Hypothesis Testing: The Basics

10 Hypothesis Testing: The Basics

10.1 Null and Alternative Hypotheses

Hypothesis testing is a fundamental statistical method for making inferences about population parameters based on sample data. It involves formulating two competing hypotheses: the null hypothesis and the alternative hypothesis.

• Null Hypothesis (H0): States that there is no effect, no difference, or no change in the population. It is the hypothesis to be tested and possibly rejected.

• Alternative Hypothesis (Ha or H1): States that there is an effect, a difference, or a change in the population. It is what the researcher hopes to support.

For example, if a new drug is tested to lower cholesterol, the null hypothesis might state that the drug has no effect, while the alternative hypothesis states that the drug does lower cholesterol.

Defining the Hypotheses:

• Population parameter: The unknown value of interest (e.g., population mean μ, proportion p).

• Sample statistic: The observed value from the sample (e.g., sample mean x̄, sample proportion p̂).

Examples:

• Testing if a new medication lowers blood pressure: H0: μ = μ0, Ha: μ < μ0

• Testing if a manufacturer’s coffee has less than 500 g per package: H0: μ = 500, Ha: μ < 500

Keyword/Concept	Definition
Hypothesis	A claim about a population parameter that is tested using sample data.
Null hypothesis (H0)	The statement tested; usually a statement of no effect or no difference.
Alternative hypothesis (Ha)	The statement a researcher hopes to support; indicates an effect, difference, or change from the null value.

10.2 Type I and Type II Errors

When making decisions in hypothesis testing, there is a chance of making an error. Two types of errors can occur:

• Type I error (α): Rejecting the null hypothesis when it is actually true (a "false positive").

• Type II error (β): Failing to reject the null hypothesis when the alternative is true (a "false negative").

The probability of a Type I error is denoted by α (the significance level), and the probability of a Type II error is denoted by β. The power of a test is 1 − β, representing the probability of correctly rejecting H0 when Ha is true.

Examples and Intuitive Consequences:

• Medical testing: Type I error = false alarm (healthy person diagnosed as sick); Type II error = missed diagnosis (sick person diagnosed as healthy).

• Quality control: Type I error = rejecting a good batch; Type II error = accepting a bad batch.

Keyword/Concept	Definition
Type I error	Rejecting the null hypothesis when it is true (probability = α).
Type II error	Failing to reject the null hypothesis when the alternative is true (probability = β).
Significance level (α)	The probability of a Type I error; common values are 0.05, 0.01.
Power (1 − β)	The probability of correctly rejecting the null hypothesis when the alternative is true.

10.3 The p-Value and Significance Level

The p-value is the probability, under the null hypothesis, of obtaining a result as extreme or more extreme than the observed sample statistic. It is used to decide whether to reject H0.

• If p-value ≤ α, reject H0 (evidence supports Ha).

• If p-value > α, fail to reject H0 (not enough evidence for Ha).

Practical vs. Statistical Significance: Statistical significance means the result is unlikely due to chance (small p-value), but practical significance considers whether the effect size is large enough to matter in real-world terms.

Keyword/Concept	Definition
Test statistic	A numerical summary of the sample that is compared to the null hypothesis.
p-value	The probability, under the null hypothesis, of observing a result as extreme as the sample statistic.
Significance level (α)	A threshold chosen before the test (e.g., 0.05) to determine statistical significance.
Statistical vs. practical significance	Statistical significance refers to p-value; practical significance refers to whether the effect size is large enough to matter.

10.4 One-Tailed and Two-Tailed Tests

Depending on the research question, hypothesis tests can be one-tailed or two-tailed:

• One-tailed test: Tests for a difference in a specific direction (e.g., greater than or less than).

• Two-tailed test: Tests for any difference from the null value, regardless of direction.

Choosing between one- and two-tailed tests depends on whether the alternative hypothesis specifies a direction.

Keyword/Concept	Definition
One-tailed test	A hypothesis test with a directional alternative (e.g., greater than or less than).
Two-tailed test	A test with a non-directional alternative (not equal to).
Directional vs. non-directional	Directional alternatives specify "greater than" or "less than"; non-directional alternatives specify "not equal".

10.5 The Steps of Hypothesis Testing

Hypothesis testing follows a structured process:

1. State the hypotheses: Formulate the null and alternative hypotheses.

2. Formulate the analysis plan: Choose the significance level (α), the probability of a Type I error, and select the appropriate test statistic.

3. Analyze the data: Compute the test statistic from the sample data and determine the p-value.

4. Draw a conclusion: Compare the p-value to α, decide whether to reject H0, and interpret the result in context.

This structured approach ensures transparency and reproducibility in statistical analysis.

Keyword/Concept	Definition
Hypothesis test steps	The sequence of stating hypotheses, choosing significance level and test statistic, analyzing data, and interpreting results.

Additional info: These notes include examples, step-by-step procedures, and practical applications to reinforce understanding of hypothesis testing concepts. Equations and statistical software screenshots are used to illustrate calculations and interpretations.