Hypothesis Testing for Population Proportions

Chapter 15 (Part I): Testing Hypotheses About Population Proportions

Introduction to Hypothesis Testing

Hypothesis testing is a fundamental statistical procedure used to make inferences about population parameters based on sample data. In statistics, a hypothesis is a conjecture or claim about a population parameter, such as a mean or proportion. Hypotheses are typically stated in terms of parameters like the population mean (μ) or population proportion (p).

• Example 1: Population proportion, $p = 0.3$

• Example 2: Mean number of sick leave days taken by employees, $\mu = 8.7$

• Example 3: Proportion of voters favoring candidate A, $p = 0.55$

Key Definitions

• Null Hypothesis ($H_0$): A statement specifying the value of a population parameter. It is the hypothesis that is initially assumed to be true and is tested against the data.

• Alternative Hypothesis ($H_a$): A statement that contradicts the null hypothesis. It represents the claim or suspicion that the researcher wants to test.

Steps in Hypothesis Testing

The process of hypothesis testing involves several key steps:

1. State the null hypothesis ($H_0$) and alternative hypothesis ($H_a$).

2. Collect sample data from the population.

3. Calculate the test statistic based on the sample data.

4. Determine the p-value or observed significance level.

5. Compare the p-value to the significance level ($\alpha$) to make a decision.

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

Elements of a Test of Hypothesis

• The null hypothesis, $H_0$

• The alternative hypothesis, $H_a$

• The decision rule

• The test statistic

• Calculation of the observed significance level, or p-value

• Interpretation of the results

Test Statistic for Population Proportion

When testing a hypothesis about a population proportion, the test statistic is calculated as follows:

$z = \frac{\hat{p} - p}{\sqrt{\frac{p(1-p)}{n}}}$

• $\hat{p}$ = sample proportion

• $p$ = hypothesized population proportion

• $n$ = sample size

Decision Rule and Significance Level

The decision rule specifies the conditions under which the null hypothesis will be rejected. The significance level ($\alpha$) is the probability of making a Type I error (rejecting $H_0$ when it is true). Common choices for $\alpha$ are 0.05 or 0.01.

• Reject $H_0$ if the p-value < $\alpha$

• Fail to reject $H_0$ if the p-value ≥ $\alpha$

Understanding the p-value

The p-value is the probability, assuming the null hypothesis is true, of obtaining a test statistic at least as extreme as the one observed. It quantifies the evidence against the null hypothesis.

• For $H_0: p = 0.30$ vs $H_a: p < 0.30$, the p-value is the probability of getting a sample proportion less than or equal to the observed value.

• For $H_0: p = 0.20$ vs $H_a: p > 0.20$, the p-value is the probability of getting a sample proportion greater than or equal to the observed value.

• For $H_0: p = 0.30$ vs $H_a: p \neq 0.30$, the p-value is twice the probability of getting a sample proportion as extreme or more extreme than the observed value (in either direction).

Types of Errors in Hypothesis Testing

• Type I Error: Rejecting the null hypothesis when it is actually true. The probability of a Type I error is $\alpha$.

• Type II Error: Failing to reject the null hypothesis when the alternative hypothesis is true. The probability of a Type II error is denoted by $\beta$.

Identifying a z-Test of Hypothesis About p

• The population of interest contains qualitative data; the parameter of interest is the population proportion $p$.

• The objective is to determine if the sample data supports the claim that $p$ is greater than, less than, or not equal to a hypothesized value.

• A large, random sample is collected, and the sample proportion $\hat{p}$ is calculated.

Elements of a z-Test of Hypothesis About p

• Define the parameter $p$ in the context of the test.

• State the hypotheses:

  • $H_0: p = p_0$

  • $H_a: p > p_0$, $p < p_0$, or $p \neq p_0$

• Decision Rule: Reject $H_0$ if the p-value < $\alpha$

• Test Statistic:

  $z = \frac{\hat{p} - p_0}{\sqrt{\frac{p_0(1-p_0)}{n}}}$

• Calculate the p-value

• Make a decision

• Interpret the results

Worked Example: Hypothesis Test for a Proportion

Scenario: A producer claims that 20% of all orange juice drinkers prefer its product. A competitor samples 200 drinkers and finds that 34 prefer the producer's brand. Test at a 0.05 significance level whether the competitor's claim (that the 20% figure is too large) is supported.

1. Parameter of interest: $p$ = proportion of all orange juice drinkers who prefer the producer's brand.

2. Null hypothesis: $H_0: p = 0.20$

3. Alternative hypothesis: $H_a: p < 0.20$

4. Sample proportion: $\hat{p} = \frac{34}{200} = 0.17$

5. Test statistic:

   $z = \frac{0.17 - 0.20}{\sqrt{\frac{0.20 \times 0.80}{200}}}$

6. Calculate p-value: Find the probability that $z$ is less than the calculated value.

7. Decision: If p-value < 0.05, reject $H_0$; otherwise, do not reject $H_0$.

8. Interpretation: State whether there is sufficient evidence to support the competitor's claim.

Types of Hypothesis Tests for Proportions

Test Type	Null Hypothesis ($H_0$)	Alternative Hypothesis ($H_a$)	When to Use
Left-tailed	$p = p_0$	$p < p_0$	Testing if the proportion is less than a specified value
Right-tailed	$p = p_0$	$p > p_0$	Testing if the proportion is greater than a specified value
Two-tailed	$p = p_0$	$p \neq p_0$	Testing if the proportion is different from a specified value

Types of Errors: Example Application

Suppose an entrepreneur is considering opening a new restaurant if more than 15% of local residents are interested. A survey of 500 people finds 90 interested.

• Type I Error: Concluding that more than 15% are interested (and opening the restaurant) when in fact 15% or fewer are interested.

• Type II Error: Concluding that 15% or fewer are interested (and not opening the restaurant) when in fact more than 15% are interested.

Significance Level ($\alpha$): The entrepreneur should choose $\alpha$ based on the relative consequences of these errors. For example, if opening a restaurant is costly, a smaller $\alpha$ may be preferred to reduce the risk of a Type I error.

Confidence Interval for a Proportion

A confidence interval provides a range of plausible values for the population proportion. The 95% confidence interval for $p$ is given by:

$\hat{p} \pm z^* \sqrt{\frac{\hat{p}(1-\hat{p})}{n}}$

• $z^*$ is the critical value from the standard normal distribution (for 95%, $z^* \approx 1.96$)

• Interpretation: We are 95% confident that the true population proportion lies within this interval.

Example: If 48 out of 80 graduate students have purchased online, $\hat{p} = 0.6$. The 95% confidence interval is:

$0.6 \pm 1.96 \sqrt{\frac{0.6 \times 0.4}{80}}$

Calculate the lower and upper limits to interpret the interval.

Additional info: These notes cover the foundational concepts and procedures for hypothesis testing about population proportions, including the formulation of hypotheses, calculation of test statistics and p-values, types of errors, and confidence intervals. The examples and tables are designed to help students apply these concepts to real-world scenarios.