Statistical studies often involve several kinds of experiments: treatment groups, control groups, placebos, and blind and double-blind tests. An experiment is a study that imposes a treatment (or control) to the subjects (participants), controls their environment (for example, restricting their diets, giving them certain dosage levels of a drug or placebo, or asking them to stay awake for a prescribed period of time), and records the responses.
The purpose of most experiments is to pinpoint a cause-and-effect relationship between two factors (such as alcohol consumption and impaired vision; or dosage level of a drug and intensity of side effects). Here are some typical questions that experiments try to answer:
Does taking zinc help reduce the duration of a cold? Some studies show that it does.
Does the shape and position of your pillow affect how well you sleep at night? The Emory Spine Center in Atlanta says yes.
Does shoe heel height affect foot comfort? A study done at UCLA says up to one-inch heels are better than flat soles.
Treatment-group versus control-group tests
Most experiments try to determine whether some type of experimental treatment (or important factor) has a significant effect on an outcome. For example, does zinc help to reduce the length of a cold? Subjects who are chosen to participate in the experiment are typically divided into two groups: a treatment group and a control group. (More than one treatment group is possible.)
The treatment group consists of participants who receive the experimental treatment whose effect is being studied (in this case, zinc tablets).
The control group consists of participants who do not receive the experimental treatment being studied. Instead, they get a placebo (a fake treatment; for example, a sugar pill); a standard, nonexperimental treatment (such as vitamin C, in the zinc study); or no treatment at all, depending on the situation.
In the end, the responses of those in the treatment group are compared with the responses from the control group to look for differences that are statistically significant (unlikely to have occurred just by chance).
Placebo tests
A placebo is a fake treatment, such as a sugar pill. Placebos are given to the control group to account for a psychological phenomenon called the placebo effect, in which patients receiving a fake treatment still report having a response, as if it were the real treatment. For example, after taking a sugar pill a patient experiencing the placebo effect might say, “Yes, I feel better already,” or “Wow, I am starting to feel a bit dizzy.” By measuring the placebo effect in the control group, you can tease out what portion of the reports from the treatment group were due to a real physical effect and what portion were likely due to the placebo effect. (Experimenters assume that the placebo effect affects both the treatment and control groups similarly.)
Blind and double-blind tests
A blind experiment is one in which the subjects who are participating in the study are not aware of whether they’re in the treatment group or the control group. In the zinc example, the vitamin C tablets and the zinc tablets would be made to look exactly alike and patients would not be told which type of pill they were taking. A blind experiment attempts to control for bias on the part of the participants and to ensure that a placebo effect will not affect only the treatment group. (If the example study was not blind, those not taking zinc may not bother to take their pills or may believe they won’t get better because they know they’re not taking the good stuff.)
A double-blind experiment controls for potential bias on the part of both the patients and the researchers. Neither the patients nor the researchers collecting the data know which subjects received the treatment and which didn’t. So who does know what’s going on as far as who gets what treatment? Typically a third party (someone not otherwise involved in the experiment) puts together the pieces independently, and only he knows which subjects received the treatment and which did not. A double-blind study is best, because even though researchers may claim to be unbiased, they often have a special interest in the results — otherwise they wouldn’t be doing the study!