Split Split Plot Design Calculator
Split split plot ANOVA with three error strata. Free online. F tests, CV percent and post-hoc options.
When to use it
Use when three factors are randomised at three different scales: main plot (hardest to randomise, e.g. irrigation), sub plot (e.g. variety), sub-sub plot (easiest to randomise, e.g. fertiliser dose). Generates three error terms, one per stratum.
When NOT to use it
Do not use when all three factors can be randomised at the same scale; a three-factor factorial RBD has more power for every effect. Do not use when df at the main-plot stratum become trivially small (a 3 by 3 by 3 with only 2 reps gives 2 main-plot error df).
What you get
Three-tier ANOVA: Block, A, Error a, B, A x B, Error b, C, A x C, B x C, A x B x C, Error c. Three F tests using the appropriate error each time; three CD values; three CV percents; post-hoc letter display per significant effect with the correct error term.
How to interpret the output
Sub-sub-plot factor C and its interactions are tested most precisely; main-plot factor A least precisely. Higher-order interactions are tested with Error c. The hierarchical randomization is what creates the three error terms; deviating from it invalidates the analysis.
Common pitfalls
- Mixing the three error terms for post-hoc.
- Forgetting that randomization happens three times: A in block, B in main plot, C in sub plot.
- Reporting one CV percent (the design has three error strata).
Try it in StatVeda
The Split-Split-Plot Design engine runs entirely in the browser. No signup, no install, no data sent to a server. Paste your data, hit Run, copy the output.
Open Split-Split-Plot DesignReferences
- Cochran, W. G. and Cox, G. M. (1957). Experimental Designs, 2nd edition. John Wiley and Sons, New York.
- Gomez, K. A. and Gomez, A. A. (1984). Statistical Procedures for Agricultural Research. John Wiley and Sons, New York.