"This is the most important thing to remember about degrees of freedom: IF ALL THE DENOMINATOR DEGREES OF FREEDOM IN YOUR F-TESTS ARE BIGGER THAN ∼ 25 (no matter what your covariance struc- ture is or which DF option is used) THEN IT DOES NOT REALLY MATTER WHICH DF OPTION IS USED."

Unbalanced data are a common problem in plant research based on designed experiments. Such data are often conveniently analysed using linear mixed models. Recent developments in mixed model theory have been implemented in major packages. This paper describes the use of the mixed procedure of the SAS System for the analysis of designed experiments. Special emphasis is given to the specification of options as depending on the assumed mixed model and on the unbalancedness in the data. In addition, we consider a compact representation of multiple comparisons for unbalanced data (letter display). Two small data sets are used to exemplify the methods.