PS381 Lecture Notes - Lecture 5: Random Assignment, Experiment, Scurvy

18 views2 pages
30 Jan 2013

For unlimited access to Class Notes, a Class+ subscription is required.

Week 3 : True Experiments
Why do experiments at all, and why care about them?
1. because you can find out things that you cant otherwise
2. they rule out alternative explanations
3. can tell you if a treatment really works
Psychological treatments that cause harm (paper)
outlines treatments that probably cause harm, and those that possibility cause harm
without true experiments, its hard to see which therapies work, which don't and which that are
possibly or probably harmful
Deterioration Effects: 1) Sometimes client deteriorate when they are in psychotherapy, but it has
nothing to do with treatment.
"post hoc ergo proper hoc" = after this, therefore, because of this (could think therapy is
harmful when it isn't because you imply causation because it comes after
: 2) Sometimes clients can prove following therapy that they would have
improved more if they hadn't done the therapy
Surgeon Lind's Experiment
Conducted an experiment, where he manipulated the diet of 12 sailors who had scurvy
Results : the sailors who drank orange and lemon juice got better
Crucial Points about Experiments
1. Manipulating a variable and seeing what happens is more beneficial
2. Experiments use comparison method : cannot know the effect of the treatment without
comparing it to others
3. Treatment conditions : conditions are the same except for the one being manipulated
4. Random assignment to condition
- randomized control experiment
- true experiment
Experiment from Causal-Model Perspective
IV = manipulated predictor variables
DV = criterion variables that depend on manipulated variables
Advantage : allow random assignment and manipulation of the IV
Causal Interpretation of Results
= Positive correlation in nonexperimental study between stress levels and amount of social interaction
May be causal in one direction (stress leads to social interaction) or other , or from a third variable
= true experiments neatly circumvents these causal ambiguities
: experimenter specifies variables as causes and effects
: random assignment means that there is no third variable
Z -> X -> Y
-> Y- > X (reverse causation)
As experiments get better, you see the treatment effects disappear
Unlock document

This preview shows half of the first page of the document.
Unlock all 2 pages and 3 million more documents.

Already have an account? Log in

Get access

$10 USD/m
Billed $120 USD annually
Homework Help
Class Notes
Textbook Notes
40 Verified Answers
Study Guides
1 Booster Class
$8 USD/m
Billed $96 USD annually
Homework Help
Class Notes
Textbook Notes
30 Verified Answers
Study Guides
1 Booster Class