KASNEB · FoundationQuantitative AnalysisBETA — flag if wrong

Hypothesis Testing

This topic introduces the concepts and procedures for hypothesis testing in quantitative analysis.

3objectives

3revision lessons

12practice questions

What you’ll learn

Aligned to the KASNEB Quantitative Analysis syllabus.

CF12.7.A Define null and alternative hypotheses.
CF12.7.B Explain the steps involved in hypothesis testing.
CF12.7.C Apply hypothesis testing to real-world business scenarios.

Defining Null and Alternative Hypotheses in Hypothesis Testing

BETA — flag if wrongAI 100

In hypothesis testing, two competing statements are formulated: the null hypothesis (H0) and the alternative hypothesis (H1). The null hypothesis represents a statement of no effect or no difference, serving as a default position that indicates no change in the population parameter being tested. The alternative hypothesis, conversely, suggests that there is an effect or a difference. It is what the researcher aims to support through evidence.

For example, if we want to test whether a new teaching method improves student performance, the null hypothesis might state that the average test scores of students using the new method are equal to those using the traditional method (H0: μ1 = μ2). The alternative hypothesis would state that the average test scores of students using the new method are different (H1: μ1 ≠ μ2).

In a practical context, such as evaluating a new product in the Kenyan market, the null hypothesis could assert that the new product has no impact on sales compared to the existing product, while the alternative hypothesis would claim that the new product does affect sales positively or negatively. Understanding these hypotheses is crucial for conducting valid statistical tests and making informed business decisions.

Key points

Null hypothesis (H0): statement of no effect or difference.
Alternative hypothesis (H1): statement indicating an effect or difference.
H0 is the default position; H1 is what researchers aim to support.
Example: H0: μ1 = μ2 vs. H1: μ1 ≠ μ2 in testing methods.
Clear definitions guide valid statistical testing.

Worked example

Consider a company in Kenya testing a new marketing strategy.

Null Hypothesis (H0): The new strategy does not increase sales. (H0: μ1 = μ2)
Alternative Hypothesis (H1): The new strategy increases sales. (H1: μ1 > μ2)

If the company collects data and finds that the average sales before the strategy were KES 100,000 and after implementing it, the average sales are KES 120,000 with a standard deviation of KES 15,000, they can perform a t-test to determine if this difference is statistically significant, thus testing their hypotheses.

More on this topic

CF12.7.B Steps in Hypothesis Testing ExplainedBETA — flag if wrongAI 100

Hypothesis testing is a statistical method used to make decisions based on data analysis. The process involves several key steps:

1. Formulate the Hypotheses: Start with two competing hypotheses. The null hypothesis (H0) represents no effect or no difference, while the alternative hypothesis (H1) indicates the presence of an effect or difference.

2. Select the Significance Level (α): Choose a significance level, commonly set at 0.05 or 5%. This threshold determines the probability of rejecting the null hypothesis when it is true (Type I error).

3. Collect Data: Gather relevant data through sampling. Ensure the sample size is adequate to provide reliable results. In Kenya, consider using M-Pesa for efficient data collection if applicable.

4. Choose the Appropriate Test: Depending on the data type and distribution, select a statistical test (e.g., t-test, chi-square test). Ensure the test aligns with the hypotheses.

5. Calculate the Test Statistic: Use the chosen statistical test to compute the test statistic from the sample data. This value will help determine whether to reject H0.

6. Determine the P-value or Critical Value: Calculate the p-value associated with the test statistic or compare the test statistic to a critical value from statistical tables.

7. Make a Decision: If the p-value is less than α, reject the null hypothesis. If it is greater, do not reject H0. This decision informs whether there is enough evidence to support the alternative hypothesis.

8. Draw Conclusions: Summarize the findings and relate them to the context of the problem. Discuss the implications of the results in a Kenyan business context, such as market trends or consumer behavior.

CF12.7.C Applying Hypothesis Testing in Business ScenariosBETA — flag if wrongAI 100

Hypothesis testing is a statistical method used to make decisions based on data analysis. In a business context, it helps assess assumptions about a population based on sample data. The process involves formulating a null hypothesis (H0) and an alternative hypothesis (H1).

1. Define the Hypotheses: The null hypothesis typically states that there is no effect or difference, while the alternative suggests that there is. For example, if a company claims its new marketing strategy increases sales, H0 could be 'the strategy has no effect on sales', and H1 could be 'the strategy increases sales'.

2. Select a Significance Level: Commonly, a significance level (α) of 0.05 is used, which indicates a 5% risk of rejecting the null hypothesis when it is true.

3. Collect Data: Gather sample data relevant to the hypotheses. For instance, sales data before and after implementing the marketing strategy.

4. Perform the Test: Use appropriate statistical tests (e.g., t-test, chi-square test) to analyze the data. Calculate the test statistic and compare it to the critical value from statistical tables.

5. Make a Decision: If the test statistic exceeds the critical value, reject H0 in favor of H1. Otherwise, do not reject H0. This decision informs business strategies and resource allocation.

In Kenya, businesses can use hypothesis testing to evaluate marketing campaigns, customer satisfaction surveys, and product performance, ensuring data-driven decision-making.

Sample KASNEB-style questions

3 of 12 questions. Beta-flagged questions are AI-drafted and pending CPA review — flag anything that looks wrong.

Q1 · MCQ · easyBETA — flag if wrongAI 100

What is the null hypothesis (H0) in hypothesis testing?

A.A. A statement that indicates no effect or no difference.✓ correct
B.B. A statement that indicates a significant effect or difference.
C.C. A statement that is always true.
D.D. A statement that can never be tested.

Q2 · MCQ · mediumBETA — flag if wrongAI 93

Which of the following statements best describes the alternative hypothesis (H1)?

A.A. It asserts that there is no significant difference.
B.B. It is a statement that the researcher aims to support.✓ correct
C.C. It is always accepted as true.
D.D. It represents the status quo.

Q3 · SHORT ANSWER · mediumBETA — flag if wrongAI 93

Define the terms 'null hypothesis' and 'alternative hypothesis'.

Model answer

1. Null Hypothesis (H0): A statement that there is no significant effect or difference in the population. It is the hypothesis that researchers aim to test against. 2. Alternative Hypothesis (H1): A statement that indicates the presence of an effect or difference. It is what researchers want to prove.

Practice the full question bank with the AI tutor

12 questions on this topic alone. Get feedback after every attempt; the tutor re-explains what you got wrong. Beta access is free.

Reserve beta access

Common questions

Define null and alternative hypotheses.

Null hypothesis (H0): statement of no effect or difference.

Explain the steps involved in hypothesis testing.

Formulate null and alternative hypotheses.

Apply hypothesis testing to real-world business scenarios.

Define null and alternative hypotheses clearly.