Introduction to

Research: Methods and

Process
 Chapter 4
Quantitative Designs

2
What Will You Learn to Do?

• Compare and contrast cross-sectional and

longitudinal studies
• Explain the differences between
nomothetic research and idiographic
research
• Discuss each type of experimental design
and its advantages and disadvantages

3
 Cross-Sectional versus
Longitudinal Studies
• Once the study purpose is established you
need to determine the frequency of data
collection
– How will we collect the data?
– How often will participants come together to
provide data?

4
 Cross-Sectional Studies
• In these types of studies data is only
collected once (i.e., “snapshot”)
• Benefits: Can collect data from large
numbers of people, less costly, take a
relatively short amount of time, and
convenient
• Limitations: Impossible to see if participants
changes their perspectives or opinions over
time or whether their mood or demeanor on
the data collection data represents their true
perspective, assessing cause and effect is
impossible

5
 Longitudinal Studies

• In these types of studies data is collected

at different points in time (i.e., waves)
• Benefits: Ability to study cause and effect
• Limitations: Require a lot of time, costly,
require more people to gather, clean,
analyze and interpret data, and attrition
(drop out of participants over time)

6
Types of Longitudinal Studies:
Panel Studies
• Longitudinal Studies that follow and
accumulate data from the same participants
over a period of time
• Group of participants is called a panel
• Useful to understand topics like aging or
disease development
• Limitations include cost, time
• Example: The Panel Study of Income
Dynamics (PSID) [national study of socio-
ecomics and health over lifetime]

7
Types of Longitudinal Studies:
Trend Studies
• Longitudinal Studies that collect data at
different points in time from different
participants of the same population
• To capture trends of a specific population
on a particular issue or concern
• Useful as comparison studies: Flemish
students’ experiences

8
Types of Longitudinal Studies:
Trend Studies

9
Types of Longitudinal Studies:
Cohort Studies
• Longitudinal Studies that collect data from
the same cohort of people over time
• An example a researcher could define a
cohort as people who have started college
at the same time, though these people
may differ on other characteristics (e.g.,
gender, age, etc.)

10
Types of Longitudinal Studies:
Cohort Studies

11
 Causality in Research

• We often attempt to establish a causal

relationship between our variables of
interest

• For example: 2012 Spanish fiscal

limitation to deduct interest expenses vs
Leverage

12
 Nomothetic Research

• This type of research aims to arrive at a

causal relationship that can be applied
across populations at large
• Quantitative & Qualitative
• Requires establishing three criteria
– #1: Correlation
– #2: Time order People with a higher
– #3: Non-Spuriousness education level will likely
earn a higher salary

13
 Causal Criteria #1:
Correlation
• Correlation means that the variables you
are studying are related to each other (i.e.,
changes in the independent variable go
hand in hand with the dependent variable)
• Establishes an association but is not
sufficient to prove one causes the other
The need to buy something Correlation
The amount of money available Casuality?

14
 Causal Criteria #2:
Time Order
• Time order determines the actual order of
changes from one variable to another
• If changes in the independent variable
happen first, then changes in the
dependent variable, then the criterion of
time order is fulfilled
New detergents 1st
Clothes are cleaner 2nd

15
 Causal Criteria #3: Non-
Spuriousness
• A relationship that is explained away by a
third variable that you may or may not
have thought about
It requires that alternative explanations for the observed relationship
between two variables be ruled out. This is termed non-spuriousness,
which simply means “not false.”
A spurious or false relationship exists when what appears to be an
association between the two variables is actually caused by a third
extraneous variable.
Classic examples of spuriousness include the relationship
between children’s shoe sizes and their academic knowledge:

• as shoe size increases so does knowledge,

• but of course both are also strongly related to age.

16
 Experimental Designs

• An experimental design refers to the

presence of a test, experiment,
intervention, or some type of manipulation
happening at the time of data collection
• For example: How will a person’s interest
in a topic increase or decrease if they are
given a pamphlet with information about
the topic

17
 Experimental Designs:
Requirements
• Presence of a control and experimental
group
• Random assignment of participants
• Pre- and post-testing (i.e., collection of
data before and after the experiment)

18
 Experimental Designs:
Experimental and Control Groups
• Experimental: Group of participants
undergoing some form of experimentation
(e.g., training, taking a test, and taking a
drug)
• Control Group: Group of participants who
does everything the experimental group
does but does not receive any test, drug,
intervention, or manipulation

19
 Experimental Designs:
Random Assignment
• Random assignment of our participants to
the experimental and control group
• Random assignment ensures that
characteristics of each group that might
influence our study are evenly distributed
between the experimental and control
condition
In some cases even the researcher does not know
which participants are assigned to which group. This is
called a double-blind study.
20
 Experimental Designs:
Pre- and Post-testing
• Measurement of participant characteristics
before and after conducting an experiment
• The pre- and the posttest must be the
same otherwise we cannot measure
change over time

21
Experimental Designs

22
Experimental Designs

23
 Solomon Four-Group
Experimental Design
• Type of experimental design that helps to
minimize measurement error
• Rationale is that when people take a test,
taking the test will someone give them insight
into what is being studied
• This can bias a study
• Design uses two experimental groups and
two control groups; however, only one
experimental and one control group take the
pretest

24
Solomon Four-Group
Experimental Design

25
Quasi-Experimental Designs

• Experimental designs can be difficult,

costly, and time consuming, so
researchers sometimes utilize quasi-
experimental designs
• Similar to experimental designs there is
some type of intervention, testing,
modification, or manipulation of results;
however, they are more relaxed about
random assignment

26
Quasi-Experimental Designs

Randomized One-Group Posttest-Only Design

27
Quasi-Experimental Designs
Randomized Posttest-Only Control Group Design

28
Quasi-Experimental Designs
Non-Random posttests only control group design

29
Quasi-Experimental Designs
Non-Random pretest posttest control group design

30
Quasi-Experimental Designs
Non-Random One-Group Pretest Posttest Design

31
32