29.07.2014 Views

ST4241: Design and Analysis of Clinical Trials - The Department of ...

ST4241: Design and Analysis of Clinical Trials - The Department of ...

ST4241: Design and Analysis of Clinical Trials - The Department of ...

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

(ii) Check that, <strong>of</strong> the six pairwise differences a j − a j<br />

′, only the three differences involving<br />

Formulation 3 are statistically significant by the Tukey criterion.<br />

<strong>The</strong> following code is used for the computation:<br />

c12 = c(1,0,0)<br />

c13 = c(0,1,0)<br />

c14 = c(0,0,1)<br />

c23 = c(1,-1,0)<br />

c24 = c(1,0,-1)<br />

c34 = c(0,1,-1)<br />

C = rbind(c12,c13,c14,c23,c24,c34)<br />

l = C%*%b<br />

ss = sqrt( diag( C%*%v%*%t(C)) )<br />

L = l/ss<br />

<strong>The</strong> computed test statistics corresponding the six pairs are:<br />

c12 0.76096856<br />

c13 -5.73428051<br />

c14 0.05461109<br />

c23 6.49524907<br />

c24 0.70635747<br />

c34 -5.78889161<br />

<strong>The</strong> critical value for the statistics using Tukey’s criterion is q 4,8,0.05 / √ 2 = 4.529/ √ 2 =<br />

3.2025. It is seen that c13, c23, c34 are significant.<br />

7

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!