Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
32 Cards in this Set
- Front
- Back
Quasi-experimental designs
|
missing a control group or random assignment
-one group pre/post test -time series -non equivalent pre/post test -non equivalent post test only |
|
Questions for selecting a design
|
How many IVs
How many levels for each IV How many subject groups How will subjects be selected/assigned How often are observations made What is the sequence of interventions/measurements |
|
Pretest/Post test Design
|
True experimental design
single factor/one way Randomized controlled trials are this type doesn't account for history/concurrent treatments |
|
Post test only design
|
true experimental design
single factor/one way only assessed following treatment |
|
Factorial design
|
true experimental design
two/three way; multiple IVs with many levels |
|
Completely Crossed
|
when every level of one factor is represented at every level of the other factor;
in a factorial design |
|
Main Effect
|
effect of one IV without consideration of the other; looking at each by itself
|
|
Interaction Effect
|
can only be studied in a multifactorial design;
when the effect of one IV is different across levels of another IV |
|
Nested design
|
true experimental design
multifactorial used when some attribute variables cannot be crossed with all levels of other variables |
|
One way repeated measures
|
true experimental design
single factor one group of subjects is exposed to all levels of one treatment variable |
|
Crossover/Counterbalanced Design
|
true experimental design
repeated measure/single factor systematically varied order of treatment conditions; when one group gets two different treatments at different times |
|
Mixed Design
|
true experimental design
multifactorial an independent factor is tested at all levels pre and post as well as across time |
|
One group pre/post test
|
quasi-experimental design
measures are taken pre/post on one group of subjects; no comparison group |
|
Non equivalent pre/post test
|
quasi experimental design
multi-group subjects not randomly assigned use historical controls (previously received different treatment) |
|
Efficacy
|
word related to Internal Validity
|
|
Effectiveness
|
word related to external validity/generalizability
|
|
In a single subject design the target behavior is this
|
(the dependent variable)
observable quantifiable valid indicator of treatment effectiveness |
|
Two important features of single subject baselines
|
stability
trend |
|
Stability
|
consistency of a response over time
|
|
Trend
|
rate of change in behavior;
need 3-4 data pts |
|
Target Behaviors are measured in these ways
|
frequency
duration magnitude |
|
Types of Reliability
|
Total (percentage)
Point by point (agree/total) Occurrence/Nonoccurrence (agree on occurance/someone thinks it occurs) |
|
ABA Design
|
single subject design
replicates a baseline phase following intervention (withdraw and reinstate) |
|
ABAB Design
|
Single Subject design
gives two opportunities to evaluate the intervention effects (withdraw and reinstate) |
|
Interactive Designs
|
Single subject design
studies two or more treatments at once |
|
Alternating Treatment Designs
|
Single subject design
treatments are rapidly alternated |
|
Multiple baseline design
|
used when treatment withdrawal is unethical
can be done across subjects, conditions, or behaviors |
|
Changing Criterion Design
|
single subject design
interventions are geared toward gradual development of a target behavior (goals) |
|
Visual Analysis focuses on
|
level (magnitude at baseline and intervention)
trend stability |
|
Celeration Line
|
line that represents linear trend
acceleration/decceleration |
|
Split middle line
|
line that divides data into two equal parts;
median slope |
|
Generalization of findings
|
External Validity
Direct Replication Systematic Replication Clinical Replication Social Validation (importance) |