multiple comparisons using R

Page 128

MULTIPLE COMPARISONS UNDER HETEROSCEDASTICITY Simultaneous Multiple

Fit:

Confidence

Comparisons

aov(formula

of

Means:

= elevel

Linear

Tukey

Contrasts

data

=

alpha)

level

Hypotheses:

Estimate med - short == 0 0.4342 long - short == 0 1.1888 long - med == 0 0.1546 R>

Intervals

~ alength,

Quantile = 2.31 95% family-wise confidence

117

lwr -0.4158 -0.0452 -0.3314

upr 1.3441 2.4221 1.8406

summary(alpha.mc) Simultaneous

Multiple

Fit:

Comparisons

aov(formula

Linear

Tests of

Means:

= elevel

General Tukey

~ alength,

Linear

Hypotheses

Contrasts

data

=

alpha)

Hypotheses:

Estimate med - short == 0 0.434 long - short == 0 1.189 long - med == 0 0.155 Signif. (Adjusted

for

codes: 0 p values

Std.

'***' 0.001 reported —

Error 0.384 0.520 0.458 '**' 0.01 single-step

t value 1.13 2.28 1.65 '*'

Pr(>\t\) 0.492 0.061 . 0.221 0.05 '.' method)

0.1

' ' 1

F r o m t h i s o u t p u t w e c o n c l u d e t h a t t h e r e is n o significant difference b e t w e e n a n y c o m b i n a t i o n of t h e t h r e e allele lengths. L o o k i n g a t F i g u r e 4.13, however, t h e v a r i a n c e h o m o g e n e i t y a s s u m p t i o n is questionable a n d one m i g h t challenge t h e v a l i d i t y of t h e s e r e s u l t s . O n e m a y argue t h a t a s a n d w i c h e s t i m a t e is m o r e a p p r o p r i a t e i n t h i s s i t u a t i o n . B a s e d o n t h e r e s u l t s f r o m S e c t i o n 3.2, we use the s a n d w i c h f u n c t i o n f r o m t h e s a n d w i c h package (Zeileis 2 0 0 6 ) , w h i c h provides a h e t e r o s c e d a s t i c i t y - c o n s i s t e n t e s t i m a t e of t h e c o v a r i a n c e m a t r i x . T h e v c o v a r g u m e n t of g l h t c a n b e u s e d to specify the alternative estimate,


Issuu converts static files into: digital portfolios, online yearbooks, online catalogs, digital photo albums and more. Sign up and create your flipbook.