Textbook Notes (280,000)
CA (160,000)
UTSC (20,000)
Psychology (10,000)
PSYB01H3 (600)
Anna Nagy (200)
Chapter 8

PSYB01H3 Chapter Notes - Chapter 8: Dependent And Independent Variables, Internal Validity, Null Hypothesis


Department
Psychology
Course Code
PSYB01H3
Professor
Anna Nagy
Chapter
8

This preview shows pages 1-2. to view the full 6 pages of the document.
Two-Group Design
Introduction to Our Research Question
Can trying to ignore a text message lead to distraction?”
this one seems to make a more specific prediction about a type of behavior
that leads to a specific outcome.
As a result, our focus has moved beyond merely describing what is
taking place to identifying how one factor (ignoring text messages)
leads to changes in another factor (distraction)
need to use experimental research to help us determine cause and effect.
Picking a Design
We should let our question guide our design choice
two main design types:
nonexperimental designs,
which focus on determining what happens
(interviews, observation, surveys)
experimental designs,
which focus on determining why something happens
Benefits of Experimental Designs
major benefit!!!
ability to identify cause-and-effect relations between variables.
first you have to establish if there is covariation between two variables
you must demonstrate that two variables vary or change together in a
systematic way.
A correlational study cannot establish causation, but it can establish
covariation.
temporal precedence
when changes in the suspected cause (treatment) occur before
changes in the effect (outcome).
then you can establish independent and dependent variables!
causality!
final step! prove that covariation between variables is due to independent
variable and not due to extraneous variable
any other factor separate from the independent variable that could
account for variations in the dependent variable.
it has implication on your internal validity of your experiment
the degree to which you can rule out other possible or alternate causal
explanations for an association between the independent and
dependent variables in your experiment

Only pages 1-2 are available for preview. Some parts have been intentionally blurred.

e.g. To show that body posturing causes changes in hormone
levels, you must demonstrate that everything except for body
posture is the same throughout your experiment.
Operationally Defining the IV: Manipulating Ignoring Text Messages
first you have to clearly conceptualize which one is the IV and DV
you can manipulate your independent variable by simply mimic types of
policies professors use in their course “forbidden phone checker”
this is an example of mundane realism
how closely our study parallels the real world.
The trick will be to make the participants’ task in our experiment
as similar to a classroom experience as possible.
two-group design (simple experiment)
an experimental design that compares two groups or conditions and is
the most basic way to establish cause and effect.
Identifying the Best Groups for Our Study
experimental group
whichever group gets the key treatment
Control group
the comparison group that gets less of the treatment
when choosing groups → we use all-or-nothing comparisons
one group receives all and other nothing lol
to create quality groups, we want to be sure we have a high degree of
experimental control
ability to keep everything between groups the same except for the one
element you want to test.
The element you want to test, sometimes called the treatment, is the
factor you think makes a difference in the outcome variable.
e.g. If you want to determine if 8 hours of sleep helps students’
alertness the next morning, you tell one group to go home and
sleep 8 hours that night, while you tell the other group to sleep 5
hours.
therefore, you should put some strain on the control
group to isolate only the factor you want to examine
Group A: Not allowed to know about incoming messages; Not allowed to use the
phone
Group B: Allowed to know about incoming messages; Allowed to use the phone
**** Because the differences between groups in an all-or-nothing approach are so
drastic, there are inevitably many unintended differences between groups. To have
You're Reading a Preview

Unlock to view full version