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 DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Statistics 511: Statistical Methods Dr. Levine Purdue University Spring 2011 Lecture 12: Confidence Intervals Devore: Section 7.17.2 March, 2011 Page 1 Statistics 511: Statistical Methods Dr. Levine Purdue University Spring 2011 Motivation • Why do we need a confidence interval? Because with each new sample we have a new parameter estimate (e.g. new sample mean).... • Which one do we choose? We do not know the true mean μ and do not know how close each one is to μ . • Thus, we want to have some degree of precision reported together with an estimate • Suppose our ¯ X = 10 . We want to say something like...”With probability 95% the true mean is between 9 and 11 ” March, 2011 Page 2 Statistics 511: Statistical Methods Dr. Levine Purdue University Spring 2011 Basic properties of Confidence Intervals • Consider normal population distribution with known σ • We want to estimate unknown μ • The problem is purely illustrative; in practice, mean is usually known before the variance (standard deviation) • We know that ¯ X is normally distributed with mean μ and standard deviation σ/ √ n . March, 2011 Page 3 Statistics 511: Statistical Methods Dr. Levine Purdue University Spring 2011 • Because the area under the normal curve between 1 . 96 and 1 . 96 is . 95 , we have P ( 1 . 96 ≤ Z ≤ 1 . 96) = P 1 . 96 ≤ ¯ X μ σ/ √ n ≤ 1 . 96 = 0 . 95 • Simple algebra tells us that P ¯ X 1 . 96 σ √ n < μ < ¯ X + 1 . 96 σ √ n = 0 . 95 March, 2011 Page 4 Statistics 511: Statistical Methods Dr. Levine Purdue University Spring 2011 The meaning of the confidence interval • The event in parentheses above is a random interval with the left endpoint ¯ X 1 . 96 σ √ n and right endpoint ¯ X + 1 . 96 σ √ n . It is centered at sample mean ¯ X . • For a given sample X 1 = x 1 ,...,X n = x n , we compute the observed sample mean ¯ x and substitute it in the definition of our random interval instead of ¯ X . The resulting fixed interval is called 95% confidence interval (CI). • The usual way to express it is either to say that ¯ x 1 . 96 σ √ n , ¯ x + 1 . 96 σ √ n is a 95% CI for μ March, 2011 Page 5 Statistics 511: Statistical Methods Dr. Levine Purdue University Spring 2011 • Alternatively, we say that ¯ x 1 . 96 σ √ n ≤ μ ≤ ¯ x + 1 . 96 σ √ n with 95% • A more concise expression is ¯ x ± 1 . 96 σ √ n March, 2011 Page 6 Statistics 511: Statistical Methods...
View
Full Document
 Spring '08
 BUD
 Statistics, Normal Distribution, Standard Deviation, Purdue University, Dr. Levine, Purdue University Spring

Click to edit the document details