Correlation, Correlational

Studies, and its methods

 Mariah Zeah T. Inosanto, RPm

 Correlations & correlation
studies/research
 Correlation studies are used by psychologists to find if there is
a systematic and consistent relationship between two variables.
 A psychologist may observe that there appears to be a
relationship between height and shoe size.
 This observation may be based on a small sample of people.
 To be sure that there is a real and consistent relationship
between height and shoe size they may decide to conduct a
correlational study.
 The goal of correlational research is to describe the
relationship between variables and to measure the strength of
the relationship.
 According to Creswell, correlational research designs
are used by investigators to describe and measure the
degree of relationship between two or more variables
or sets of scores.
 A procedure in which subjects’ scores on two
variables are simply measured, without manipulation
of any variables, to determine whether there is a
relationship.
 Correlational research examines the relationship
between two or more non manipulated variables.
 Definitions of Correlation
 To identify the relationships between two or more variables
 Relationship the range of score on one variable
is associated with the range of score of the other variable

 Correlation (correlation coefficient)

 How well does A predict B
 Positive versus negative correlation
 Strength of the correlation
 -1.0 to +1.0
 Characteristics
 Variables cannot be manipulated

 Cannot prove a causal relationship

 Only examine the possibilities that one

variable might cause something to happen
 Purpose
 Help us to understand related events,
conditions and behaviours : explanatory
studies
 To make predictions of how one variable
might predict another : prediction studies
 Variables used : i) predictor variable
ii)criterion variable
 WHEN DO WE USE CD?
 When we want to see if there is a relationship
between variables or to predict an outcome.
important NOTE:
 Correlation can be positive or negative.
 There is no perfect 1:1 relationship between items
 Correlations cannot tell us the cause of any
relationship.
What is a correlational analysis?
 A correlational analysis looks for an
association between two variables called co-
variables.
 The strength and direction of an association
between two variables is measured.
 The direction of correlations can be
categorized into one of these three: Positive
correlation, (+) Negative correlation, (-)
 Zero correlation, (0)
 3 characteristics
 A correlation describes three characteristics of
a relationship.
 The direction (positive / negative)of the
relationship.
 The form (linear/ nonlinear) of the
relationship.
 The consistency or strength (magnitude) of the
relationship.
 Direction
 In a positive relationship, there is a tendency
for two variables to change in the same
direction.
 In a negative relationship, there is a tendency
for two variables to change in opposite
directions.
Scatter Plot
Examples of positive and
negative relationships
 2 forms of correlation
 Linear correlation
Data points in the scatter plot tend to cluster around
a straight line. The size of increase in Y is
consistently predictable (not accurately).
(height and age)- Pearson

 Monotonic (nonlinear) correlation

The relationship is consistent and predictable, but
not linear.
(practice & Performance) Spearman
2 forms of correlation
2 forms of correlation
 Correlational Design
= a study that assesses the extent to which two
variables are related
 Defines the relationship in quantitative terms
 Correlational (“co-related”)

