Scribd
Upload
23 views27 pages

Chp4 Final

This document discusses various non-experimental research designs, including quasi-experimental designs, correlational designs, causal modeling, and ex-post facto designs. It provides examples and explanations of each design. Quasi-experiments resemble experiments but lack random assignment. Correlational designs measure relationships between variables without manipulation. Causal modeling represents causal relationships mathematically. Ex-post facto designs examine pre-existing variables' effects without manipulation.

Uploaded by

Nikko Jhon Coronel
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
23 views27 pages

Chp4 Final

This document discusses various non-experimental research designs, including quasi-experimental designs, correlational designs, causal modeling, and ex-post facto designs. It provides examples and explanations of each design. Quasi-experiments resemble experiments but lack random assignment. Correlational designs measure relationships between variables without manipulation. Causal modeling represents causal relationships mathematically. Ex-post facto designs examine pre-existing variables' effects without manipulation.

Uploaded by

Nikko Jhon Coronel
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 27

LECTURE

Survey Research
Constructing Surveys
Measuring Responses
Important Considerations for Survey Items
Collecting Survey Data
Evaluating Surveys and Survey Data
Sampling
Probability Sampling
Nonprobability Sampling
Module 4
Non-experimental Designs

Quasi-Experimental
Designs
Correlational Designs
Causal Modeling
Ex-post facto
What does ’quasi” means?
Quasi-experiments superficially resemble experiments
but lack their required manipulation of antecedent
conditions and/or random assignment to conditions.
How do quasi- They may study the effects of preexisting antecedent
experiments differ conditions—life events or subject characteristics—on behavior.

from actual
Example: compare the incidence
experiments? of Alzheimer’s disease in patients
who used ibuprofen since age 50
and those who did not.

W/ IA

W/OUT IA
EXPERIMENTS VS. QUASI-EXPERIMENTS

In experiments, researchers randomly assign We should use quasi-experiments when we cannot


subjects to antecedent conditions that they create. or should not manipulate antecedent
conditions.
An experiment might randomly assign subjects to
either daily ibuprofen or aspirin use, and then Quasi-experiments could study the effect of
measure their incidence of Alzheimer’s. spouse abuse on the frequency of child abuse.
CORRELATIONAL DESIGNS
CORRELATIONAL DESIGNS
Pearson correlation
coefficient
is used to calculate simple
correlations (between two variables)
gathered through surveys (questionnaires and interviews), archival
research (past studies that present the data) and naturalistic
observation (observation of the phenomena as they naturally
happen, without intervening).
Correlational Study: TWIN STUDIES
Biological Basis of Behavior – A Debate on Nature Versus Nurture

https://www.youtube.com/watch?v=IyT2AlzzzQs
In 1990 psychologists Thomas Bouchard Jr. and his associates investigated the
influence our genes have in psychological attributes.
Four properties of correlation

Linearity means how the relationship between


x and y can be plotted as a line (linear
relationship) or a curve (curvilinear
relationship).
Sign refers to whether the correlation
coefficient is positive or negative.

Magnitude is the strength of the correlation


coefficient, ranging from -1 to +1.
Probability is the likelihood of obtaining a
correlation coefficient of this magnitude due to
chance.
Why doesn't correlation prove causation?

Since correlational studies do not create multiple levels of an independent variable and
randomly assign subjects to conditions, they cannot establish causal relationships.
There are three additional reasons that correlations cannot prove causation:

Causal direction Third variable


problem Bidirectional
Since correlations are symmetrical,
A could cause B just as readily as B
causation
A third variable—family
could cause A. conflict—may create the Two variables—insomnia
appearance that insomnia and depression—
Does insomnia cause depression and depression are related to may affect each other.
or does depression cause each other.
insomnia?

Why doesn't correlation prove causation?


SIMPLE vs PARTIAL vs MULTIPLE
CORRELATION

Capital + profit (advertisement cost is controlled) Correlation between capital + profit + advertisement cost
When should we compute a partial
correlation?
Sample Scenario:
A researcher wants to know the relationship between height & weight of her
participants of the study
We should compute a partial correlation
when we want to hold one variable (gender)
constant to measure its influence on a
correlation between two other variables
(height and weight).

We want to “partial out” some variables


Partial correlation:if we want to calculate the correlation between height and
weight while holding constant the effect of gender on the correlation
When do researchers use multiple
correlation?

Researchers use multiple correlation (R)


when they want to know whether there is a
relationship among three or more variables.
Example: we could measure age, television
watching, and aggression levels and find that
R = +.71.
When do researchers use multiple
regression?

Researchers use multiple regression to


predict behavior measured by one variable
based on scores on two or more other variables.
We could estimate aggression level using age
and television watching as predictor variables.
CAUSAL MODELING
Causal models are mathematical models
representing causal relationships within an
individual system or population.

Causal models incorporate the idea of multiple causality,


Causal that is, there can be more than one cause for any
particular effect.

modeling The best-known form of causal modelling is path


analysis, which was originally developed in genetics, but
was adopted as a technique in the 1960s by American
sociologists such as Otis Dudley Duncan.

Most causal modelling is associated with survey research


Causal
modeling
Causal models incorporate the idea of multiple causality,
that is, there can be more than one cause for any particular
effect.

For example, how prognosis may be related to intervention


given, stressor and sex.
Causal
modeling
In longitudinal designs, the same group of subjects is measured
at different points of time to determine the effect of time on
behavior.
In cross-sectional studies, subjects at different developmental
stages (classes) are compared at the same point in time.
Causal
modeling
In pretest/posttest designs, a researcher measures
behavior before and after an event.
Solomon 4-group design

Causal
modeling
This variation on a pretest/posttest design includes four conditions:
(1) a group that received the pretest, treatment and posttest
(2) a nonequivalent control group that received only the pretest and posttest
(3) a group that received the treatment and a posttest
(4) a group that only received the posttest
EX-POST FACTO DESIGN
Quasi-Experimental Designs

Ex post facto
Ex post facto means “after the fact.”
A researcher examines the effects of already existing
subject variables (like gender or personality type),
but does not manipulate them.

Examining how an independent variable, present


prior to the study in the participants, affects a
dependent variable.

Examples:
What is the effect of day care on the social skills of children?
Effects of Marital Problems on Children

You might also like