by Dr. Janet Waters (revised, 2017)
In general, a correlational study is a quantitative method of research in which you have 2 or more quantitative variables from the same group of participants, & you are trying to determine if there is a relationship (or covariation) between the 2 variables (that is, a similarity in pattern of scores between the two variables, not a difference between their means). Theoretically, any 2 quantitative variables from the same group of participants can be correlated (for example, midterm scores & final exam scores, or midterm scores and number of body piercings!) as long as you have numerical scores on these variables from the same participants; however, it is usually a waste of time to collect & analyze data when there is little reason to think these two variables would be related to each other.
Research Ethics for Correlational Research: As with all research methods, make sure your research proposal has been approved by your instructor or supervisor before conducting your correlational study. Your research proposal must include how you plan to gather data on your participants & a copy of your consent form. Always go over the consent form with your participants before they sign, and ensure their anonymity and confidentiality is protected in your research process (within the legal requirements).
The Correlational Coefficient: Try to have 30 or more participants; this is important to increase the validity of the statistical finding.
Both positive & negative correlations occur & are equally valuable. An example of a positive correlation is a well-established one between the number of hours of study & exam scores. An example of a negative correlation would be the number of interruptions from phone calls & texts while studying & exam scores. A perfect correlation would be expressed as r = +1.0 & -1.0, while no correlation would be r = 0. Perfect correlations would almost never occur; expect to see correlations much less than + or - 1.0. Although correlations can't prove a causal relationship, they can be used for prediction, to support a theory, or to measure test-retest reliability.
You may collect your data through testing, for example scores on a knowledge test (an exam or math test, etc.), or through psychological tests, numerical responses on surveys & questionnaires, etc., such as an interval scale (e.g. rate your stress on a scale from 1 to 7). Even archival data can be used (e.g. Kindergarten grades) as long as it is in a numerical form.
With the use of Excel, calculating correlations is probably the easiest data to analyze. In Excel, set up three columns: Participant #, Variable 1 (e.g. hours of study), & Variable 2 (e.g. exam scores). Then enter your data in these columns. Select a cell for the correlation to appear in & label it. Click "Formulas" on the toolbar at the top, then "More Functions" then "Statistical", then "Pearson". When asked, highlight in turn each of the two columns of data, click "OK", & your correlation will appear. Critical Values tables online or in any statistics textbook can tell you if the correlation is significant, considering the number of participants.
You can also do graphs & scatter plots with Excel, if you would like to depict your data that way (See "Charts").
Use the standard APA style research report. In the Introduction, briefly review past research & theory in your topic question (e.g. summarize current research on stress & academic achievement). Use APA referencing style to cite your sources. Then in the Method section, present a general description of the group of participants (their number, mean age, gender, etc.) in the Participants section, any materials you may have used (e.g. tests, surveys, etc.) in the Materials section, & in the Procedure section, note that your general research strategy was a correlational study, & describe your methods of data collection (e.g. survey, test, etc.).
In the Results section of the report, present your correlation statistic in both a table & in words, & note whether or not it is significant. If you have more than 2 variables to correlate, present a correlational matrix, showing the correlation between each of the variables. In the following example, 4 variables were correlated with each other. The correlation between exam scores & hours of study, for example, is r = +.67, p <.01. This indicates a significant positive relationship between the number of hours of study & subsequent exam scores.
* p < .01
In the Discussion section, relate your results to past or current research & theory you had cited & described in the Introduction. Do note the statistical significance of your findings, & limits to their generalizability. Remember that even if you did not obtain the significant differences you had hoped to, your results are still interesting, & must be explained, with reference to other research & theory.
© Janet Waters (2017)
Capilano University | 2055 Purcell Way, North Vancouver, British Columbia Canada V7J 3H5 Tel: 604.986.1911
Sunshine Coast | 5627 Inlet Avenue, Sechelt, British Columbia Canada V0N 3A0 Tel: 604.885.9310