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: Prediction (Confidence) intervals for new subjects I A 100(1 )% prediction interval for an individual new value of y at x = x p is y t / 2 (Estimated standard error of prediction) or y t / 2 s s 1 + 1 n + ( x p x ) 2 SS xx where t / 2 is based on (n2) degrees of freedom. Problem I Refer again to the drug reaction regression. Predict the reaction time for the next performance of the experiment for a subject with a drug concentration of 4%. Use a 95% prediction interval. Something of less importance I Along with prediction interval for a new subject at x = x p , one can talk about estimating the mean of y in that subpopulation with characteristic (predictor) x p . I The confidence interval is going to be different from the prediction interval because y = s 1 n + ( x p x ) 2 SS xx is different from ( y y ) = s 1 + 1 n + ( x p x ) 2 SS xx Multiple regression I In order to explain that response time, it may be better to consider some other factors instead of just the drug...
View
Full
Document
This note was uploaded on 06/06/2011 for the course STAT 515 taught by Professor Zhao during the Spring '10 term at South Carolina.
 Spring '10
 Zhao
 Degrees Of Freedom, Standard Error

Click to edit the document details