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;
56 Cards in this Set
- Front
- Back
What is the difference between a Research Design and Methodology? |
Research Design refers to your PLAN, Methodology refers to your PRACTICES. |
|
T/F: Findings always prove or disprove the hypothesis |
False! Findings do not necessarily prove the hypothesis |
|
T/F: Data may be taken as proof |
False! Data can only be taken as proof if no alternative hypotheses can account for your findings |
|
Parsimony |
The simplest explanation that can account for the findings and is most likely |
|
Plausible Rival Hypothesis |
Alternative explanations for your findings, whether parsimonious or not |
|
Findings |
The hard data you found |
|
Conclusions |
The explanations of your findings, they should adhere closely to findings |
|
T/F: Tentativeness and ambiguity of research findings can be eliminated if the study is good enough |
False, they can never be eliminated |
|
Internal validity |
The extent to which a study rules out alternative explanations of the findings |
|
Threats to internal validity |
Factors other than the IV that can influence the results |
|
Maturation |
The process of changing over time, such as growing older, tired, or bored |
|
Instrumentation |
Changes in the measuring instrument or procedure over time |
|
Response shift |
Changes in a person's standards, values, or perspective that lead to evaluating the same things in different ways |
|
External validity |
The extent to which the results of a study can be generalized beyond the study and to other populations |
|
Internal Validity |
To what extent can the intervention account for the results |
|
External validity |
To what extent can results be generalized |
|
Construct validity |
What specific part of the intervention was the causal agent |
|
Statistical conclusion validity |
To what extent is a relation shown and how well can we detect it's effects |
|
True or False: statistical regression is a threat to internal validity |
True |
|
What is Diffusion/Imitation |
When information given to one group leaks to some or all other groups (talking between groups) |
|
How do you prevent Reactivity of experimental Arrangements? |
Blind randomization so participants don't know if they're being watched or not |
|
Why would we not want to tell people they're in a study? |
Hawthorn effect |
|
How to prevent interference from multiple treatments? |
Stagger the order of treatments across groups |
|
How to prevent reactions to being assessed? |
Throw in some "red herring" measures so they don't know what you're trying to measure |
|
Confound |
A factor that occurred with the intervention that could account for the results |
|
How to prevent attention/contact with subjects providing intervention |
Blind and double blind studies |
|
Demand characteristic |
Information conveyed to participants, like a man in a white lab coat = authority |
|
Alpha |
The probability of rejecting a hypothesis when that hypothesis is true (type 1 error) |
|
Beta |
The probability of accepting a hypothesis when it is false (type 2 error) |
|
Power |
The probability of finding differences between conditions when there are really differences present |
|
Why is subject heterogeneity a threat to statistical conclusion validity? |
It makes it more difficult to detect differences due to your intervention |
|
Experimenter expectancies |
When the researchers expectancies and desires influences subjects |
|
Single operattions/narrow stimulus sampling |
When something seemingly irrelevant influences the results |
|
Cues of experimental situation |
Factors associated with the intervention actually contribute to results |
|
Grounded theory approach to qualitative research |
Using observations to form theories (e.g. from clinical work) |
|
True experiment |
The design allows for maximum control over the IV (randomized control trials) |
|
Quasi-experiments |
The conditions of true experiments are approximate - can't control everything |
|
Case-control designs |
The variable is studied by selecting participants who vary in that variable |
|
When are restricted samples fine? |
When studying a small specific area of study (video game violence won't apply to middle aged women) |
|
Cons of a 2x2 factorial design |
It isn't practical because it can get big and complicated fast and is expensive and it can be difficult to interpret |
|
Non equivalent pretest-posttest control group design |
Same as a normal pretest-posttest but without randomization |
|
Sequence effect |
When the order participants received Tx was responsible for results rather than Tx itself |
|
Order effect |
When treatment occurred led to results rather than results itself |
|
Pros and cons of No-Treatment Control Group |
Sets baseline for Tx group, but ethical problem of them not getting Tx |
|
Why No-contact control groups are bad |
Violates informed consent and poses as potential for harm, and using data without asking |
|
Benefits of nonspecific-treatment or attention placebo control group |
Addresses threats to internal/construct validity by highlighting the effects of your "active ingredient" |
|
Cons of nonspecific-treatment or attention placebo control group |
Difficult to make the control group non-therapeutic AND credible. |
|
Advantages of routine or Standard Treatment |
All participants get Tx, less attrition, clinically relevant (want to know if Tx B > Tx C) |
|
Yoked control group |
Matching control subjects to either other controls or Tx people to equilize groups on a particular variable |
|
Nonrandomly assigned or nonequivalent control group |
Adding groups and not RAing and yoking to assess for history, maturation, and testing |
|
Dismantling-treatment strategy |
Analyzes components of a treatment by isolating them. Requires 2 or more treatment groups |
|
Constructive-treatment strategies |
Opposite if dismantling. Adds components to enhance outcomes - "what can be added to make it more effective" |
|
Parametric treatment strategy |
When we know the "what" but not "how" it works. Changing process of your methods rather than content of Tx |
|
Comparative Treatment strategy |
Contrast 2 treatments and see which is better (TF-CBT vs TAU) |
|
Treatment Moderator Strategy |
Examines factors that may moderate Tx effects |
|
Treatment mediator strategy |
Explores mechanisms of change in therapy |