Some variables are manipulated and others are controlled. The greatest advantage with this method is that you can infer cause and effect because of the way the experiment is set up and the way it is controlled. A disadvantage can be your subjects might not behave as naturally as they should. There are two very important types of variables: You must have these two variables in order to have an experiment that demonstrates causality. Variables meaning to vary, something that can be changed.
E.g. time, temperature, height, etc.
Independent variable (IV) – What the experimenter manipulates to see if it affects behavior.
Dependent variable (DV) – The behavior that is measured to see if the IV had an effect.
E.g. you are studying the effects of alcohol on memory. The amount of alcohol is the IV and you are measuring the memory (DV). A good way of thinking about this; the IV is the cause and the DV is the effect.
When an experiment is conducted, usually there is more than one IV and DV. Because conducting research is very time consuming, allowing more than one IV and DV will allow you to collect more data to learn more about human behavior.
E.g. Males age 20, 25, 30, 35 were given 20 words to be recalled. The 20 year old group better. What is the IV?
Age, number of words, or intelligence (IQ)? The only IV in this study is AGE. The researcher is only manipulating the age.
In a study, your IV will be mentioned.
E.g. Subjects were asked to smell spices and researchers recorded the number of sneezes and how long it took.
The IV – types of spices
The DV – number of sneezes and how long it took (2 DVs)
With an experiment, you need at least one IV, one DV, and a control group.
Control group – a group that is used as a standard for comparison. It does not possess the independent variable. The control and experimental groups must be equal in every way expect for the independent variable. There must be some type of bases for comparison to determine if there is a cause and effect relationship. In certain cases you can have more than one control group.
All other groups in the study are called the experimental group(s) and the control group is the standard; void of the independent variable.
E.g. You are looking at the effects of alcohol on memory; there is 2 different kinds of control groups that you can have and you can have 2 scenarios:
- Your control group has nothing to drink. This will not allow your groups to be equal because the control group will be expected to do better on the memory test since they did not receive any alcohol.
- Your control group has a non-alcoholic drink. This group will have some sort of expectations about their level of intoxication and in turn will have the same expectations as the group who received alcohol. This group has been given a placebo.
Ideally, you would want your groups to have similar expectations. In this case, the placebo is the non-alcoholic drink.
Placebo control group is a special type of control group that is used to control for subjects’ expectations that could affect results.
If the control group is given a placebo, then it’s assumed that all groups (control and experimental) are equal in terms of their expectation, and so any differences in behavior (e.g. memory) can be attributed to the actual amount of alcohol consumed, and not to expectation.
An important kind of variable is the confounding variable. It is a variable that interferes with the results of the study. It affects the dependent variable; therefore you are not sure whether the effects are caused by the independent variable or the confounding variable. Confounding variables change with the independent variable as it is unintentionally effecting the experiment.
E.g. Regarding the alcohol example, the independent variable is the amount of alcohol consumed, the dependent variable is the performance on the memory task, and a confounding variable may be underlying alcohol tolerance.
E.g. You want to study the effects of study time and grades on a test. You are going to have 3 different groups.
Group 1 will not study
Group 2 will study for 5 hours
Group 3 will study for 10 hours
You’ll then measure what the average grade of each group is.
Independent variable – hours of study
Dependent variable – grades
Control group – group 1
Experimental group – groups 2 and 3
The group studying for 10 hours is doing the same as the group who did not study! Is there a problem?
You discovered that the group who studied for 10 hours did not get any sleep the night prior to the test because of studying. Is their grade caused by how much they studied or is the grade caused by how much they slept? You don’t know. What you have is called a confounding variable (CV).