InThinking Revision Sites

INTHINKING REVISION SITES

Own your learning

Why not also try our independent learning self-study & revision websites for students?

We currenly offer the following DP Sites: Biology, Chemistry, English A Lang & Lit, Maths A&A, Maths A&I, Physics, Spanish B

"The site is great for revising the basic understandings of each topic quickly. Especially since you are able to test yourself at the end of each page and easily see where yo need to improve."

"It is life saving... I am passing IB because of this site!"

Basic (limited access) subscriptions are FREE. Check them out at:

www.StudyIB.net

Correlational studies

  • /
  • Psychology textbook/
  • 1. Research in psychology/
  • Quantitative research methods/
  • Correlational studies

One of the confusing terms in psychology is the word "correlation."  Many studies show a correlation between variables, but they are not correlational studies. How do we know the difference when talking about the research method used in a study? 

Correlation defined

Correlation is the measurement of the extent to which pairs of related values of two variables tend to change together or co-vary. If one variable tends to increase with the other variable, it is a positive correlation.  If one variable tends to decrease as the other variable increases, then it is an inverse or negative correlation.

A curvilinear relationship is a type of relationship between two variables where when one variable increases, so does the other variable, but only up to a certain point, after which, as one variable continues to increase, the other decreases. If you were to graph this kind of curvilinear relationship, you will come up with an inverted-U.

The other type of curvilinear relationship is one where when one variable increases, the other decreases up to a certain point, after which, both variables increase together. This will give you a U-shaped curve.

When we talk about research methods, we usually talk about experimental methods and correlational methods. Correlational methods find a relationship between two variables.  The following table summarizes the difference between experimental and correlational methods.

Experimental vs correlational research

Experimental

  • Used to test cause-and-effect relationships between variables.
  • An independent variable is manipulated and a dependent variable is measured.
  • Extraneous variables are controlled so that they do not influence the variable being measured.
  • High internal validity allows us to draw conclusions about causality.

Correlational

  • Used to test the association between variables.
  • Variables are only observed with no manipulation by the researcher.
  • Limited control is used, so other variables may play a role in the relationship.
  • High external validity; you can generalize your conclusions to other populations or settings.

What is a "correlational study?"

When discussing correlational studies on Paper 3, remember that a correlational study should have no manipulation by the researcher and it must yield statistical results.  The most common way that we obtain data for a "correlational study" is by using questionnaires and/or surveys.  Another data collection technique is the use of psychometric tests - e.g. IQ tests, measures of depressive symptoms, and tests of attitudes.

Data is usually plotted on a scatterplot and the line-of-best-fit is determined.  This is done through a statistical process called regression analysis. 

The strength of the relationship is measured by carrying out a Spearman's rho rank correlation (non-parametric test) or a Pearson's r (a parametric test).  The statistical calculation will be between -1 and +1, where -1 would be an inverse or negative correlation and +1 would be a positive correlation.

Exam tip

One of the errors that students often make is assuming that if a study finds a correlation between two conditions, it is automatically a "correlational study."  Most studies show a correlation (relationship) between variables, so the concept of correlation can be a bit confusing.

Think about Loftus and Palmer (1974).  The study is clearly experimental.  However, the researchers concluded that there was a correlation between the intensity of the verb and the size of the estimate - in other words, a positive correlation.  However, the study is still experimental as the IV was manipulated.

And what if you were giving a questionnaire to students in your school about how they felt about the level of stress and support in your program? You might find that first-year students overall reported less stress than those that were in the higher grades.  You might also find that there was more concern about social stress than academic stress.  However, these are trends that you pull out of the questionnaire (or an interview).  This is what we call an inductive content analysis.  In other words, there is no statistical measurement that is being pulled from the questionnaires; instead, the researcher is interpreting the data and drawing conclusions about the different groups.  So, although the research may see a correlation - that is, it appears that the older students seem more stressed than the younger students - there is no statistical analysis.  This study would be classified as an interview (or questionnaire) and not as a "correlational study."

For your IB exams, remember that correlational studies are a quantitative approach to studying behaviour.

Research designs