Textbook Notes (369,138)
Canada (162,411)
York University (12,903)
Psychology (3,584)
PSYC 2520 (20)
Chapter 8

Ch. 8 - Quasi-Experimental Designs.pdf

2 Pages

Course Code
PSYC 2520
Josee Rivest

This preview shows 80% of the first page. Sign up to view the full 2 pages of the document.
Ch. 8 - Quasi-Experimental Designs Friday, December 14, 28:59 AM PSYC 2520: Introduction to Experimental Psychology Beginning Behavioral Research: A Conceptual Primer (7thed. 2012)Rosnow & Rosenthal Chapter 8: NonrandomizedResearchand Causal Reasoning How is causal reasoning attempted in the absenceof randomization? • Prospective data - Data that will be collected in the future • Retrospective data - Data from past situations • The challenge is to try to emulate the causal reasoning of Mill's methods (Ch. 7) in order to arrive at causal hypotheses that are as sound as possible within the limitations of retrospective data How is the third-variable problemrelevant? • Requirements for causal inference: ○ Covariation ○ Temporal precedence (X must precede Y) ○ Exclusion of plausible rival explanations of the covarying relationship between X and Y  The concept of a rival explanation is known as the third-variable problem (that is, in nonrandomized research, a "third variable" that is correlated with both X and Y can also account for the correlation between X and Y) □ e.g. that age is responsible for the correlation between children's shoe size and spelling ability What is meant by subclassification on propensity scales? • Nonequivalent-groups designs - A between subjects design in which the sampling units are allocated to the experimental and control groups by means other than randomization Group A NR O X O ○ Group B NR O O  Where O = observation or measurement and X = treatment or intervention  NR = nonrandomized, R = randomized • Randomized design with a wait-list control group Group 1 R O X O O ○ Group 2 R O O X O ○ Benefits:  May overcome objections to a randomized design if the objections are based on the ethical cost of depriving control subjectsof the benefits of the treatment given to the experimental subjects  Those in group 2 are later given the opportunity to receive the treatment if a beneficial effect is observed  Information is gained about the immediate and delayed effect of the treatment as well as a replication of the immediate effect • "Type G Error" (for "group error")- Relevant extraneous factors exist that are characteristic of one group but uncharacteristic of the other group • In nonequivalent groups designs with large relevant subgroups, comparability of the "treated" and "untreated" subjects may be achieved by subclassification on propensity scores ○ This procedure, described as subclassification on propensity scores, reduces all of the variables on which the "treated" and "untreated" sampling units differ to a single composite variable (this variable is called a propensity score) What are time-seriesdesignsand "foundexperiments"? • In time-series designs, the defining characteristic is the study of variation across some dimension over time • Interrupted time-series designs compare the "effects" of an intervention in a situation before and after it occurs (e.g., the Vienna subway suicide study) O O O X O O ○  Where O is the occurrence of a situation and X is the intervention • Found experiments-- experiments that are essentially "found" (or discovered) in naturally occurring situations What within-subjectsdesignsare used in single-caseexperiments? • Single-case experimental designs come in many different forms (e.g., A-B-BC-B and A-B-A-B); the unit of study may be an N of 1 (e.g., the study of Robbie) or a few subjects (Skinner's study of superstition in pigeons) or several groups of individuals with one of the treatments randomized (the A-B-C study in Box 8.3) ○ Single-case experimental designs are a family of nonrandomized designs that is a mainstay of behavior modification research ○ Characteristics of all single-case experimental designs:  They incorporate "treatments" (interventions) that are manipulated and controlled for within a repeated-measures design  Only one sampling unit is studied, or only a few sampling units are studied  Repeated measurements are taken of the unit (a within-subjects design)  Random assignment is rarely used • Behavioral baseline- a relatively stable pattern in the subject's behavior before the experimental treatment or intervention • A-B design- the simplest of all single-case designs ○ In the A phase, no treatment (or intervention) is in effect ○ In the B phase, a treatment (or intervention) is operating The first A is the baseline period
More Less
Unlock Document

Only 80% of the first page are available for preview. Some parts have been intentionally blurred.

Unlock Document
You're Reading a Preview

Unlock to view full version

Unlock Document

Log In


Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Sign up

Join to view


By registering, I agree to the Terms and Privacy Policies
Already have an account?
Just a few more details

So we can recommend you notes for your school.

Reset Password

Please enter below the email address you registered with and we will send you a link to reset your password.

Add your courses

Get notes from the top students in your class.