4

From Wikipedia:

a mixed-design analysis of variance model (also known as a split-plot ANOVA) is used to test for differences between two or more independent groups whilst subjecting participants to repeated measures. Thus, in a mixed-design ANOVA model, one factor (a fixed effects factor) is a between-subjects variable and the other (a random effects factor) is a within-subjects variable. Thus, overall, the model is a type of mixed effect model.

My questions:

  1. What relation is between mixed design and split-plot design? Is a split-plot design a within-subject design, or a between-subject design, or both?
  2. Why is the model of a mixed design a mixed effect model? Which input variable has random effect and which input variable has fixed effect?
amoeba
  • 93,463
  • 28
  • 275
  • 317
Tim
  • 1
  • 29
  • 102
  • 189

1 Answers1

6

I'm sure terminology varies, but I think it's fair to say that a split-plot design (where there are two or more treatments imposed at different hierarchical levels) is a specific example of a mixed design. Mixed effect models (also called multilevel or hierarchical models; repeated measures are another special case) are so-called because they include both random and fixed effect terms.

I would say that split-plot designs are "both" between- and within-subject designs, because (at least) one treatment is between- and (at least) one treatment is within-subject.

In order to answer the other question one would need a more specific example.

Ben Bolker
  • 34,308
  • 2
  • 93
  • 126
  • +1 but I think one can answer Q2 as well: both between- and within- factors are treated as fixed, whereas the plot id (aka subject id) is a grouping variable that is treated as random. – amoeba May 13 '19 at 15:23