📊

Two-Proportion Z-Test on TI-84

Jul 12, 2025

Overview

This lecture explains how to calculate the test statistic and P-value for a two-proportion hypothesis test using the TI-84 calculator, emphasizing the importance of sample data and proper function selection.

Finding the Test Statistic and P-value

  • The test statistic measures how unusual or surprising a sample is under the null hypothesis.
  • Calculating the statistic by hand is complex and prone to errors, so use your calculator.
  • Use the TI-84 calculator's "Stat" button, then select "Tests," and choose "2-PropZTest" (option 6) for these problems.

Why Use 2-PropZTest?

  • The "2" in 2-PropZTest means the test compares two populations.
  • The "prop" indicates the test is about proportions (fraction or percentage of successes).
  • The "Test" part signifies it's a hypothesis test, as learned in chapters 7.5 and 8.
  • Example: Comparing infants who got therapy versus those who didn’t.

Entering Sample Data

  • X1 and N1 are the number of successes and sample size for group 1 (e.g., X1=377, N1=937).
  • X2 and N2 are the number of successes and sample size for group 2 (e.g., X2=431, N2=932).
  • These numbers come directly from the problem prompt.
  • Use data previously identified when calculating the sample proportions.

Choosing the Inequality

  • The required inequality (less than, greater than, not equal) is found in step one of the hypothesis test.
  • If the question mentions "lower," use the "less than" option for the alternative hypothesis.

Calculating and Interpreting the P-value

  • Hit "Calculate" after entering values to get the P-value.
  • If you see a P-value like 4.4E-3, it is 0.0044 as a decimal, indicating a small probability.
  • Very small P-values (almost zero) suggest the sample is highly unusual under the null hypothesis.

Key Terms & Definitions

  • Test Statistic — A numerical measure of how far the sample result is from the null hypothesis.
  • P-value — The probability of observing a sample result as extreme as, or more extreme than, the observed value, assuming the null hypothesis is true.
  • 2-PropZTest — A calculator function for comparing proportions from two independent samples.
  • X1, N1, X2, N2 — Number of successes and sample sizes from two groups, respectively.

Action Items / Next Steps

  • Practice using the TI-84 to perform 2-PropZTest with sample data.
  • Refer back to your hypothesis from step one to select the correct alternative hypothesis direction.