When one variable changes in value, what

happens to the other variable?
 Types of Correlation Design
 The two primary correlation designs:
 1.THE EXPLANATORY/explanation
DESIGN
 2.THE PREDICTION DESIGN
 THE EXPLANATION DESIGN
 Other names of this designs:
• 'relational' research (Cohen & Manion, 1994, p.123)
• 'accounting-for-variance studies' (Punch, 1998, p.78)
• 'explanatory' research (Fraenkel & Wallen, 2000, p.
360)
 Is a correlational design in which we are
interested in the extent to which two/more
variables co-vary.
 Consists of a simple association between two
or more variables
 Characteristics
• we correlate two/more variables
• we collect data at one point in time
• we analyze all participants as a single group
• we obtain at least 2 scores for each individual
in the group (one for each variable)
• we report the use of the correlation statistical
test in the data analysis
• we make interpretations/draw conclusions from
the statistical test results.
 THE PREDICTION DESIGN
 Seek to anticipate outcomes by using certain variables as
predictors.
 Purpose = to identify predictor variables that will predict an
outcome or criterion.
 Will report correlations using the correlation statistical test;
may include advanced statistical procedures.
 Characteristics:
 • typically include the word 'prediction' in the title (might also
be in the purpose statement/research questions).
 • typically measure the predictor variable(s) at one point in
time and the criterion variable at a later point in time.
 • forecast future performance.
 Types of Correlational Studies
 There are several ways to collect data in an effort to show a
correlation between variables. The three most common types
of correlation studies:
 Naturalistic Observation is when a researcher collects data
by observing subjects in their natural environment without
interfering or interacting with them in any way. This type of
observation is commonly used when lab experimentation is not
possible, feasible or ethical.
 An example may be that a researcher wants to see if there if
there is correlation between class participation and grades by
observing the amount of participation by subjects in a
classroom. This method can be time-consuming but offers the
advantage of being assured that the subjects are behaving
normally.
 Survey Research is done by gathering information from a
random selection of subjects through the use of mail surveys,
email or internet surveys, or interviews. Survey research is
relatively simple to perform once the survey questions have
been developed and the researcher can reach a large number of
potential subjects quickly. The drawbacks are that the
response rate can be low and there is no guarantee that the
subjects are being honest.
 An example of survey research that is testing for a correlation
could be a researcher who is looking for a correlation between
home ownership and education level by surveying home
owners and asking about their education level.
 Archival Research involves analyzing data that has
previously been collected by others and looking for
correlations. The researcher does not have control over
the data or how it was gathered, however, the
researcher may have access to large amounts of data
with relatively little effort and often the data is free.
 For example, a researcher may examine the crime
statistics of several neighborhoods to see if there is
any correlation with crime and a sluggish housing
market in particular areas.
 Statistical Techniques
 Researchers use several statistical techniques to look for
correlations in the data collected through these types of
studies. While this module does not allow for an in-depth
discussion of all of the various statistical techniques used in
correlational studies, following is a list of the commonly used
analyses:
 The most common statistical test is the calculation of the
correlation coefficient (r), as discussed in the previous
module in this series. This is a bivariate correlation analysis
that is a measure of the strength of the relationship between
two variables. There are several different correlation
coefficient calculations and the types of calculation used
depends on the data type. The Pearson Correlation Coefficient
is the most common.
 Regression analysis allows for the analysis of more than just two
variables. It used to examine one or more independent variables
(multiple variables) to predict a single dependent variable or
outcome. For example, a researcher may be looking at a the monthly
discretionary spending of families (dependent variable) and looking for
correlations with other variables such as the number of children,
income, college education, and size of home (the independent
variables). The regression analysis is commonly used to look for linear
relationships (linear regression analysis), but there are other forms as
well. The regression analysis is used to develop predictions.
 Path Analysis is an extension of regression analysis for more than a
single dependent variable or outcome. This allows for testing of more
complex theoretical models
 Canonical correlation analysis is used to examine the possible
correlation between two different linear sets of variables. For example,
the researcher may examine the presence of two variables – diagnosis
of clinical depression and recent traumatic life events – on those that
attempted suicide.
 Correlation Example
Is there a relationship between self-esteem and GPA?

1. Need to have different levels of my first variable:

self-esteem

Very high self-esteem -------- ?

Moderately high self-esteem--?
Average self-esteem -----------?
Moderately low self-esteem --?
Very low self-esteem ----------?
 Correlation Example
Raw Data:
Self-esteem score GPA
Tim 42 3.8
Bart 10 1.4
Kelsey 15 2.5
Kim 22 3.1
Etc.
 Correlation Example
See scatterplot of data

Self-esteem and GPA data

3.5

2.5
GPA

2 Series1

1.5

0.5

0
0 5 10 15 20 25 30 35 40 45
self-esteem
 Direction of Correlation
 Scatterplot showed a positive correlation
 As one variable increased, the second variable also increased
 As self-esteem goes up, academic achievement also goes up
 Think of some examples of positively correlated variables

 Negative (inverse) correlation

 As on variable increases, the second variable decreases (i.e. one gets
bigger, the other gets smaller)
 As amount of alcohol intake increases, motor control decreases
 Think of examples of negatively correlated variables

= direction of the correlation

 Strength of Correlation
How strongly related are the two variables of
interest?
 the “sloppiness” of association
 Degree of accuracy with which you can make a
prediction about 2nd variable given value of the
first variable
 Ranges from -1 to 1
 -1 and 1 are very strong (perfect) correlations
 0 is no correlation; no relationship
Correlation – strength and direction
 Correlation Example
 High Self-esteem and GPA

Does (A) lead to (B)? Or is the other way around? Or, are
there other factors that lead to both (A) and (B)?

 Two independent carefully conducted studies found that there

is no causal relationship between these two factors. They are
correlated because both of them are correlated to some other
factors: intelligence and family social status.

 **Correlations do NOT tell us that one variable CAUSES the

other variable.
 Correlational research
 Strengths
 Can study a broad range of variables
 Can look at multiple variables at one time
 Large samples are easily obtained
 Weaknesses
 Relationships established are associational, not causal
 Individuals not studies in-depth
 Potential problems with reliability and validity of self-
report measures
Correlational Studies
Samples

The connectedness to
nature scale: A measure of
individuals' feeling in community
with nature.
 Ego-integrity
versus ego-dispair: The effect of "accepting
the past" on
depression in older women. International
Journal of Aging
and Human Development
 Personal
philosophy and personal achievement: Belief
in free will
predicts better job performance. Social
Psychological and
Personality Science, 1, 43-50.