Many times in research, a psychologist wants to look at two or more groups to see which condition works best. In this lesson, we’ll look at some of the strengths and weaknesses of the between-subjects design and how to form equivalent groups.
Lou is a psychologist who is interested in how room temperature affects how people perform on a test.
He gathers participants and gives them a basic reading and math test in one of two rooms. One room is set to 50 degrees, and the other is set to 85 degrees. Will the heat or the cold produce better test scores? That’s what Lou wants to figure out.There are many elements of experimental design. One common experimental design method is a between-subjects design, which is when two or more separate groups are compared. For example, Lou has two groups of participants, one in the 50 degree room and one in the 85 degree room.
He is comparing the scores of the two groups to see if the cold room or the hot room will produce better test scores.In a between-subjects design, the goal is to see if one treatment is better than the other. For example, it might involve comparing teaching methods or treatments for anxiety or other mental illness. For each subject, one score is gathered.
Each subject’s score is averaged with the other subjects in their treatment group. Finally, the average scores for each of the groups are compared to see if one treatment is more effective than the other. Let’s look closer at the strengths and limitations of between-subjects design and look at the importance and types of equivalent groups.
Strengths & Limitations
So why should Lou go with a between-subjects design for his study, as opposed to another type of experimental design? There are several strengths of a between-subjects design. One major strength is that the scores of the participants are not influenced by other factors.
For example, what if Lou decided to use the same participants for both conditions? He gives a person a test in a 50 degree room and then he gives them a similar test in an 85 degree room.The problem there is that the person might do better in the 85 degree room not because of the heat, but because they’ve practiced with the first test. Or they might do worse because they are tired from taking the first test. Either way, their scores are being influenced by a factor other than the temperature.
In a between-subjects design, though, each participant is only taking one test, and therefore their test scores aren’t being influenced by practice or fatigue. Lou is more likely to be able to see the variability between conditions without all the noise of the other factors. There are some limitations, though. The most major limitation is that of individual differences. What if the people in the 50 degree room are just smarter than the ones in the 85 degree room? In that case, it might appear as though the 50 degree room produces better results. In reality, though, the individual differences of the participants are a major factor in the results.
There are ways to mitigate the problem of individual differences. One thing that Lou can do is to randomly assign subjects to groups. For example, he could flip a coin to see if a participant will take the test in a 50 degree room or in an 85 degree room. By doing this, he is much less likely to end up with all the smart people in one room.Another way that he could prevent issues of individual differences in his study is through matched groups.
This is when he matches each subject up with another subject from the other group based on a specific criteria. For example, Lou could match people based on their IQ. If subject A has an IQ of 110 and is in the 50 degree room, Lou would find another subject with an IQ of 110 and put them in the 85 degree room.
This type of matching is done for every participant until Lou has two equivalent groups.Finally, Lou could hold his groups constant. For example, if Lou only chose participants that had an IQ between 100 and 110, his groups would naturally be equivalent on the factor of IQ.
Between-subjects design in research involves comparing different groups of people to see the impact of different treatments. One strength of a between-subjects design is that it reduces the impact of variables, like practice or fatigue of testing. But the most major weakness of between-subjects design is the danger that the groups might not be equivalent.
However, there are three things that researchers can do to improve the chances of equivalent groups: random assignment, matched groups, and holding groups constant.
Following this lesson, you’ll have the ability to:
- Define between-subjects design and identify its goal
- Describe some strengths of this type of design
- Identify the weaknesses in this type of design
- Explain how to mitigate the major weakness through random assignment, matched groups, and holding groups constant