STAT368 Lecture : Concepts of ANOVA.pdf
Document Summary
The -test studied in the previous chapter does not apply directly when there are more than two means to be compared, but the basic ideas extend in a natural way. Example: we are to investigate the formulation of a new synthetic bre that will be used to make cloth for shirts. 10% - 40% by weight (the one factor is cotton content) and the experimenter chooses 5 levels of this factor: 15%, 20%, 25%, 30%, 35%. There are 5 replicates (complete repetitions of the ex- periment). In a replicate ve shirts, each with a di erent cotton content, are randomly chosen from the ve populations of shirts. The 25 tensile strengths are measured, in random order. This is then a completely randomized design (crd). (why random order?) ; their numerical are labelled 1 values are not important for the analysis. Thus, e. g. , and averages at level are ( = 5 = # of replicates). ( = 1.