Hypothesis Testing and Significance in Statistics

Test of Significance

Introduction to Hypothesis Testing

Hypothesis testing is a fundamental statistical method used to make decisions or judgments about population parameters based on sample data. It involves formulating two competing hypotheses and using sample evidence to determine which hypothesis is more plausible.

• Null Hypothesis (H0): A statement that there is no effect or no difference; it is assumed true until evidence suggests otherwise.

• Alternative Hypothesis (Ha): A statement that contradicts the null hypothesis; it represents the effect or difference the researcher expects to find.

• Types of Tests: One-sided (left or right) and two-sided tests, depending on the direction of the alternative hypothesis.

Key Terms and Concepts

• P-value: The probability, under the null hypothesis, of obtaining a result equal to or more extreme than what was actually observed. A small p-value indicates strong evidence against H0.

• Statistical Significance: If the p-value is less than the chosen significance level (commonly 0.05), the result is considered statistically significant, and H0 is rejected.

• Confidence Level: The probability that a confidence interval contains the true population parameter.

Steps in Hypothesis Testing

General Procedure

1. State the Hypotheses: Formulate H0 and Ha.

2. Choose the Significance Level (α): Common choices are 0.05 or 0.01.

3. Compute the Test Statistic: Calculate the appropriate statistic (e.g., z, t) based on the sample data.

4. Find the P-value: Determine the probability of observing the test statistic under H0.

5. Make a Decision: Compare the p-value to α and decide whether to reject H0.

Types of Hypothesis Tests

• One-tailed Test: Used when the alternative hypothesis is directional (e.g., greater than or less than a specified value).

• Two-tailed Test: Used when the alternative hypothesis is non-directional (e.g., not equal to a specified value).

Formulating Hypotheses

Null and Alternative Hypotheses

The null hypothesis typically states that a population parameter equals a specified value. The alternative hypothesis states that the parameter differs from that value, either in a specific direction (one-tailed) or in any direction (two-tailed).

• Null Hypothesis (H0): $H_0: ext{parameter} = ext{specified value}$

• Alternative Hypothesis (Ha):

  • Left-tailed: $H_a: ext{parameter} < ext{specified value}$

  • Right-tailed: $H_a: ext{parameter} > ext{specified value}$

  • Two-tailed: $H_a: ext{parameter} eq ext{specified value}$

Examples

• Example 1: A snack company produces 454-g bags of cookies. The quality assurance department wants to test if the mean net weight of all bags is 454 g.

  • Null hypothesis: $H_0: ext{mean} = 454$

  • Alternative hypothesis: $H_a: ext{mean} eq 454$ (two-tailed test)

• Example 2: In 2005, the mean retail price of history books was $176.01. To test if the mean price has increased:

  • Null hypothesis: $H_0: ext{mean} = 176.01$

  • Alternative hypothesis: $H_a: ext{mean} > 176.01$ (right-tailed test)

Using the P-value Approach

Guidelines for Assessing Evidence

1. State the null and alternative hypotheses.

2. Choose the significance level (α).

3. Compute the value of the test statistic.

4. Determine the p-value.

5. Compare the p-value to α:

   • If $p ext{ value} ext{ } < ext{ } ext{significance level}$, reject H0.

   • If $p ext{ value} ext{ } > ext{ } ext{significance level}$, do not reject H0.

6. Interpret the results in the context of the problem.

Summary Table: Hypothesis Test Types

Test Type	Alternative Hypothesis	Example
Left-tailed	$H_a: ext{parameter} < ext{value}$	Mean weight is less than 454 g
Right-tailed	$H_a: ext{parameter} > ext{value}$	Mean price is greater than $176.01
Two-tailed	$H_a: ext{parameter} eq ext{value}$	Mean weight is not equal to 454 g

Additional info:

• When the sample data provide substantial contradictory evidence, the null hypothesis is rejected.

• If the sample data do not provide enough evidence, the null hypothesis is not rejected, and its plausibility is maintained.

• Choosing the correct form of the alternative hypothesis is crucial and should reflect the research question.