HOMEWORK QUESTIONS SECTION 8.3 ESTIMATING A POPULATION MEAN ONE-SAMPLE Z INTERVAL FOR A POPULATION MEAN 𝑥 ± 𝑧∗ 𝜎 𝑛 As long as the Random, Normal, and Independent conditions are met…This is your confidence interval! We use this when we know 𝜎 CHOOSING A SAMPLE SIZE Now that we know 𝜎 … 𝑧∗ 𝜎 𝑛 ≤ 𝑀𝐸 Ex: Obtaining monkeys is time-consuming and expensive, so researchers want to know the minimum number of monkeys needed to generate a satisfactory estimate of cholesterol levels for a study. They want their estimate to be within 1 mg/dl of the true value of 𝜇 at a 95% confidence interval. WHEN 𝜎 IS UNKNOWN…T DISTRIBUTIONS WHEN 𝜎 IS UNKNOWN…T DISTRIBUTIONS 𝑥−𝜇 𝑡= 𝑑𝑓 = 𝑛 − 1 𝑠𝑥 𝑛 ONE-SAMPLE T INTERVAL FOR A POPULATION MEAN 𝑥 ± 𝑡∗ 𝑠𝑥 𝑛 Use when the population is Normal or the sample size is large enough (𝑛 ≥ 30) and the population is at least 10 times the sample size. T PROCEDURES: THE NORMAL CONDITION Sample size less than 30 – use t if the data appear close to Normal (roughly symmetric, single peak, no outliers). Do not use otherwise. Large Samples – t can be used even for clearly skewed distributions #63 HOMEWORK #2 Pg 518 (63, 67-70, 72-78)