This tutorial is going to teach you about a randomized block design. A randomized block design is a little bit different than other types of designs that we've studied.
A researcher, suppose, wants to identify whether a new acid reflux drug is more effective than the one that's currently available. So he gathers 500 volunteers with acid reflux. Puts the number one on 250 cards, and the number two on another 250. He places them into a hat, mixes them up, has people pull out numbers. Those who received a "one" received a new drug, those selected "two" will receive the old drug. But the problem is, what if men and women respond differently to the drug?
This would be the researcher's original plan. So we start with all these volunteers, men and women, and then we randomly assign them to groups. That would be the old design. And the better design here is called a Block design. So we're not going to do this. We're going to try something different.
What we're going to do instead is first take our large group and break it into smaller subgroups of just men and just women. On my picture we have nine men and 14 women, but we had a lot more in the original description. What we're going to do then is we're going to run the experiments essentially in parallel: one experiment for men and one experiment for women.
We're going to take those men and randomly assign half the men to the treatment and half to the control. We're going to take half the women and assign them to the treatment and assign them to the control. And so it will look like this. Men receiving the treatment, men receiving the control. Women receiving the treatment and women receiving the control.
And what's most important, you might notice, that there are five men receiving treatment and four receiving control. That is just the way it happens sometimes where we don't have exactly equally sized groups. But that's OK.
By doing a Block design rather than a completely randomized design, we can observe differences within the group that we might have missed had we done it with a large group. So for instance, suppose the drug was more effective for women than for men. We would see that in this experiment here. We would see that the drug was effective for women. We would also see that it wasn't effective for men.
Now one minor disadvantage to running a Block design is that you do lose some of the replication that you would have had, had you run it in a large group. So sometimes you need to make your sample size a little bit bigger in order to overcome that. And it might be a little bit harder to draw legitimate conclusions with small groups.
And so to recap, in a Block design, the subjects or experimental units are grouped together by some similar characteristic that you think might affect the outcome. In this example, we use gender. But then you run the experiment in parallel, resulting in two or more separate experiments that run at the same time. And then you can compare the treatments within each of those groups.
And so we talked about a randomized Block design and how it differs from a completely randomized design. Good luck and we'll see you next time.
An experimental design where the subjects are separated into homogenous groups, called blocks, based on some variable we think may affect the outcome of the experiment. We then run the experiment separately within each block.