Correlational Research

Survey Research
Group 1
Adef Silfia
Siti Kamaliyah
Tesha Fersty Fadhilah
CORRELATIONAL
RESEARCH
DEFINITION AND PURPOSE
 Correlational research involves collecting data to
determine whether and to what degree a relation exists
between two or more variables. The degree of relation
is expressed as a correlation coefficient.

 The purpose of a correlational study may be to

determine relations among variables (i.e., a relationship
study) or to use these relations to make predictions (i.e.,
a prediction study). Correlational studies typically
investigate a number of variables believed
THE CORRELATIONAL
RESEARCH PROCESS
Problem Selection
 Correlational studies may be designed either to
determine whether and how a set of variables are
related or to test hypotheses regarding expected
relations. The variables to be correlated should be
selected on the basis of some rationale suggested
by theory or experience.
Participant and Instrument Selection
 A common, minimally accepted sample size for a
correlational study is 30 participants. If validity
and reliability are low, a larger sample is needed
because errors of measurement may mask a true
relation. The higher the validity and reliability of
the variables to be correlated, the smaller the
sample can be, but not fewer than 30.
Design and Procedure
 In the basic correlational design, scores for two (or
more) variables of interest are obtained for each
member of a selected sample, and the paired
scores are correlated.
Data Analysis and Interpretation
 A correlation coefficient is a decimal number between –1.00
and 1.00. It describes both the size and direction of the
relation between two variables. If the correlation coefficient
is near 0.00, the variables are not related.

 A correlation coefficient near 1.00 indicates that the

variables are strongly and positively related. A person with a
high score on one variable is likely to have a high score on
the other variable, and a person with a low score on one is
likely to have a low score on the other. An increase on one
variable is associated with an increase on the other.
RELATIONSHIP STUDIES
 A relationship study is conducted to gain insight
into the variables or factors that are related to a
complex variable, such as academic achievement,
motivation, or self-concept. Such studies give
direction to subsequent causal–comparative and
experimental studies.
Data Collection
 In a relationship study, the researcher first
identifies the variables to be related. A smaller
number of carefully selected variables is preferred
to a large number of carelessly selected variables.
Data Analysis and Interpretation
 In a relationship study, the scores for one variable
are correlated with the scores for another variable,
or scores for a number of variables are correlated
with some particular variable of primary interest.
PREDICTION STUDIES
 A prediction study is an attempt to determine
which of a number of variables are most highly
related to the criterion variable. Prediction studies
are often conducted to facilitate decision making
about individuals or to aid in the selection of
individuals.
Data Collection
 The major difference in data collection procedures
for a prediction study and a relationship study is that
in a prediction study the predictor variables are
generally obtained earlier than the criterion variable,
whereas in a relationship study all variables are
collected within a relatively short period of time.
After the strength of the predictor variable is
established, the predictive relation is tested with a
new group of participants to determine how well it
predicts for other groups.
Data Analysis and Interpretation
 Data analysis in prediction studies involves
correlating each predictor variable with the
criterion variable
 SURVEY
RESEARCH
 Survey Research: Definition

Dornyei : surveys are especially well suited for asking factual

questions, behavior questions, and attitudinal questions.

Creswell : survey research designs are procedures in quantitative

research in which investigators administer a survey to a sample or
to the entire population of people to describe the attitudes, options,
behaviors, or characteristics of the population.

Gay : survey research involves collecting data to test hypothesis or

to answer research questions about people’s opinion on some topic
or issues.
 Types of Survey Research

Time of Data Collection

Longitudinal Cross-Sectional

Trend Attitudes and Practices

Group Comparison
Cohort

Community Needs

Panel Program Evaluation

National Assessment
Longitudinal Surveys

Longitudinal surveys are extremely useful for studying the dynamics of

a topic or issue over time, and data are collected at two or more times.

1. A trend survey examines changes over time in a similar particular

population with the different sample to find out the tendency a
phenomenon.

2. A cohort survey involves one population selected at a particular time

period.

