LectureOct24

# LectureOct24 - BME 423 Lecture Notes - Oct. 21, 2008...

This preview shows pages 1–8. Sign up to view the full content.

Confidence Intervals (CI) BME 423 Lecture Notes - Oct. 21, 2008 I. Size of Treatment Effect: Difference of two Means II. What Does Confidence Mean? III. CI to Test Hypothesis IV. CI for the Population Mean V. Size of Treatment Effect: Difference of two Proportions VI. CI for the Population Proportion Glantz Chapt. 7 pp 219-244

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
I. Size of Treatment Effect: Difference of two Means To test null hypothesis of no difference – t Test 12 22 XX t s s nn = + () tt α ν > Reject null hypothesis: P < 2 ν= +− t s = 2 112 2 (1 ) ( 1 ) 2 ns n s s −+ =
( ) ( ) () 12 1 2 XX t s μ −− = Suppose two samples are drawn from populations with different means? 0.05 t ν 0.05 t 95% of the values of t fall in the interval: 0.05 0.05 tt t −< < 0.05 t to 0.05 t

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
( ) ( ) () 12 1 2 XX t s μ −− = Suppose two samples are drawn from populations with different means? Solve for 0.05 0.05 tt t ν −< < ( ) ( ) 1 2 0.05 0.05 s μμ < ( ) ( ) 1 2 0.05 1 2 1 2 0.05 t s t s νμ < <−+ 95% CI for ( )
( ) () ( ) 12 1 2 XX t s t s αα νμ μ ν −− < <−+ In General: 100(1- α) % CI for ( )

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

## This note was uploaded on 12/02/2008 for the course BME 423 taught by Professor D'argenio during the Fall '06 term at USC.

### Page1 / 13

LectureOct24 - BME 423 Lecture Notes - Oct. 21, 2008...

This preview shows document pages 1 - 8. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online