This preview shows pages 1–5. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Chapter 3 Review of Statistics (Part 2) Confidence Intervals for the Population Mean It is impossible to know the true population mean μ Y from random samples. However, it is possible to construct an interval that contains μ Y with a prespecified probability. I The prespecified probability is called the confidence level . I The interval is called the confidence interval . 95% confidence interval for μ Y is Y & 1.96 SE ( Y ) ¡ μ Y ¡ Y + 1.96 SE ( Y ) or μ Y = & Y ¢ 1.96 SE ( Y ) ¡ . The interval contains the true μ Y in 95% of all possible random samples. Comparing Means from Different Populations: Hypothesis Tests Do recent male and female college graduates earn the same amount on average? I Let μ w be the mean hourly earning in the population of women recently graduated. I Let μ m be the population mean for recently graduated men. The null and the twosided alternative hypothesis for our question are: H : μ m & μ w = 0 vs. H 1 : μ m & μ w 6 = 0. Population means are unknown, we have to estimate them from samples. Comparing Means from Different Populations: Hypothesis Tests An estimator of μ m & μ w is Y m & Y w where Y m and Y w are the sample average for men and women. I To test the null hypothesis, we need to know the distribution of Y m & Y w . Suppose we have samples of n m men and n w women. I Y m is approximately distributed N ( μ m , σ 2 m / n m ) , where σ 2 m is the population variance I Y w is approximately distributed N ( μ w , σ 2 w / n w ) ,where σ 2 w is the population variance....
View
Full
Document
This note was uploaded on 11/20/2011 for the course ECONOMICS 220:322 taught by Professor Otusbo during the Fall '10 term at Rutgers.
 Fall '10
 Otusbo

Click to edit the document details