statistical hypothesis, Hypothesis, A guess or


conjecture

Statistical Hypothesis
Is an assertion, statement, or conjecture concerning one or more unknown parameters or
distributional properties of the population.

Steps in formulating hypothesis testing


This consist of five important steps
 Formulate the null and alternative hypothesis
 Collect the data and decide on an appropriate statistical testing procedure. Specify
the level of significance α
 Compute the test-statistic or probability value (p-value)
 Determine the critical region, also called the rejection region.
 Make a decision and a conclusion about the hypothesis

Two types of statistical hypothesis


Null Hypothesis
Denoted as H0
Is a statement of no difference and contains the equality statement that you want to test
Alternative Hypothesis
Denoted as H1 or Ha
Is the operational statement of the research and contains the non-equality statement
It is an assertion believed to be true whenever the null hypothesis is rejected
Null and Alternative hypothesis
The rejection of the null hypothesis H0 leads the acceptance of the alternative
hypothesis Ha
which may be Directional or Non-Directional
Directional alternative hypothesis
Is an assertion that one measure is less than or greater than another measure
It specifies which measure is greater or lesser

This involves the quantifiers < or >


Non directional alternative hypothesis
Is a statement which asserts that one value is differ from another

This involves the quantifier ≠


Conducting a statistical test
A researcher who collects and uses sample data to infer whether there is sufficient
evidence favoring the alternative hypothesis Ha rather than the null hypothesis H0
arrives at one of these two conclusions:
 Reject H0 in favor of Ha because of sufficient evidence in the data
 Fail to reject H0 (do not reject H0) because of insufficient evidence in the data.
Statistical test
A Statistical test of hypothesis is a method or tool used to decide whether or not to
reject a statistical hypothesis.
These statistical test are classified into one-tailed or two-tailed test.
One tailed test and Two tailed test
One-tailed test
 is used when an alternative hypothesis is directional
 Two-tailed test
 Is used when an alternative hypothesis is non directional
 Remember:
Directional hypothesis < or >
Non-directional hypothesis ≠

Four possibilities
You have made the right decision when a true null hypothesis is not rejected or when
false null hypothesis is rejected.
You commit errors when true null hypothesis is rejected (type I error) and when a false
null hypothesis is not rejected (type II error).
Type I error
 Is an error of rejecting a null hypothesis when in fact it is true
 Type II error
 Is an error of accepting a null hypothesis when in fact it is false
Type I error
α = P[Type I error]
Known as the level of significance.
This is the probability of rejecting a true null hypothesis.
A confidence level 1 – α is the probability of making the correct decision of not rejecting
a true null hypothesis.
Type II error
β=P[Type II error]

Measures the risk of accepting a false null hypothesis.


regions
Critical Region or Rejection Region
 Consists of values that support the alternative hypothesis Ha and leads to the
rejection of null hypothesis Ha.
it has an area given by the level of significance α
Non-critical Region
 Consists of values that support the null hypothesis H0 and leads to its non-
rejection.
 it has an area given by the confidence level 1 – α
One tailed test critical region
Two tailed test critical region

Formulate the hypothesis


H0: The students that are above average intelligence are equal to 100
Ha: The students that are above average intelligence are greater than 100

You might also like