Hypothesis Testing for Population Proportions and Means: Structured Study Notes

Hypothesis Testing for Population Proportions and Means

Introduction to Hypothesis Testing

Hypothesis testing is a fundamental statistical procedure used to evaluate claims about a population based on sample data. The process involves four main steps: writing hypotheses, calculating a test statistic, obtaining a p-value, and stating a conclusion. This method allows researchers to determine whether there is enough evidence to reject a default assumption about a population parameter.

• Hypothesis Test Steps:

  1. Write Hypotheses

  2. Calculate Test Statistic

  3. Get P-Value

  4. State Conclusion

• Example: An article claims that 50% of students listen to music while studying. A hypothesis test can be used to determine if the proportion is actually higher.

Step 1: Writing Hypotheses

Every hypothesis test begins with two statements:

• Null Hypothesis (H0): The default assumption or status quo about a population parameter (e.g., "50% of students listen to music").

• Alternative Hypothesis (Ha): The opposing claim that the researcher seeks evidence for (e.g., "More than 50% of students listen to music").

• Notation:

  • For proportions: $H_0: p = p_0$, $H_a: p \neq p_0$, $p > p_0$, or $p < p_0$

  • For means: $H_0: \mu = \mu_0$, $H_a: \mu \neq \mu_0$, $\mu > \mu_0$, or $\mu < \mu_0$

• Example: A business journal wants to prove that more than 20% of companies have female CEOs. $H_0: p = 0.20$, $H_a: p > 0.20$

Step 2: Calculating the Test Statistic

The test statistic measures how far the sample data is from the claimed parameter. The choice of test statistic depends on the parameter being tested and whether certain values (like standard deviation) are known.

• Formulas:

  • Mean (σ known): $z = \frac{\bar{x} - \mu}{\sigma / \sqrt{n}}$

  • Mean (σ unknown): $t = \frac{\bar{x} - \mu}{s / \sqrt{n}}$

  • Proportion: $z = \frac{\hat{p} - p}{\sqrt{p(1-p)/n}}$

  • Variance: $\chi^2 = \frac{(n-1)s^2}{\sigma^2}$

• Example: A sample of students has a mean age of 22, while the claimed mean is 23 with σ = 4 and n = 35. Use the z-test statistic.

Step 3: Obtaining the P-Value

The p-value is the probability of obtaining a sample as extreme as the observed one, assuming the null hypothesis is true. It is calculated based on the test statistic and the type of test (left-tailed, right-tailed, or two-tailed).

• P-Value Calculation:

  • Left-tailed: Area to the left of the test statistic

  • Right-tailed: Area to the right of the test statistic

  • Two-tailed: Twice the area in the tail beyond the test statistic

• Example: If $z = 1.73$, the p-value is the area to the right of 1.73 in the standard normal distribution.

Step 4: Stating the Conclusion

The conclusion is based on comparing the p-value to the significance level (α). If the p-value is less than α, the null hypothesis is rejected. Otherwise, it is not rejected.

• Significance Level (α): The threshold for how unusual a sample must be before rejecting H0 (commonly 0.10, 0.05, or 0.01).

• Decision:

  • Reject H0 if p-value < α

  • Fail to reject H0 if p-value ≥ α

• Example: "There is evidence to disprove that 50% of students listen to music."

Hypothesis Tests for Mean (σ Known and Unknown)

When testing means, the procedure depends on whether the population standard deviation is known or unknown. If known, use the z-test; if unknown, use the t-test.

• z-test: Used when σ is known and the population is normal or n > 30.

• t-test: Used when σ is unknown and the population is normal or n > 30.

• Example: A lighting company claims bulbs last 25,000 hours (σ = 1,200 hr). A sample finds a mean of 24,600 hr. Use the z-test to evaluate the claim.

Hypothesis Tests for Proportion

Testing proportions involves comparing the sample proportion to the claimed population proportion using the z-test statistic.

• Formula: $z = \frac{\hat{p} - p}{\sqrt{p(1-p)/n}}$

• Conditions: Random samples and $np \geq 5$, $nq \geq 5$

• Example: A tech company claims 90% of devices pass inspection. A sample of 200 devices finds 172 passed. Test if the pass rate is below 90%.

Hypothesis Tests for Variance

Variance tests use the chi-square statistic to determine if the sample variance differs from the claimed population variance.

• Formula: $\chi^2 = \frac{(n-1)s^2}{\sigma^2}$

• Conditions: Data must be normally distributed.