3. A panel survey involves a sample in which the same individuals are

studied over time.
vCross-Sectional Surveys
Cross-sectional designs are effective for providing a snapshot of the current
behaviors, attitudes, and beliefs in a population. This design also has the advantage of
providing data relatively quickly—you do not have to wait for years.

Attitudes and Practices

Group Comparison

Community Needs

Program Evaluation

National Assessment
 Conducting Survey Research

 Conducting a Questionnaire Study

 Stating the Problem
The problem or topic studied and the contents
of the questionnaire must be of sufficient
significance both to motivate potential
respondents to respond and to justify the
research effort in the first place.
  Constructing the Questionnaire

As a general guideline, a questionnaire should be attractive, brief,

and easy to respond to. Respondents are turned off by sloppy,
crowded, misspelled, and lengthy questionnaires, especially ones
that require long written responses to each question

Here the guidelines for constructing a questionnaire:

•Make the questionnaire attractive and brief.
• Know what information you need and why.
• Include only items that relate to your study’s objectives.
• Collect demographic information, if needed.
• Define or explain ambiguous terms.
• Focus items on a single topic or idea.
• Word questions as clearly as possible.
• Avoid leading questions
• Use examples if item format is unusual.
• Avoid or carefully word items that are potentially controversial or embarrassing.
  Pilot Testing Questionnaire
Pilot testing the questionnaire provides information about
deficiencies and suggestions for improvement. The end product
of the pilot test will be a revised instrument ready to be mailed to
the already selected research participants.

 Cover Letter
The cover letter should explain the purpose of the study
• Emphasizing its importance and significance.
• Give the respondent a good reason for cooperating Include a mailing
address, phone number, or email address where you can be reached in
case potential respondents want to ask questions.
Sample Cover
Letter
Administering the Questionnaire

• Selecting participants
• Distributing the questionnaire
• Conducting follow-up activity
• Dealing with nonresponse
• Tabulating questionnaire responses
• Analyzing results
 Administering the Questionnaire
Selecting
Participants

The selected research participants

must be able and willing to provide the
desired information to the researcher.

Individuals who possess the desired

information but are not sufficiently
interested or for whom the topic under
study has little meaning are not likely to
respond.
 Administering the Questionnaire
Distributing the
Questionnaire
Method Advantages Disadvantages
Mail Inexpensive Response rate may be small
Can be confidential or anonymous Cannot probe, explain, or follow up
Easy to score most items items
Standardized items and procedures Limited to respondents who can read
Possibility of response sets

Email Speedy results Not everyone has email

Easy to target respondents Possibility of multiple replies from
Other advantages same as mail single participant
Other disadvantages same as mail

Telephone High response rates Requires phone number lists

Quick data collection Difficult to get in-depth data
Can reach a range of locations and Administrators must be trained
respondents
Methods Advantages Disadvantages
Personal Efficient when respondents are closely Time-consuming
administrati situated Administrators must be trained
on
Interview Can probe, follow up, and explain Time-consuming
questions No anonymity
Usually high return rate Possible interviewer bias
May be recorded for later transcription Complex scoring of unstructured items
and Administrators must be trained
analysis
Flexibility of use
 Administering the Questionnaire
Conducting Follow-up
Activities
An initial follow-up strategy: Send out a reminder postcard

Full-scale follow-up activities: Send out the second

questionnaire

The rule of thumb for your survey response rate, based on a good sample, is 50%.

If those responding were quite similar to the total sample,

How to deal with generalizability would be fine
nonresponse?
Randomly selecting a small sample of non-respondents
and interviewing them
 Administering the Questionnaire
Tabulating Questionnaire
Responses
Closed-ended questions

Open-ended questions
Using scannable answer sheet
Code answers according to
patterns in the responses provided
Entering the responses one by
one into a computer spreadsheet
 Administering the Questionnaire
Analyzing
The total sample size Results The response rate for
each item
The overall percentage
of returns

The simplest way to present the results is

to indicate the percentage of respondents
who selected each alternative for each item

A better way to report is to group items into

clusters that address the same issue and
develop total scores across an item cluster.
 Let’s have a great discussion!
“The aim of an argument or discussion
should not be victory, but progress”