This preview shows pages 1–4. 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: Paired ttest Earlier tested 1 = 2 using two inde pendent random samples { X 1 ,...,X n 1 } and { Y 1 ,...,Y n 2 } from N ( 1 , 2 1 ) ,N ( 2 , 2 2 ) populations. Basis: X Y N 1 2 , 2 1 n 1 + 2 2 n 2 2sample Z or 2sample t , depending on whether variances were known or not. 1 Variance both populations added. In crease in noise so harder to reject H because standard deviation denom inator reduces magnitude of Z or T ra tio(equivalently wider confidence inter vals). As a result, statistical test may not be sensitive to small differences in signal 1 2 . Sometimes experiment can be designed in advance to reduce variation in the population by pairing observations and taking differences before analysing. 2 Example 4.63, p 267 . Test whether knowl edge of basic statistical concepts improved af ter a short course given to engineers....
View
Full
Document
This note was uploaded on 01/03/2012 for the course EE 1244 taught by Professor Drera during the Fall '10 term at Conestoga.
 Fall '10
 drera

Click to edit the document details