Scribd
Upload
26 views3 pages

Hypothesis Testing in Inferential Statistics

Inferential statistics provides tools and techniques to draw valid conclusions about populations based on samples. Statistical hypothesis testing verifies hypotheses about population characteristics or relationships between variables. The null hypothesis states no difference or relationship, while the alternative hypothesis specifies a difference or relationship. Type I and Type II errors occur when the null hypothesis is incorrectly rejected or accepted, respectively. The significance level indicates the probability of a Type I error. Hypothesis tests involve formulating hypotheses, choosing a test, determining critical values, calculating test statistics, and making conclusions about whether to reject or accept the null hypothesis.

Uploaded by

Aileah Gotladera
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
26 views3 pages

Hypothesis Testing in Inferential Statistics

Inferential statistics provides tools and techniques to draw valid conclusions about populations based on samples. Statistical hypothesis testing verifies hypotheses about population characteristics or relationships between variables. The null hypothesis states no difference or relationship, while the alternative hypothesis specifies a difference or relationship. Type I and Type II errors occur when the null hypothesis is incorrectly rejected or accepted, respectively. The significance level indicates the probability of a Type I error. Hypothesis tests involve formulating hypotheses, choosing a test, determining critical values, calculating test statistics, and making conclusions about whether to reject or accept the null hypothesis.

Uploaded by

Aileah Gotladera
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

INFERENTIAL STATISTICS

PROVIDES VARIED TOOLS AND TECHNIQUES THAT HELP THE RESEARCHER DRAW VALID
AND RELIABLE INFRENCES/CONCLUSIONS ABOUT THE POPULATION ON THE BASIS OF
THE SAMPLE

STATISTICAL HYPOTHESIS
- IT IS A STATEMENT ABOUT OUR EXPECTATION REGARDING SOME CHARACTERISTIC OF
A POPULATION OR OF THE EXPECTED RELATIONSHIP(S) BETWEEN 2 OR MORE VARIABLES
IN A SPECIFIED POPULATION

HYPOTHESIS TESTING
- STATISTICAL TOOL/PROCEDURE THAT VERIFIES THE STATISTICAL HYPOTHESIS

NULL HYPOTHESIS ( Ho )
- NO DIFFERENCE/RELATIONSHIP HYPOTHESIS
- CURRENTLY BELIEVE TO BE TRUE/CURRENTLY ACCEPTED

ALTERNATE HYPOTHESIS ( Ha )
- NEGATES THE NULL HYPOTHESIS
- SPECIFIES AN EXISTENCE OF A DIFFERENCE/RELATIONSHIP
- CLAIM TO BE ACCEPTED IN CASE Ho IS REJECTED

EXAMPLES
1. A COMPARATIVE STUDY ON THE CONSUMER’S ACCEPTANCE OF X AND Y SHAMPOO
Ho: THE CONSUMER’S ACCEPTANCE OF X AND Y ARE THE SAME
Ha: THE CONSUMER’S ACCEPTANCE OF X AND Y ARE NOT THE SAME

2. USTET SCORES AND ACADEMIC ACHIEVEMENT OF STUDENTS IN PRIVATE AND PUBLIC


SCHOOLS
Ho: THERE IS NO RELATIONSHIP BETWEEN USTET SCORES AND THE ACADEMIC
ACHIEVEMENT AMONG THE THREE LEARNING AREAS OF PRIVATE AND PUBLIC
SCHOOLS
Ha: THERE IS A RELATIONSHIP BETWEEN USTET SCORES AND THE ACADEMIC
ACHIEVEMENT AMONG THE THREE LEARNING AREAS OF PRIVATE AND PUBLIC
SCHOOLS

3. A MANUFACTURER OF IT GADGETS RECENTLY ANNOUNCED THEY HAD DEVELOPED


A NEW BATTERY FOR A CELLPHONE AND CLAIMED THAT IT HAS AN AVERAGE LIFE
OF AT LEAST 48HRS. WOULD YOU BUY THIS BATTERY?
Ho: AVERAGE LIFE OF THE BATTERY IS AT LEAST 48HRS
Ha: AVERAGE LIFE OF THE BATTERY IS LESS THAN 48HRS

TYPES OF ERRORS : IN ACCEPTING/REJECTING Ho, ANYONE OF THE FOLLOWING


ERRORS CAN BE COMMITTED

Ho TRUE FALSE

REJECTED TYPE 1 ERROR NO ERROR

ACCEPTED NO ERROR TYPE 2 ERROR

TYPE I ERROR (Α) REJECTING A TRUE HYPOTHESIS: ANALOGY IN THE COURT


(CONVICTING AN INNOCENT PERSON)

TYPE II ERROR (Β) ACCEPTING A FALSE HYPOTHESIS: ANALOGY IN THE COURT (FREEING
A GUILTY PERSON)

LEVEL OF SIGNIFICANCE
- THE PERCENTAGE/PROBABILITY OF COMMITTING A TYPE1 ERROR
- DENOTED BY α.
e.g. 10% , 5% , 1%

NOTE: 5% LEVEL OF SIGNIFICANCE IMPLIES THAT WE ARE 95% CONFIDENT (LEVEL OF


CONFIDENCE) THAT WE HAVE MADE THE RIGHT DECISION (α = 0.05)

CRITICAL VALUE OF A STATISTICAL TEST


- VALUE THAT DIVIDES THE DISTRIBUTION INTO A REJECTION REGION (RR) AND
ACCEPTANCE REGION (AR)

ACCEPTANCE AND REJECTION REGIONS (α represents the area of the shaded region )

 TWO-TAILED TEST
SUITABLE WHEN: 𝐻0 : 𝜇1 = 𝜇2

𝐻𝐴 : 𝜇1 ≠ 𝜇2
 LEFT-TAILED TEST
SUITABLE WHEN: 𝐻0 : 𝜇1 = 𝜇2

𝐻𝐴 : 𝜇1 < 𝜇2

 RIGHT-TAILED TEST
SUITABLE WHEN: 𝐻0 : 𝜇1 = 𝜇2

𝐻𝐴 : 𝜇1 > 𝜇2

STEPS IN HYPOTHESIS TESTING


1. FORMULATE A NULL HYPOTHESIS (H0) & THE ALTERNATE HYPOTHESIS (HA)
2. SET THE LEVEL OF SIGNIFICANCE
3. CHOOSE AN APPROPRIATE TEST STATISTIC AND IDENTIFY WHICH TYPE OF TEST (1-
TAILED OR 2-TAILED) TO USE
4. DETERMINE THE CRITICAL VALUE FOR THE TEST FROM THE TABLE (FOUND IN
APPENDIX OF STATISTICAL BOOKS)
5. COMPUTE FOR THE VALUE OF THE TEST STATISTIC
6. COMPARE THE VALUES OBTAINED IN (4) AND (5). DECIDE WHETHER TO ACCEPT OR
REJECT NULL HYPOTHESIS
7. CONCLUSION (IT IS THE PART WHERE THE RESEARCHER EXPLAINS HIS/HER DECISION )

You might also like