Correlational Studies in Psychology: Examples, Advantages & Types
This lesson describes correlational studies, or the measurement of the relationship between variables. These variables can occur in a variety of settings and are not controlled by the researcher.
We also recommend watching Correlational Research: Definition, Purpose & Examples and Case Study Design: Definition, Advantages & Disadvantages
What is Correlational Research?
In psychology, correlational research can be used as the first step before an experiment begins. It can also be used if experiments cannot be conducted. It determines if a relationship exists between two or more variables, and if so to what degree the relationship occurs. There are three common types of correlational research.
1) Natural observation is observing and recording variables in a natural environment, without interfering. For example, you might observe student class attendance in order to predict grade success. This type of research is often used when lab experimentation is not possible or ethical. However, it can be time consuming and does not allow variable control.
2) Survey research gathers information via surveys or questionnaires by choosing a random sample of participants. For example, if you've ever filled out a satisfaction survey on a new product in a mall, you've participated in survey research. Those surveys are used to predict whether a new item will be successful. Survey research is quick and convenient, but participants can affect the outcomes in a variety of ways.
3) Lastly, archival research analyzes data collected by others. For example, you might look at archive records to predict how crime statistics influenced local economics. Archive research is often free. However, large amounts of data are needed in order to see any type of significant relationship. Researchers cannot control the data or how it was gathered.
Relationship Between Variables
Correlational studies can suggest a relationship exists between variables. However, it cannot prove that one variable causes a change in another. If there are no associations between the variables tested, then there are no causal connections between them. Take, for example, the experiment in which you observe students with low attendance to see if affects their grades. If those students get low grades, this suggests there is a causal relationship between a lack of class attendance and academic performance. However, with only two variables available, it cannot be proved that these students will get better grades if they show up more consistently.
Additionally, correlation does not mean causation. Correlation does not indicate a cause-effect relationship because there may be confounding factors. Confounding factors are variables that influence the independent variable, as well as the dependent variable. Following the previous example, low attendance does not always cause poor grades because there might be confounding factors. For example, the student might not like the subject, or could have a learning disability that affects their performance.
The degree of the relationship is viewed as a coefficient of correlation, or the linear dependence of variables. The correlation coefficient of -1 indicates a weak/negative relationship. A +1 indicates a strong/positive relationship, while a 0 indicates no relationship at all. If correlation coefficients are strong, then it can be assumed that one variable can predict another variable (e.g., SAT scores and student success).
Ace Your Next Test & Improve your Grades
As a member, you'll get unlimited access to over 5,000+ video lessons in Math, English, Science, History, and more. Plus, get practice tests, quizzes, and personalized coaching to help you succeed. Learn More
Search Our Courses
Education Portal Video Lessons
- More affordable than tutoring
- All major high school and college subjects
- Unlimited access to all 8,500+ video Lessons
- Study on your own schedule