Statistical Analysis
Statistical analysis was performed using the mixed model and t-test procedure of SAS (SAS, 1998). A completely
randomized, repeated measure design was used to analyze the production and exterior egg quality data
for the 10 experimental periods of the whole production trial. Compound symmetry with heterogeneous variance
across periods, which allows for unequal variance across periods, proved to be the most accurate method
available for the data. Differences between means were determined using the least squares differences test.
Plumage condition and physiological response parameter were analyzed using the t-tests procedure. Mortality
data were analyzed using PROC FREQ (SAS, 1998).
Unless otherwise stated, the level of significance was
assessed at P < 0.05.