Correlational Studies Looking for Relationships

29
Research Methods in Psychology
doing
2
learn
by
DESIGNING SUR VEY
RESEARCH How do various
people feel about whether gay
men and lesbians should have the right
to legally marry? To appreciate the difficulties of survey research, try writing a
question about this issue that you think
is clear enough and unbiased enough to
generate a valid portrait of people’s
views. Then ask some friends whether or
not they agree that it would be a good
survey question, and why.
Correlational Studies: Looking for Relationships
correlational studies Research methods that examine relationships between
variables in order to analyze trends, test
predictions, evaluate theories, and suggest new hypotheses.
correlation The degree to which one
variable is related to another.
Data collected from naturalistic observations, case studies, and surveys provide valuable descriptions of behavior and mental processes, but they can do more than that.
The data can also be examined for what they reveal about the relationships between
research variables. For example, fear surveys show that most people have fears, but correlational analysis of those surveys also shows that fear is related to age. Specifically, as
people get older, they tend to have fewer fears (e.g., Kleinknecht, 1991). Correlational
studies examine relationships between variables in order to describe research data
more fully, to test predictions, to evaluate theories, and to suggest new hypotheses about
why people think and act as they do.
Correlation refers to both the strength and the direction of the relationship between
two variables. A positive correlation means that the two variables increase together or
decrease together. A negative correlation means that the variables move in opposite
directions. For example, James Schaefer observed 4,500 customers in 65 bars and found
that the tempo of the jukebox music was negatively correlated with the rate at which
the customers drank alcohol. The slower the tempo, the faster the drinking (Schaefer
et al., 1988). Does this mean that Schaefer could have worn a blindfold and predicted
exactly how fast people were drinking by timing the music? Could he have plugged his
ears and determined the musical tempo just by watching people’s sip rates? No and no,
because the accuracy of predictions made about one variable from knowing the other
depends on the strength of the correlation. Only a perfect correlation between two variables would allow you to predict the exact value of one from a knowledge of the other.
The weaker the correlation, the less one variable can tell you about the other.
Psychologists describe the strength and direction of correlations with a number
called a correlation coefficient, which can range from a high of 1.00 to a low of .00 (see
the “Statistics in Psychological Research” appendix). If the correlation between two variables is positive—if they both move in the same direction—the correlation coefficient
will have a plus sign in front of it. If there is a minus sign, the correlation is negative,
and the two variables will move in opposite directions. The larger the correlation coefficient, the stronger the relationship between the two variables. The strongest possible
relationship is indicated by either 1.00 or 1.00 (see Figure 1.6). A correlation of .00
indicates that there is virtually no relationship between variables.
Correlation coefficients can help to describe the results of correlational research and
evaluate hypotheses, but psychological scientists must be extremely careful when