Hi. This tutorial covers the idea of blinding. So let's first of all take a look at why blinding is needed. So we're going find something called the experimenter effect so when an experimenter, knowing which participants are in the treatment and control group, gives subtle clues to the participant, possibly confounding the response.
So the experimenter effect also occurs when the judgment of an evaluator of the response is influenced for financial or ideological reasons. So if an experimenter is hoping to get certain results from his experiment, due to money or these ideological reasons, they may have some sort of influence in how the participants are responding to specific types of treatments.
So blinding is a way for researchers to eliminate the experimenter effect. So let's define blinding. So blinding is an experimental design technique where some involved in the experiment are prevented from knowing certain information that may lead to biased results. So we're going to prevent either the evaluator or the participant from knowing certain information that might come up in the study.
And there are really two types of blinded experiments. The first one is what we call the single blind experiment. A single blind experiment is an experiment in which participants do not know which treatment they received, whereas a double blind experiment is an experiment in which neither the participant nor the one measuring the response knows which treatment the participant received.
So single blind is only when the participant doesn't know the treatment. Double blind is where the participant and whoever is measuring whatever response variable you have knows which treatment the participant has.
So blinded experiments are often useful in medical studies. So if a patient knows he or she is receiving a high dose medication, they may be more inclined to report a better bill of health. Then if a doctor is trying to show a certain medication is effective, he or she may ignore patient symptoms that may show a medication is ineffective.
So in this first case, it might be important just to do a single blind experiment just so the patient doesn't know, well, am I receiving the high dose or the low dose medication? And in the second case, a double blind experiment might be needed so that neither the patient nor the doctor knows what the patient is receiving. There would just need to be some third party that knows who received which treatment.
There are going to be cases where blinding isn't possible. Let's say you are trying to gauge the effectiveness of two different exercise techniques, maybe swimming versus biking. If you're running an experiment where those are your two treatment groups, it's going to be very hard-- it's going to be impossible to do any sort of blinding because the participant will obviously know if they are in the swim group versus the bike group.
But whenever possible, blinding is a good idea just to eliminate some of those extraneous factors that can pop up. So that is the tutorial on blinding. Thanks for watching.