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;
47 Cards in this Set
- Front
- Back
Test Problems
|
Being able to pick out the independent, dependent variables, possible values and direction of relationship. Measurement validity, measurement reliability, causality, control variable, model types, hypothesis, randomization, spurious.
|
|
Eight Factors Jeopardizing Internal Validity
|
History
Maturation Testing Instrumentation Regression Artifacts Selection Biases Experimental Mortality Selection-Maturation Interaction |
|
Five Threats to External Validity
|
Interaction Effects of Testing
Interaction of Selection and Experimental Treatment Reactive Effects of Experimental Arrangements Multiple-Treatment Interference Irrelevant Replicablility of Treatments |
|
Five Elements of Causality
|
1) Theoretical Basis and Plausibility
2) Time order (Cause>Effect) 3) Correlation 4) Must understand why????? 5) Ability to rule out rival causes |
|
Correlation
|
Patterned relationship (both variable go up, one goes up one goes down, non-linear, etc.)
|
|
Correlation Coefficient Properties
|
1) Extent to which two variable are related
2) Ranges between 1 and -1 3) Positive or negative correlation 4) |
|
History Threat
|
The history of subjects or other events that may affect the results
|
|
Maturation Threat
|
Passage of time and varying growth
|
|
Testing Effect
|
Getting better at taking test
|
|
Selection Biases
|
Duh (not random)
|
|
Regression Effect Threat
|
Will move back to the mean
|
|
Instrumentation Threat
|
Changes in observer or testing material can influence results
|
|
Experimental Mortality
|
People drop out, die, move away, get removed
|
|
What types of evidence are necessary to support a claim that one variable is the cause of change in another?
|
1) Time order
2) Correlation 3) Theoretical Framework & Plausibility 4) 5) Rule out all rival explanations |
|
Which of the threats to internal validity is likely to be the most common?
|
History
Selection Maturation |
|
Which of the threats of internal validity will cause the most trouble or harm?
|
History
Design Contamination |
|
Contrast History to Maturation
|
History is outside factors, maturation occurs to the subjects
|
|
Good research design...
|
should eliminate threats to internal validity.
|
|
Ubiquitous
|
Manipulation, logic,
|
|
Percentage of Normal Distribution scores in each interval
|
Bell curve shaped
|
|
Random selection vs. random assignment
|
Selection is external, assignment is internal
|
|
Important in a quasi-experimental...
|
is the comparison group similar (equivalency)
|
|
One Shot Design
|
X O
|
|
One Group Pretest/Post-test Design
|
O X O
|
|
Static Group Design
|
X O
_ _ _ _ O |
|
Time Series Design
|
O O O O X O O O O
|
|
Non-Equivalent Control Group Design
|
O X O
_ _ _ _ _ O O |
|
Multiple Time-Series Design
|
O O O O X O O O O
- - - - - - - - - - - - - - - - - - - O O O O O O O O |
|
Pre-Test/Post-Test Control Group Design
|
O X O
______ O X O |
|
Experimental Designs
|
Pretest/Posttest Control Group
Solomon Four Group Post Test Only Control Group |
|
Solomon Four Group Design
|
O X O
______ O O ______ X O ______ O |
|
Quasi-Experimental
|
Analysis of results that approximates the control in an experiment because not all factors can be controlled.
|
|
Pre-Test or Non-Test Design
|
X O
|
|
Post Test Only Control Group
|
X 0
-------- 0 |
|
Ethical Considerations (Bellmont Report)
|
1) Ethical Consent
2) Balancing cost and benefits 3) Selection |
|
Anonymous vs. Confidential
|
Anonymous means nobody knows (including the researcher) who the participants are; Confidential means that the researchers know who the participants are but promise not to disclose this info.
|
|
Sampling Options
|
Random Sampling
Systematic Sampling Stratified Sampling Cluster Sampling Convenience Sampling Proposive Sampling Snowball Sampling |
|
|
|
|
Systematic Sampling
|
Choosing subjects from the population at regular intervals (every 10th customer who walks through the door, every hundredth name in the phone book, etc.)
|
|
Stratified Sampling
|
Making sure your population has representatives from every subpopulation.
|
|
Cluster Sampling
|
When the population is divided into geographic clusters (blocks, neighborhoods, etc.), and respondents are selected at random within each cluster
|
|
Convenience Sampling
|
The researcher makes a limited attempt to insure that this sample is an accurate representation of the population
|
|
Proposive Sampling
|
?
|
|
Snowball Sampling
|
For a particular type of group asking for recommendation of subject, and then asking those subjects for recommendations, and so on.
|
|
Problems with too large a sample
|
Waste of resources
Participant Risk |
|
Random Sampling
|
Every individual in the population of interest has an equal opportunity of being selected for the sample
|
|
Solomon Four Group
|
controls for the effect of the pretest.
|