• Example: A cereal packaging line requires variance ≤ 0.25 g2. A sample variance of 0.31 g2 is tested at α = 0.10.

Hypothesis Testing Using Critical Values

The critical value method compares the test statistic to a threshold (critical value) that defines the rejection region. If the test statistic falls in the rejection region, the null hypothesis is rejected.

• Critical Value: The boundary between expected and unusual test statistics, found from α.

• Rejection Region: Area beyond the critical value.

• Example: For a right-tailed test with α = 0.01 and z = 2.17, compare z to the critical value.

Confidence Intervals and Hypothesis Testing

Confidence intervals can be used to reach the same conclusion as a two-tailed hypothesis test. If the claimed value is outside the confidence interval, the null hypothesis is rejected.

• Example: A teacher claims the average test score is 75. A sample mean of 78 with a standard deviation of 6 is used to create a 90% confidence interval and test the claim at α = 0.01.

Type I and Type II Errors

Hypothesis tests are subject to two types of errors:

• Type I Error (α): Rejecting a true null hypothesis.

• Type II Error (β): Failing to reject a false null hypothesis.

• Minimizing Errors:

  • Decrease α to minimize Type I error.

  • Increase α to minimize Type II error.

• Example: Testing if a treatment lowers blood pressure to 120 mmHg. Type I error: Conclude treatment works when it does not. Type II error: Conclude treatment does not work when it actually does.

Summary Table: Hypothesis Test Steps and Formulas

Parameter	Step 1: Hypotheses	Step 2: Test Statistic	Step 3: P-Value	Step 4: Conclusion
Mean (σ Known)	$H_0: \mu = \mu_0$ $H_a: \mu \neq, >, < \mu_0$	$z = \frac{\bar{x} - \mu}{\sigma / \sqrt{n}}$	$P(Z [<|>|] z)$ or $2 \cdot P(Z [<|>|] z)$	Compare p-value to α; reject or fail to reject H0
Mean (σ Unknown)	$H_0: \mu = \mu_0$ $H_a: \mu \neq, >, < \mu_0$	$t = \frac{\bar{x} - \mu}{s / \sqrt{n}}$	$P(T_{n-1} [<|>|] t)$ or $2 \cdot P(T_{n-1} [<|>|] t)$	Compare p-value to α; reject or fail to reject H0
Proportion	$H_0: p = p_0$ $H_a: p \neq, >, < p_0$	$z = \frac{\hat{p} - p}{\sqrt{p(1-p)/n}}$	$P(Z [<|>|] z)$ or $2 \cdot P(Z [<|>|] z)$	Compare p-value to α; reject or fail to reject H0
Variance	$H_0: \sigma^2 = \sigma_0^2$ $H_a: \sigma^2 \neq, >, < \sigma_0^2$	$\chi^2 = \frac{(n-1)s^2}{\sigma^2}$	$P(\chi^2_{n-1} [<|>|] \chi^2)$ or $2 \cdot P(\chi^2_{n-1} [<|>|] \chi^2)$	Compare p-value to α; reject or fail to reject H0

Performing Hypothesis Tests Using TI-84 Calculator

Statistical calculators like the TI-84 can be used to perform hypothesis tests for means and proportions. Enter the sample data or statistics, select the appropriate test (z-test, t-test, or proportion test), and interpret the output.

• Example: A nutritionist tests if the average daily protein intake differs from 50g using sample mean, standard deviation, and significance level.

Practice Problems and Applications

Practice problems reinforce the steps and concepts of hypothesis testing. They include real-world scenarios such as testing claims about attendance, product quality, or health statistics.

• Example: A city government claims that no more than 25% of households have solar panels. A survey tests if the rate is actually higher.

Visual Representation of Hypothesis Testing

Visual aids, such as normal distribution curves with shaded rejection regions, help illustrate the concept of p-values and critical values in hypothesis testing.

Type I and Type II Error Scenarios

Understanding the consequences of Type I and Type II errors is crucial for interpreting hypothesis test results and designing studies.

• Example: A new cancer screening test reports whether a patient has cancer. Type I error: False positive. Type II error: False negative.

Summary

Hypothesis testing is a structured process for evaluating claims about population parameters. By following the four steps—writing hypotheses, calculating test statistics, obtaining p-values, and stating conclusions—students can rigorously test assumptions and interpret statistical evidence. Mastery of these concepts is essential for further study in statistics and for practical applications in research and industry.