Textbook Notes (280,000)
CA (170,000)
UW (6,000)
PSYCH (1,000)
Chapter 4

PSYCH257 Chapter Notes - Chapter 4: External Validity, Statistical Significance, Internal Validity


Department
Psychology
Course Code
PSYCH257
Professor
Pamela Seeds
Chapter
4

This preview shows pages 1-2. to view the full 6 pages of the document.
Research Methods:
Important Concepts:
Basic Components of a Research Study:
Hypothesis (educated guess, what you expect to nd)
Research design (how you want to test the hypothesis)
 DV (what you are studying)
 IV (in$uences on the behaviours on the DV)
Internal validity (the extent to which we can be condent that the
independent variable is causing the dependent variable to change)
External validity (how well the results relate to things outside your study)
Hypothesis:
Decide what to study
Put it in words that are unambiguous and in a form that is testable
Testability (ability to test the hypothesis)
IV (factors thought to a+ect the DV)
Internal and External Validity:
Confound (a variable that interferes with the IV and has an e+ect on the DV)
Control groups (help rule out alternative explanations)
Randomization (process of assigning people to di+erent research groups,
equal chance of being placed in any group)
Analogue models (create in the controlled conditions of the lab aspects that
are comparable (analogous) to the phenomenon under study)
Statistical vs. Clinical Signicance:
Staticians (gather, analyze, interpret data from research)
Statistical signicance (probability of obtaining the observed e+ect by chance
is small)
 mathematical calculation about the di+erence between groups
Clinical signicance (whether or not the di+erence was meaningful for those
a+ected)
E+ect size (how large the di+erences are between groups)
Social validity (obtaining input from the person being treated, as well as from
signicant others, about the importance of the changes that have occurred)
The Average Client:
Patient uniformity myth (tendency to see all P’s as one homogeneous group)
 discounting the individual di+erences
 comparing groups according to their mean scores
 make inaccurate generalizations and treatments

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

Studying Individual Cases:
Case study method (best way to begin exploring a relatively unknown
disorder)
 investigating intensively one or more individuals who display the
behavioural and physical patterns
 relies on clinician’s observations of di+erences among one person or one
group with a disorder, people with other disorders, and people with no
psychological disorders
 clinician collects as much information as possible to obtain a detailed
description of the person
 downside (coincidences occur that are irrelevant to the condition under
study)
 not experimental (only observational)
Research by Correlation:
Correlation (statistical relationship between two variables)
 study phenomenon just as they occur
Epidemiological Research:
Epidemiology (study of incidence, distribution, and consequences of a
particular problem or set of problems in a population)
 Incidence (estimated number of new cases during a specic period)
 Prevalence (number of people with a disorder at any one time)
 correlational (not experimental)
Research by Experiment:
Experimental Designs:
Clinical trial (experiment used to determine the e+ectiveness and safety of a
treatment)
 method of evaluation that follows a number of generally accepted rules
 randomized clinical trials (experiments that employ randomization of P’s
into each experimental group)
 controlled clinical trials (describe experiments that rely on control
conditions to be used for comparison purposes)
Control Groups:
Placebo e+ect (when behaviour changes as a result of a person’s expectation
of change rather than as a result of any manipulation by an experimenter)
Frustro e+ect (disappointed that they are not in the treatment group)
 make them worse
Placebo control groups (placebo given to control groups to think that they are
getting a treatment)
You're Reading a Preview

Unlock to view full version