Вы находитесь на странице: 1из 23

The Correlational

Approach
MSA
Introduction

 There are several types of research studies.


 All research studies can be classified under
two main categories: the qualitative versus the
quantitative.

08/03/09 Dalia Mostafa 2


Introduction
 The qualitative approach involves the
collection of narrative data in order to gain
insights into a phenomenon of interest; data
analysis includes the coding of the data and
production of verbal synthesis (inductive
process).
e.g. Historical Research
08/03/09 Dalia Mostafa 3
Introduction

 The quantitative approaches involve the


collection of numerical data in order to
explain, predict and/or control a phenomenon
of interest; data analysis is mainly statistical
(deductive process).

08/03/09 Dalia Mostafa 4


Introduction

 Such as:
-The Correlational Research
-The Experimental Research

08/03/09 Dalia Mostafa 5


The Correlational Research

Definition:
 The correlational research attempts to
determine whether and to what degree, a
relationship exists between two or more
quantifiable (numerical) variables.

08/03/09 Dalia Mostafa 6


The Correlational Research

 You collect data on at least two variables for


the same group of subjects and then calculate a
correlation coefficient between the two
variables.

08/03/09 Dalia Mostafa 7


What is a Correlation Coefficient?

A correlation coefficient is a number between


-1 and 1 which measures the degree to which
two variables are linearly related.
 It is represented by the letter (r).

08/03/09 Dalia Mostafa 8


What is a Correlation Coefficient?

 If there is perfect linear relationship with positive


slope between the two variables, we have a
correlation coefficient of 1.
r=1
 If there is positive correlation, whenever one
variable has a high (low) value, so does the other.

08/03/09 Dalia Mostafa 9


What is a Correlation Coefficient?
 If there is a perfect linear relationship with
negative slope between the two variables, we
have a correlation coefficient of -1.
r = -1
 If there is negative correlation, whenever one
variable has a high (low) value, the other has a
low (high) value.

08/03/09 Dalia Mostafa 10


What is a Correlation Coefficient?

 A correlation coefficient of 0 means that there is


no linear relationship between the variables
(null).
r=0

08/03/09 Dalia Mostafa 11


What is a Correlation Coefficient?

 To understand what is a correlation


coefficient, follow these links and move the
curser:
http://noppa5.pc.helsinki.fi/koe/flash/corr/corrx2-en.html
http://noppa5.pc.helsinki.fi/koe/corr/cor7a/cor7a.html

08/03/09 Dalia Mostafa 12


What is a variable?

Variable: a defined characteristic that varies; it


has at least two values and usually more.
 For example, anxiety about writing in a second
language is a variable, because it varies across
students.

08/03/09 Dalia Mostafa 13


What is a measure?

 To assign a value to the degree of anxiety that


students feel, they are given a test (measure)
of writing anxiety.

08/03/09 Dalia Mostafa 14


Examples of Correlational Research
 The relationship between intelligence and self-
esteem
 The relationship between anxiety and
achievement
 The relationship between using an aptitude test
and predicting success in an algebra course
08/03/09 Dalia Mostafa 15
Examples of Correlational Research
 A group of high school students took two tests
that required them to solve analogies to
recognize antonyms (relationship).
 The researchers discovered a correlation
between students’ abilities to complete
analogies correctly and to identify antonyms.
08/03/09 Dalia Mostafa 16
Examples of Correlational Research
 In general, students who were good at one task
were also good at the other; students weak in
one task were weak in the other.

08/03/09 Dalia Mostafa 17


An Important Note

In correlational research, no attempt is made to


state that one thing causes another, only that
one thing (one variable) is predictable from
the other.

08/03/09 Dalia Mostafa 18


Validity
 A measure (test) is valid if it measures what it is
intended to measure.
 To demonstrate the validity of a test we want to
show that scores on the test correlate highly with
some external measure of what the test
purportedly measures.
 This external measure is referred to as the
criterion.
08/03/09 Dalia Mostafa 19
Reliability

 The reliability of a measure refers to the


accuracy or consistency of the measurement.
 There are many sources of error that can
reduce the accuracy of measurements.

08/03/09 Dalia Mostafa 20


Reliability
 In such cases, it is important to provide
evidence that the observations or ratings are
reliable.
 This is accomplished by determining
interrater reliability, sometimes called
interobserver reliability or interjudge
reliability.

08/03/09 Dalia Mostafa 21


Reliability
 To do this, two or more persons rate the same
phenomenon.
 Their ratings are then compared to see how
well they agree with one another.

08/03/09 Dalia Mostafa 22


Recap
The Qualitative & Quantitative approaches
The definition of the correlational research
The definition of the correlational coefficient: Positive,
Negative & Null
What is a variable?
What is a measure?
The validity & reliability of a correlational research

08/03/09 Dalia Mostafa 23

Вам также может понравиться