Chapter 10-Testing of Hypotheses I

Hypothesis:
A hypothesis is a testable proposition or assumption made to explain a phenomenon, which
can be proved or disproved through scientific investigation. (preposition= judgment or opinion)
Characteristics of a hypothesis:
Hypothesis must possess the following characteristics:

1. Clear and Precise: A hypothesis must be clear and precise.

2. Testable: It should be testable through observation and deduction.
3. Relational: If relational, it should state the relationship between variables.
4. Specific and Limited: Hypotheses should be limited in scope and must be specific
5. Simple: It should be easily understandable, though simplicity doesn’t imply less
significance.
6. Consistent: It must align with established facts.
7. Time-bound: It should be testable within a reasonable timeframe.
8. Explanatory: It should explain the facts leading to its formulation and be empirically
grounded.

Definitions of Basic Concepts in Hypothesis Testing

Basic Concepts in Testing of Hypotheses

In hypothesis testing, we aim to make inferences or draw conclusions about a population based
on sample data. The process involves testing an assumption or claim about a population
parameter, such as the population mean, proportion, or variance.

(a) Null Hypothesis (H₀) and Alternative Hypothesis (Hₐ)

1. Null Hypothesis (H₀): The null hypothesis is the default assumption or claim that there is
no significant effect or difference.

2. Alternative Hypothesis (Hₐ): The alternative hypothesis is the hypothesis that contradicts
the null hypothesis. It suggests that there is a significant effect or difference, and is usually
what the researcher wants to prove or find evidence for.

1
2
3
 Chapter 10

Hypothesis:
A hypothesis is a testable proposition or assumption made to explain a phenomenon, which
can be proved or disproved through scientific investigation. (preposition= judgment or opinion)
Characteristics of a hypothesis:
Hypothesis must possess the following characteristics:

9. Clear and Precise: A hypothesis must be clear and precise.

10. Testable: It should be testable through observation and deduction.
11. Relational: If relational, it should state the relationship between variables.
12. Specific and Limited: Hypotheses should be limited in scope and must be specific
13. Simple: It should be easily understandable, though simplicity doesn’t imply less
significance.
14. Consistent: It must align with established facts.
15. Time-bound: It should be testable within a reasonable timeframe.
16. Explanatory: It should explain the facts leading to its formulation and be empirically
grounded.

4
5
6
7
8
4. A sample of 900 members is found to have a mean of 3.47 cm. Can it be reasonably
regarded as a simple sample from a large population with mean 3.23 cm. and standard
deviation 2.31 cm.?

9
 Chapter 12

Multivariate Analysis of Variance (MANOVA) is an extension of Analysis of Variance

(ANOVA) used when there are two or more dependent variables. MANOVA tests whether the
mean differences among groups (based on multiple dependent variables) are statistically
significant. It considers the relationships between the dependent variables and their combined
effect on group differences.
In essence, MANOVA helps analyze multiple outcomes simultaneously, providing a more
comprehensive understanding of how different factors affect several dependent variables.

10
11
12
13
14
T.A.T. (Thematic Apperception Test): It is a projective psychological test where respondents
are shown ambiguous images and asked to tell a story about them. This test is used to explore
underlying thoughts, feelings, and motives.

15
 Chapter 11

1. What is Chi-square test? Explain its significance in statistical analysis.

Answer:
The Chi-square test is a statistical method used to compare observed data with expected data

16
to see if there is a significant difference. It helps determine whether the difference between
what we observe and what we expect is due to random chance or a real effect.

Significance in Statistical Analysis:

1. Testing relationships: It helps to check the relationship between categorical variables

(e.g., gender and preferences).
2. Goodness of fit: It assesses whether the observed data matches a theoretical
distribution (e.g., checking fairness of a coin).
3. Independence test: It checks whether two variables are independent of each other in
a contingency table.
4. Flexibility: Widely used in social sciences, biology, and business for analyzing
survey results, experiments, or market trends.

The Chi-square test is easy to use and provides critical insights into how well data fits a
hypothesis or expected pattern.

2. Write short notes on the following:

(i) Additive property of Chi-square

Question: What is the additive property of Chi-square?

Answer: The additive property of Chi-square means that if you add up independent Chi-
square values calculated from different datasets, the total is also a Chi-square value. This
property helps in combining tests from different groups or experiments.

(ii) Chi-square as a test of ‘goodness of fit’

Question: How does Chi-square test work as a test of ‘goodness of fit’?

Answer: The Chi-square test of goodness of fit checks how well the observed data matches
with the expected data based on a specific model or hypothesis. For example, it can test if a
die is fair by comparing the actual rolls to the expected equal distribution.

(iii) Precautions in applying Chi-square test

Question: What precautions should be taken when applying the Chi-square test?
Answer:

• The sample size should be large enough for reliable results.

• Data should be in the form of counts or frequencies, not percentages.
• Observations must be independent, meaning one result does not affect another.
• Expected frequencies in each category should not be too small (ideally 5 or more).

(iv) Conditions for applying Chi-square test

Question: What are the conditions for applying the Chi-square test?
Answer:

17
 • The data should be categorical (e.g., male/female, yes/no).
• Observations should be randomly selected and independent.
• The expected frequency in each category should generally be 5 or more.
• It cannot be used for very small datasets or continuous data without converting them
into categories.

Questions
Briefly discuss the contents of a research proposal.

The sampling design should be featured in a research proposal because:

1. Representativeness: Ensures the sample reflects the population.

2. Validity and Reliability: Avoids biases and ensures accurate results.
3. Sample Size: Determines the appropriate sample size for statistical power.
4. Resource Management: Helps allocate resources effectively.
5. Statistical Accuracy: Ensures data is suitable for analysis.
6. Error Minimization: Reduces sampling and non-sampling errors.
7. Replicability: Allows other researchers to replicate the study.

18
(a) Dependent and Independent Variables

• Dependent Variable: The knowledge of Tourism and Hospitality Management

(THM) graduates about the Fourth Industrial Revolution.
• Independent Variables:
o Internal traits of THM graduates (e.g., prior knowledge, skills).
o Role of university administrators and faculties.
o Support from external bodies (industry, government policies, NGOs).
o Social surroundings.

Conceptual Model:

• The dependent variable (knowledge of THM graduates) is influenced by various

independent variables (internal traits, university role, external support, and social
surroundings). These factors interact in different ways to shape the level of awareness
about the Fourth Industrial Revolution among THM graduates.

(b) Basic Components of a Theoretical Framework:

1. Concepts: The key ideas or variables that are central to the research.
2. Relationships: Describes how the concepts are linked or affect each other.
3. Theoretical Basis: The theories or previous research that support the framework.
4. Assumptions: Underlying assumptions that influence the framework.
5. Propositions/Hypotheses: Specific statements about the relationships between
concepts that can be tested.
6. Operational Definitions: Clear definitions of concepts and variables that will be
measured in the study.

19