# Lecture11A - 30 May 2003 Biostatistics 6650-L11A 1 Todays...

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

30 May 2003 Biostatistics 6650--L11A 1

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

View Full Document
30 May 2003 Biostatistics 6650--L11A 2 Today’s Schedule ANOVA general/assumptions example
30 May 2003 Biostatistics 6650--L11A 3 ANOVA: general What if we want to compare means for more than 2 groups? Could use multiple 2-sample t-tests • 5 groups…. . 5 C 2 or 10 pairwise tests if groups have common variance, is there a more efficient method? ANOVA(analysis of variance) is the usual solution Null Hypothesis: – 3 groups: H o : 0 1 =0 2 =0 3 – k groups: H o : 0 1 =0 2 =…= μ k Alternative Hypothesis: – H 1 : At least one mean is different from the others

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

View Full Document
30 May 2003 Biostatistics 6650--L11A 4 ANOVA: general ANOVA is very powerful tool. Can analyze a wide variety of study designs. Completely randomized designs effect of exercise, diet, insulin on HbA1C in DMII patients effect of fish-oil dose(none, 3, 6, 9g/day) on renal function » estimate linear dose effects Two-way ANOVA effect of treatment and sacrifice time on tumor growth in mice Factorial designs Ex: 2 3 factorial--effect of calorie restriction(none,20%), exercise(yes,no), and weight(normal, overweight) on energy expenditure; study all 8 combinations, allows us to examine main effects and interactions
30 May 2003 Biostatistics 6650--L11A 5 ANOVA: general ANOVA works by partitioning the total variation in the data into pieces from various sources

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

View Full Document
30 May 2003 Biostatistics 6650--L11A 6 ANOVA: general • Notation: x ij = j th observation in the i th group Group 1 Group 2 Group 3 x 11 =3 x 21 =6 x 31 =9 x 12 =5 x 22 =1 x 32 =10 x 13 =4 x 23 =7 x 33 =7 x 24 =4 x 34 =8 n 1 =3 n 2 =4 n 3 =4 N=11 =4 =4.5 =8.5 =5.818 1. x 2. x 3. x .. x th i. 1 i 1 1 1 1 is the sample size for group i, i=1,2,. ..,K x = , is the mean for the i group n 1 , is the total sample size x..= is the grand mean N i i n i ij j n K K i ij i i j n x N n x = = = = = ∑ ∑ ∑
30 May 2003 Biostatistics 6650--L11A

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 06/17/2011 for the course BME 6650 taught by Professor Multipleinstructors during the Spring '03 term at Mayo Clinic College of Medicine.

### Page1 / 19

Lecture11A - 30 May 2003 Biostatistics 6650-L11A 1 Todays...

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

View Full Document
Ask a homework question - tutors are online