As a researcher, I often tell people about experimental findings and the explanations behind them… and every once in a while someone will say, “I have an example that disproves that theory!” or something like, “Well, my brother’s kid’s sister’s husband’s nephew doesn’t do that!” And in my head, I always think… “n=1.”
In research terminology, the variable n stands for the number of subjects in the study. A study with just one person just isn’t very powerful. So one contrary example doesn’t “disprove” a finding. After all, typical studies base their conclusions on a sample… but I should say, in developmental psych, the samples still tend to be rather small. But back to my original point — one single experience can vary widely — however, the empirical “truth” is more likely to be found in a chorus of common experience. So the larger the n, the more likely you’ll approximate the “truth” about the population. (As a statistics aside, this is also part of the assumption underlying the whole of inferential statistics… and it has its own set of problems but that’s another blog.)
Now that little Mo has been born into our household, he is my highly salient n of 1. In my mind, Mo’s experience will be weighted quite heavily relative to the other babies I’ve read about in studies. This is the unfortunate consequence of being a cogsci mom.
So here is Mo at 7 wks old, doing his rendition of contingency learning — if kick, then mobile moves!