Q. What are control experiments?
A. ‘Control’ experiments are tests in which factors aren’t deliberately changed and they are done in tandem with ‘controlled variable’ experiments which are tests with one factor (the independent variable) is deliberately changed.
Q. Why bother with control experiments?
A. In real life, things don’t always go to plan. Let’s consider the example of growing slime mould.
Suppose I decide to grow the slime mould in a plastic pot. I put the slime on oat flakes and wait for it to grow. However, after a couple of days no growth. Why not? Well, it turns out I forgot to add a source of moisture. So, I hypothesize it didn’t grow due to lack of water. To test my hypothesis, I do a controlled experiment. In this experiment, I set up 10 identical pots both containing slime, the only difference is 5 pots conatain a blob of agar (to provide moisture). After a couple of days, four pots with agar have slime growing in them and no growth in dry pots. Therefore, my hypothesis is probably correct!
Q. Five pots had water but slime only grew in four! What happened to the fifth pot?
A. The slime mould may have been dead, unhealthy, slow to grow or became infected. In experiments with living things there may be variations in setup which are hard to see. To overcome this potential for variation, we need a large sample size and, ideally, repeated experiments several times. It would be time consuming (and boring) for any participant to repeats lots of experiments. However, if many participants share their results the data set quickly becomes large enough to take out random variation. In other words, having more samples and repeating experiments more times makes it less likely that we will reach a wrong conclusion because of random variation.