Definition
The duplication/repetition of an experiment, either in its entirety or parts of it, using a new set of experimental units/material each time. Each new repitition is called a 'replicate'. Replication involves performing the trial each time from scratch and measuring the outcome, as opposed to taking multiple measurements at each trial using the same sample or different Samples. The Replicates are performed in random order, as are the trials in the original design. Replication helps measure the variation inherent in the experiment (experimental error), which can then be used to test the fit of the model.
Advantages of replication:
1. Averages out the effect of extreme observations, reducing the variability in the experimental results and increasing the precision of the effect estimates.
2. Increases the power of the test, i.e., the likelihood of detecting an effect of a given size.
3. Facilitates the Lack-of-Fit test by allowing the partitioning of the Error sum of squares into the Pure error and Lack-of-fit components.
See Also
Design of Experiments (DOE)