Section 7.1: Introduction to Hypothesis Testing

Overview

This section introduces the fundamental concepts and procedures of hypothesis testing in statistics. Hypothesis testing is a systematic method used to evaluate claims about population parameters based on sample data.

• Hypothesis Test: A process that uses sample statistics to test a claim about the value of a population parameter.

• Statistical Hypothesis: A statement about a population parameter, typically formulated as a pair of hypotheses: the null hypothesis and the alternative hypothesis.

• Objective: To determine whether there is enough evidence in a sample to infer that a certain condition holds for the entire population.

Hypothesis Tests

Key Concepts

Hypothesis tests involve making decisions about population parameters using sample data. The process requires careful formulation of hypotheses and understanding possible errors.

• Null Hypothesis (H0): The hypothesis that contains a statement of equality (e.g., =, ≤, ≥). It is assumed true until evidence suggests otherwise.

• Alternative Hypothesis (Ha): The complement of the null hypothesis, containing a statement of strict inequality (e.g., <, >, ≠).

• Claim Representation: Either hypothesis may represent the original claim.

Stating Hypotheses

Translating Claims

To conduct a hypothesis test, translate verbal claims about population parameters into mathematical statements. Then, write the complement as the opposing hypothesis.

• Verbal Statements: Claims such as "the mean is at least k" or "the mean is less than k" are translated into mathematical hypotheses.

• Mathematical Statements: For example, H0: μ ≥ k, Ha: μ < k.

• Example: If a school claims that 61% of students participate in extracurricular activities, then H0: p = 0.61 (claim), Ha: p ≠ 0.61.

Types of Errors in Hypothesis Testing

Type I and Type II Errors

Decisions in hypothesis testing are based on sample data, which can lead to errors:

• Type I Error: Rejecting the null hypothesis when it is actually true. The probability of a Type I error is denoted by α (alpha).

• Type II Error: Failing to reject the null hypothesis when it is actually false. The probability of a Type II error is denoted by β (beta).

• Example: If the USDA limit for salmonella contamination is 7.5%, a Type I error would be falsely concluding contamination exceeds the limit, while a Type II error would be failing to detect contamination above the limit.

Level of Significance

Definition and Importance

The level of significance (α) is the maximum allowable probability of making a Type I error. It is chosen by the researcher and commonly set at 0.10, 0.05, or 0.01.

• α (alpha): The probability threshold for rejecting the null hypothesis.

• β (beta): The probability of making a Type II error.

Statistical Tests and Test Statistics

Test Statistic and Standardization

After stating the hypotheses and specifying the significance level, a random sample is taken and sample statistics are calculated. The test statistic is compared with the parameter in the null hypothesis and then standardized (e.g., z, t, χ2).

• Test Statistic: The value calculated from sample data used to decide whether to reject H0.

• Standardized Test Statistic: Converts the test statistic to a common scale (z, t, χ2).

P-Value and Nature of Tests

P-Value

The P-value is the probability, assuming H0 is true, of obtaining a sample statistic as extreme or more extreme than the observed value. It is used to make decisions about H0.

• Decision Rule: If P-value ≤ α, reject H0. If P-value > α, fail to reject H0.

Types of Tests

The nature of the test depends on the alternative hypothesis:

• Left-tailed Test: Ha contains < (e.g., μ < k). P-value is the area to the left of the test statistic.

• Right-tailed Test: Ha contains > (e.g., μ > k). P-value is the area to the right of the test statistic.

• Two-tailed Test: Ha contains ≠ (e.g., μ ≠ k). P-value is the sum of the areas in both tails.

Making and Interpreting Decisions

Decision Rule Based on P-value

Compare the P-value with the significance level to decide whether to reject or fail to reject H0. Interpret the decision in the context of the original claim.

• If Claim is H0: Reject H0 → reject the claim; Fail to reject H0 → not enough evidence to reject the claim.

• If Claim is Ha: Reject H0 → support the claim; Fail to reject H0 → not enough evidence to support the claim.

Steps for Hypothesis Testing

Procedure

Follow these steps to conduct a hypothesis test:

1. State the claim mathematically and verbally. Identify H0 and Ha.

2. Specify the level of significance (α).

3. Determine the standardized sampling distribution and draw its graph.

4. Calculate the test statistic and its standardized value. Add it to your sketch.

5. Find the P-value.

6. Use the decision rule: If P-value ≤ α, reject H0; otherwise, fail to reject H0.

7. State the interpretation in the context of the original claim.

Strategies for Hypothesis Testing

Supporting or Rejecting Claims

The strategy depends on whether you want to support or reject a claim:

• Supporting a Claim: Word the claim as the alternative hypothesis.

• Rejecting a Claim: Word the claim as the null hypothesis.

• Example: If a medical research team wants to support the claim that mean recovery time is less than 96 hours, set Ha: μ < 96 hours. If an opposing team wants to reject the claim, set H0: μ ≤ 96 hours.

Key Formulas

Standardized Test Statistics

• z-test (for mean, σ known):

• t-test (for mean, σ unknown):

• z-test (for proportion):

• χ2-test (for variance):

Summary Table: Types of Errors

Additional info: Academic context and examples were expanded for clarity and completeness.