HYPOTHESIS
TESTING
BUA212
OUTLINE
• Hypothesis Testing
• Null and alternative hypotheses.
• Types of errors in hypothesis testing.
• P-value, t-tests, z-tests: concepts and applications in business
DEFINITION AND PURPOSE
• Hypothesis Testing: A statistical method used to make decisions or
inferences about a population based on sample data. It determines
whether there is enough evidence to support a specific claim.
• It is used for decision-making in areas like quality control, market
research, financial forecasting, and employee performance evaluation.
NULL AND ALTERNATIVE HYPOTHESES
• Null Hypothesis (H₀): A statement of no effect or no difference,
serving as the default assumption or claim.
• Example: There is no relationship between intelligence and academic
results.
• Alternative Hypothesis (H₁ or Ha): A statement that contradicts
the null hypothesis, representing the effect or difference being tested.
• Example: There is a relationship between intelligence and academic
results.
Hypotheses are mutually exclusive and collectively exhaustive
TYPES OF ERRORS IN HYPOTHESIS TESTING
Type I Error (False Positive)
• Rejecting a null hypothesis (H₀) when it is true. For example, concluding that a
new marketing strategy increases sales when it does not. Probability of Type I
error = α.
Type II Error (False Negative)
• Failing to reject a null hypothesis (H₀) when it is false. An example is failing to
detect that a new supplier improves quality. Probability of Type II error = β.
Power of a Test = 1 - β (the probability of correctly rejecting H₀).
STEPS IN HYPOTHESIS TESTING
1. Formulate Hypotheses: Define H₀ and H₁ clearly
2. Choose the Significance Level (α): Commonly used levels are 0.05 or 0.01.
3. Collect data and Select the Appropriate Test Statistic: Depends on the sample
size, data distribution, and variance. Examples: Z-test, T-test, Chi-square, F-test.
4. Calculate the Test Statistic and P-value.
5. Make a Decision: Compare p-value with the level of significance (α). The
decision rule is that if p-value ≤ α, reject H₀; otherwise, fail to reject H₀.
6. Interpret Results: State the conclusion in the context of the research question.
COMMON HYPOTHESIS TESTS
Z-tests
Used for large samples (n ≥ 30) or when population variance is known.
• Types
• One-sample z-test: Compare a sample mean to a known population
mean
• Two-sample z-test: Compare means of two large independent groups.
• Business Example
Testing the difference in customer spending across two store locations.
COMMON HYPOTHESIS TESTS
T-test: Used when sample size is small (n < 30) and population variance
is unknown.
• One-sample T-test: Tests if the sample mean is significantly
different from a known population mean.
• Two-sample T-test: Tests if the means of two independent
samples are significantly different.
• Paired T-test: Tests if the means of two related groups are
significantly different. e.g., before and after data).
• Business Example: Comparing employee satisfaction scores before and
after a new policy.
COMMON HYPOTHESIS TESTS
Chi-square Test
• Used for categorical data to test the association between variables or the
goodness of fit.
ANOVA (Analysis of Variance)
Used to compare the means of three or more groups.
• One-way ANOVA: Tests for differences among group means.
• Two-way ANOVA: Tests for the interaction effect between two independent
variables.
ASSUMPTIONS AND CONDITIONS
• Normality: Data should follow a normal distribution for Z and T tests.
Graphical methods (histograms, Q-Q plots) and statistical tests
(Shapiro-Wilks test) to check for normality.
• Independence: Observations should be independent. Check study
design and sampling methods for independence.
• Homogeneity of Variance: Variances across groups should be equal
for ANOVA. Use Levene's test for homogeneity of variance.
APPLICATIONS IN BUSINESS
• Quality Control: Testing whether product defects exceed an
acceptable threshold.
• Market Research: Comparing customer preferences between regions
or demographics.
• Financial Analysis: Evaluating returns of two investment portfolios.
• HR Decisions: Assessing training program impacts on employee
productivity.
EXAMPLE
• The average weight of a dumbbell in a gym is 90lbs. However, a
physical trainer believes that the average weight might be higher. A
random sample of 5 dumbbells with an average weight of 110lbs and a
standard deviation of 18lbs. Using hypothesis testing check if the
physical trainer's claim can be supported for a 95% confidence level.
SOLUTION
• H₀ : The average weight of the dumbbells may not be greater than 90lbs
• H1: The average weight of the dumbbells may be greater than 90lbs
As the sample size is less than 30, the t-test is used
• = 110, μ = 90, n = 5, s = 18, α = 0.05
• = = 2.484
• Using the t-distribution table, the critical value is 2.132
• As 2.484 > 2.132, the null hypothesis is rejected.
Answer: The average weight of the dumbbells may be greater than 90lbs
EXAMPLE
• The mean height of a student population is 65 inches. 50 students were
sampled with an average height of 66 inches and variance of 9 inches.
Using hypothesis testing check if the average height of a sample of
students is different from the known population mean height at 0.05
significance level.
• H₀: The average height of the sample is not different from the known population mean height
• H1: The average height of the sample is different from the known population mean height
Since the sample size is more than 30, the Z-test is used
• = 66, μ = 65, n = 50, σ = 3, α = 0.05
• = = 2.36
• Compare Z-value to critical value (±1.96)
• As 2.36 > 1.96, the null hypothesis is rejected.
Conclusion: The average height of the sample is different from the known population mean
height.
