Randomness vs. Balance

• Show some pictures with a subliminal cue, and some without, and count how many are correctly recognized.

  Which pictures are shown in which condition?

It is tempting to just randomize things. But if you have twenty trials of two factors (cued and uncued) and you "just randomize" them, it is like flipping a coin twenty times. You will not necessarily then end up with the same numbers of trials in each condition! (This is called the "gambler's fallacy".)

Because having even numbers of your various conditions is often important for doing statistical testing of your data, you should "balance" your design rather than purely "randomizing" it. This means that you should make sure that all the various permutations work out evenly:

• Each subject should see half cued and half uncued pictures.
• Each picture should be cued for half the subjects and uncued for the other half.