Download Independent variable

“How do I love thee?
Let me count the ways…”
-Elizabeth Barrett Browning
Social Psychology as a Science
Chapter 9
Social Psychology as a Science
 Where do we find research ideas?
 Personal Experience - Observation
 Theory
 Previous Research
 News reports
 Literature and poetry
 Everywhere!
Social Psychology as a Science
 Narrowing the research question?
 Descriptive questions
 Measuring how often an event occurs
 For example: How often do people report falling in love?
 Causal questions
 Identifying why some event occurs
 For example: Why do some people report being deeper in
love than others?
“How do I love thee? Let me count the ways.
I love thee to the depth and breadth and height
My soul can reach, when feeling out of sight…”
 Increasing the precision of the question
 Do people in long distance relationships report feeling more in love
than those in close relationships?
Social Psychology as a Science
 What makes a “good” research question?
 One that defines its theoretical (conceptual) variables in
measurable terms.
 Variables must be operationally defined (actual variables).
 Definition never fully captures all of the conceptual variable.
Conceptual
Variable
Love
Number of
Text
Messages
Actual
Variable
Social Psychology as a Science
Amount of Conceptual variable accounted for by the
actual variable is called Criterion Relevance
(overlap of love and text messaging).
Aspects of the Theoretical variable not
accounted for by the operationally
defined actual variable are called
Criterion Deficiency.
Conceptual
Variable
Love
Aspects of the operationally defined
variable that are unrelated to the
theoretical variable is called
Criterion Contamination.
Number of
Text
Messages
Actual
Variable
Social Psychology as a Science
Amount of Conceptual variable accounted for by the
actual variable is called Criterion Relevance
(overlap of love and text messaging).
Aspects of the Theoretical variable not
accounted for by the operationally
defined actual variable are called
Criterion Deficiency.
Conceptual
Variable
Long
Distance
Aspects of the operationally defined
variable that are unrelated to the
theoretical variable is called
Criterion Contamination.
Number of
Driving
Minutes apart
Actual
Variable
Social Psychology as a Science
 Selecting a design (Experimental)

Independent variable (IV)




Must have at least two levels/conditions
Is manipulated by the experimenter
Is expected to have an effect on the participant’s
behavior
Dependent Variable (DV)
Must be measurable (a number)
 Is a measure of the participant’s response to the IV
 For example: The number of text messages sent per day

Social Psychology as a Science
 Selecting a design (Experimental)

Control Variable (CV)

Any variable that potentially might have an effect on
the participant’s behavior that the experimenter is not
interested in assessing.
 Held constant (one level)
 For example: Only right handed people are participants

Hypothesis: a statement that makes a prediction
about how the IV will affect the DV.


Therefore, both variables should be present in the
statement.
The statement should be in the form of a prediction.
Social Psychology as a Science
 Selecting a design (Experimental)

Random assignment

Participants should be randomly assigned to each
level of IV (in a between-subjects design).
 Different people are placed in each level of the IV.

Can be a simple randomization procedure.
 (two levels of the IV… flip a coin)

Minimizes the chance of some types of confounding.
 (e.g., too many highly social people in one level of the IV)
 Any single trait has an equal probability to be in a level.
 Works well with large sample sizes.
Social Psychology as a Science
 Selecting a design (Experimental)

How do we find participants for our study?

Samples of convenience
 (e.g., college students from a single class)
 May share a common trait – problematic

Random sample
 A subset of people drawn from a population using a
random procedure
 Can be problematic as well (e.g., unrepresentative)

Representative random sample
 Key traits are identified and the subset of people drawn
from the population still maintain the proportion of the key
traits in the populations (e.g., ratio of males to females).
Social Psychology as a Science
(Knowledge Check)
Preschool school children were randomly divided into two groups. Children in one
group were asked to wait in a room by themselves while they watched a short film.
This film depicted adults engaging in violent behaviors directed at an inflatable
clown doll (the Bobo doll). These behaviors included hitting the doll with a wooden
mallet, throwing the doll in the air, and sitting astride the doll while punching it in
the nose. Children in the other group were asked to sit alone in a room but
watched a film of the adult playing with the doll in a nonviolent manner. After
viewing the films, children in both groups were allowed to play by themselves in a
room full of toys. These toys included those that they had seen the adult models
play with. The children were observed at play for several minutes. Those children
who had watched the violent films were much more likely to engage in violent
behaviors than were the children who had watched the nonviolent films.



What is the Independent variable/s in this design?
What is the dependent variable/s in this design?
What control variables can you identify or think the experimenters should have
used in the study?
Social Psychology as a Science
 Selecting a design (Quasi-experimental)




Appears similar to an experimental design
A design where we cannot randomly assign to the levels of the IV
Therefore, levels of the IV are selected rather than manipulated
Examples of quasi-experimental variables:





Person characteristics: sex, IQ, personality traits
Environmental conditions: distance living apart, heat, snow storm
Social group affiliation: church, sorority, country club
Colorado Blizzard babies: compare birthrates of cities affected by
storm and those not affected (nonequivalent control group)
Difficulty employing proper controls

(e.g., finding the proper nonequivalent control group)
Social Psychology as a Science
 Selecting a design (Correlational)

Assesses the relationship between two variables

Strength of the relationship (-1.00 to 1.00)
Strong correlation: 0.86
 Weak correlation: 0.09


Direction of the relationship (positive or negative)
Positive: as one variable increases, the other increases, or as
one variable decreases, the other decreases
 Negative: as one variable increases, the other decreases


Example: As the number of bystanders increases, the
amount of helping a person receives decreases (-0.86)
Scatter Plots of Correlations
 Selecting a design (Correlational)
Social Psychology as a Science
(Knowledge Check)
It was reported in a research study that ownership of a dog may be
therapeutic (Friedman, 1979). One-year follow-up studies were
conducted on a group of 112 coronary patients after their release
from the hospital. They were divided into two groups: patients who
were dog owners and patients who were not. When the death rates
of the two groups were compared, a surprising difference emerged.
Fully 30 of 53 (57%) dog owners survived at least a year, whereas
only 28 of the 59 (47%) nonowners enjoyed a one-year survival
record. The appropriate statistical analysis revealed that the
difference was statistically significant.



What conclusions can we draw from this study?
What if any confounding variables can you identify?
If you could repeat this study, what would you attempt to control?
Social Psychology as a Science
 Less commonly used designs in social psychology
 Developmental designs
 Cross-sectional
 Longitudinal
 Cross-lagged panel designs
 Self-reports (questionnaires)
 Advantages?
 Disadvantages?
 Observations
 Unobtrusive observation
 Unobtrusive measures
Social Psychology as a Science

Social Psychology as a Science
"How do I love thee? Let me count the ways.“
I love thee to the depth and breadth and height
My soul can reach, when feeling out of sight
For the ends of Being and ideal Grace.
I love thee to the level of everyday's
Most quiet need, by sun and candle-light.
I love thee freely, as men strive for Right;
I love thee purely, as they turn from Praise.
I love thee with a passion put to use
In my old griefs, and with my childhood's faith.
I love thee with a love I seemed to lose
With my lost saints, --- I love thee with the breath,
Smiles, tears, of all my life! --- and, if God choose,
I shall but love thee better after death
-Elizabeth Barrett Browning