26.12.2014 Views

Clinical Biochemistry of Domestic Animals (Sixth Edition) - UMK ...

Clinical Biochemistry of Domestic Animals (Sixth Edition) - UMK ...

Clinical Biochemistry of Domestic Animals (Sixth Edition) - UMK ...

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

22<br />

Chapter | 1 Concepts <strong>of</strong> Normality in <strong>Clinical</strong> <strong>Biochemistry</strong><br />

Estimated Marginal Means<br />

1. Age<br />

Estimates<br />

Measure: count<br />

95% Confidence Interval<br />

Age<br />

Mean Std. Error Lower Bound Upper Bound<br />

infant 53.333 .540 52.089 54.578<br />

adult 49.067 .540 47.822 50.311<br />

2. Cocktail<br />

Measure: count<br />

Estimates<br />

95% Confidence Interval<br />

Cocktail<br />

Mean Std. Error Lower Bound Upper Bound<br />

1 42.300 1.138 39.676 44.924<br />

2 51.100 .557 49.816 52.384<br />

3 60.200 .771 58.421 61.979<br />

Measure: count<br />

Pairwise Comparisons<br />

(I) cocktail (J) cocktail Mean<br />

Difference<br />

(IJ)<br />

95% Confidence Interval<br />

for Difference a<br />

Std. Error Sig. a Lower Bound Upper Bound<br />

1 2 8.800* 1.517 .001 13.374 4.226<br />

3 17.900* 1.606 .000 22.744 13.056<br />

2 1 8.800* 1.517 .001 4.226 13.374<br />

3 9.100* .640 .000 11.031 7.169<br />

3 1 17.900* 1.606 .000 13.056 22.744<br />

2 9.100* .640 .000 7.169 11.031<br />

Based on estimated marginal means<br />

* The mean difference is significant at the .05 level.<br />

a Adjustment for multiple comparisons: Bonferroni.<br />

FIGURE 1-15 (Continued).<br />

as those given previously for the example <strong>of</strong> the basic<br />

repeated measures design with the following additions:<br />

1. In the Repeated Measures dialog box, age is<br />

added as a between subjects factor by moving “ age ” into<br />

the Between-Subjects Factor(s): box.<br />

2. In the Repeated Measures: Options dialog box,<br />

both the repeated measures factor, here cocktail , and the<br />

between subjects factor, here age , are moved from the<br />

Factor(s) and Factor Interactions: box to the Display<br />

Means for: box for requesting options such as the display<br />

<strong>of</strong> descriptive statistics.<br />

3. For between subject factors having more than 2<br />

categories, pairwise multiple comparisons <strong>of</strong> means can<br />

be obtained by hitting the Post-Hoc... tab, which opens the<br />

Repeated Measures Post Hoc Multiple Comparisons<br />

for Observe... dialog box. In this dialog box all desired<br />

between subject factors can be moved from the Factor(s):<br />

box to the Post Hoc Test for: box and the desired pairwise<br />

multiple comparisons procedure(s) selected.<br />

A partial printout <strong>of</strong> the SPSS output for the example<br />

is presented in Figure 1-15 . Cocktail ( COCKTAIL ),<br />

the within subject main effect, is highly significant<br />

( p 0.0005), age ( AGE ), the between subject main effect,<br />

is also highly significant ( p 0.001), but the interaction<br />

between cocktail and age ( COCKTAIL * AGE ) is nonsignificant<br />

( p 0.177).

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

Saved successfully!

Ooh no, something went wrong!