Devin has taught psychology and has a master's degree in clinical forensic psychology. He is working on his PhD.
Definitions in Correlational Research
Your brain can do some really cool things. For instance, you learn that a particular jingle means the ice cream trucks are nearby. The louder the jingle, the closer it is. And if you were lucky enough to have several types of ice cream trucks, you will recognize which jingle goes with which ice cream truck.
The world is full of things where if thing A happens, then there is a good chance that thing B will happen. If thing A is the jingle, then there is a good chance that thing B, the ice cream truck, is close by. We can also make things more complicated by thing A being the loudness of the jingle and thing B being the distance to the ice cream truck. As the loudness increases, the distance shrinks. As the distance increases, the loudness goes down.
This is kind of a silly example, but it's an example of how you naturally correlate one event with another. A correlation is simply defined as a relationship between two variables. The whole purpose of using correlations in research is to figure out which variables are connected. I'm also going to start referring to the things as variables; it's a more scientific name. This simple definition is the basis of several statistical tests that result in a correlation coefficient, defined as a numerical representation of the strength and direction of a relationship.
Correlation research is looking for variables that seem to interact with each other, so that when you can see one changing, you have an idea of how the other will change. This often entails the researcher using variables that they can't control. For example, a researcher may be interested in studying the preference for ice cream based on age. If we cannot assign age, does that mean we have to scrap the whole correlation? Nope!
Since the researcher cannot assign certain variables, this would mean the researcher is performing a quasi-experimental study. A quasi-experimental study is defined as an experiment in which participants are not randomly assigned. There are different techniques for how we might overcome this, and I encourage you to explore this in other lessons.
While we focus on correlation in research, we must also note that the correlation can be positive or negative. Positive correlations mean that as variable A increases, so does variable B. A negative correlation is defined as when variable A increases, variable B will decrease. Please note that I did not say how much the other variable moves when the first variable changes.
When looking for correlations, a researcher will look for patterns - what they have seen happen again and again. A simple pattern known to every teacher, but unfortunately not every student, is the link between studying and grades. The studious student who studies is more likely to score a higher score on their test. Students who don't study much are less likely to score as high as those who do.
You may be sitting there doubting what I've said because you've taken tests before where you didn't study and did just fine. And, there are others who do study and still don't get good grades. This is because there isn't a perfect correlation, or a perfect 1:1 relationship, between the items. There is just too much going on in the real world for this to be a perfect connection. Things like personal talents, distractions, familiarity with the subject and brain stuff make everyone a little different.
This interference in a correlation is known as an extraneous variable, which is simply defined as a variable that is influencing the study. They are something to watch out for when you're looking at correlations because nothing in the math or experiment will say, 'Here it is; this is messing up your experiment.'
The previous example was a good example for a positive correlation, but what about a negative correlation? Sticking with the grades and people, did you ever know that person who did nothing but watch TV? The person who watches too much television usually doesn't do well on their tests. This means as they watch more television, their grades go down. 10 hours of television gets a C, while 30 hours of television gets an F.
However, one issue with this is it's not always clear which caused which. Maybe the person who watches a lot of television got a bad grade on the last test. It is with this in mind that we also have to introduce the idea that correlations do not indicate direction. In this example, we don't know if the bad grade caused the TV watching or the TV watching caused the bad grades.
A correlation is simply defined as a relationship between two variables. Researchers using correlations are looking to see if there is a relationship between two variables. This relationship is represented by a correlation coefficient, defined as a numerical representation of the strength and direction of the relationship.
This relationship can be represented by a positive correlation, meaning that as variable A increases, so does variable B, or a negative correlation, defined as when variable A increases, variable B will decrease. One of the issues of the correlation is that it is not always clear when there is an extraneous variable, which is simply defied as a variable that is influencing the study. Lastly, correlations do not indicate a direction of effect, so you don't know if variable A causes variable B, or vice versa.
Following your completion of this lesson, you'll be able to:
- Characterize correlation, correlation coefficient and extraneous variable
- Differentiate between a positive and a negative correlation
- Provide an explanation of the limitations involved when doing correlational research
To unlock this lesson you must be a Study.com Member.
Create your account
Register to view this lesson
Unlock Your Education
See for yourself why 30 million people use Study.com
Become a Study.com member and start learning now.Become a Member
Already a member? Log InBack