Term
| What is the difference between an experimental design and a non-experimental design? |
|
Definition
Experimental- random assignment
NE- No random assignment |
|
|
Term
| What are the goals of science? |
|
Definition
1. Describe
2. Predict
3. Explain |
|
|
Term
| What are generation 1st questions? |
|
Definition
-finding out if variables are related
-description of the world (how much etc.)
-Newtonian style |
|
|
Term
| What are generation 2nd questions? |
|
Definition
-boundary conditions of first generation questions
-under what circumstances are variables related
-moderating variables |
|
|
Term
| What are generation 3rd questions? |
|
Definition
-processes that underlie relationships between variables
-mediation: mechanisms which produce relationships |
|
|
Term
|
Definition
-counterintuitive
-practical implications
-confirms some but not all beliefs
-good writing
-titles are long and have a colon |
|
|
Term
| What are the 3 conditions needed to measure causality? |
|
Definition
1. X must precede Y temporally
2. X must be reliably correlated with Y
3. the relationship between X and Y must not be explained by other causes |
|
|
Term
| What is the gold standard for inferring causality? |
|
Definition
| random assignment (it rules out most alternative explanations) |
|
|
Term
| Explain the counter-factual model: |
|
Definition
in the case of random assignment,
the effect of the manipulation is simply the difference in Y between the treatment and control condition The change in Y can stem from no other cause than that of the manipulation ...hence, causality |
|
|
Term
| What are the 6 ways of controlling for extraneous variables? (from best to worst) |
|
Definition
1. direct manipulation
2. random assignment
3. eliminate/include extraneous variables
4. statistical control
5. rational argument
6. analyze reliable scores |
|
|
Term
| What is statistical control? |
|
Definition
| a method of controlling for extraneous variables- extraneous variables are measured, but not explicitly represented as variables- the influence is removed statistically ahead of time |
|
|
Term
| What is rational argument? |
|
Definition
| a method of controlling for extraneous variables- arguments as to why other explanations are not plausible |
|
|
Term
| What is 'analyzing reliable scores'? |
|
Definition
| a method of controlling for extraneous variables- Scores need to be precise/consistent. Effects are due to content of measures not random or systematic error. |
|
|
Term
| By not using random assignment- it is difficult to establish _______ and infer ______? |
|
Definition
| internal validity and causality |
|
|
Term
| Describe random assignment: |
|
Definition
| Minimizes differences between groups by equally distributing characteristics across groups. Equates groups on all variables (those measured and not measured) before study. |
|
|
Term
| Describe direct manipulation: |
|
Definition
| a method of controlling for extraneous variables- being in control of the when and how “the cause” occurs |
|
|
Term
| what is a threat to internal validity? |
|
Definition
| Something that jeopardized the conclusion that X causes Y |
|
|
Term
|
Definition
| a threat to internal validity: Specific event that take place concurrently with treatment. Could be anything (e.g., weather change, big event in news, local initiative, etc) |
|
|
Term
| what is the term for a specific event that take place concurrently with treatment. Could be anything (e.g., weather change, big event in news, local initiative, etc) |
|
Definition
| History (a threat to internal validity) |
|
|
Term
|
Definition
a threat to internal validity: Naturally occurring changes are
confounded in the treatment. People change over time. Get older, more mature, hungrier, make more money, etc |
|
|
Term
| what is the term for "Naturally occurring changes that confound the treatment. People change over time. Get older, more mature, hungrier, make more money, etc" |
|
Definition
| Maturation (a threat to internal validity) |
|
|
Term
|
Definition
a threat to internal validity: Relative for longitudinal or lagged
designs where participants are tested more than
once. Practice or reactivity. Simple measuring
something may change outcome (i.e.,
information provided, introspection occurs) |
|
|
Term
| what is the term for "Relative for longitudinal or lagged designs where participants are tested more than once. Practice or reactivity." |
|
Definition
| a threat to internal validity: Testing |
|
|
Term
|
Definition
| a threat to internal validity: Meaning and interpretation of scores change over time. Particularly pertinent for observers or coders (e.g., get tired, change their standards, etc.) |
|
|
Term
| what is the term for "Meaning and interpretation of scores change over time. " |
|
Definition
| a threat to internal validity: Instrumentation |
|
|
Term
| what is Attrition (or mortality) |
|
Definition
a threat to internal validity: Loss of cases from
study. Problem when it is systematic (e.g.,
certain people are more or less likely to drop
out than others). |
|
|
Term
what is the term for "Loss of cases from
study." |
|
Definition
| a threat to internal validity: Attrition (or mortality) |
|
|
Term
|
Definition
a threat to internal validity: Statistical regression to the mean.
Tendency for extreme cases to be less extreme on subsequent measures. Problematic when selecting participants based on extreme
scores. |
|
|
Term
| what is "the tendency for extreme cases to be less extreme on subsequent measures." |
|
Definition
| a threat to internal validity: Regression |
|
|
Term
| what is Ambiguous temporal precedence |
|
Definition
a threat to internal validity: Lack of
understanding about what variable occurred first (which is the cause and which is the effect). Measuring variables at same time (e.g., job satisfaction and performance). |
|
|
Term
| what is "Lack of understanding about what variable occurred first (which is the cause and which is the effect)" |
|
Definition
| a threat to internal validity: Ambiguous temporal precedence |
|
|
Term
|
Definition
a threat to internal validity: Respondents in conditions differ at
the outset. |
|
|
Term
| what is the term for when Respondents in conditions differ at the outset. |
|
Definition
|
|
Term
| what is Treatment diffusion or imitation |
|
Definition
a threat to internal validity: Control
cases learn about treatment or try to imitate experiences of treated cases. |
|
|
Term
what is the term for when "Control
cases learn about treatment or try to imitate experiences of treated cases." |
|
Definition
| Treatment diffusion or imitation |
|
|
Term
| what is Compensatory rivalry |
|
Definition
| a threat to internal validity: Control cases learn about treatment and become competitive with treated cases. |
|
|
Term
| what is the term for when "Control cases learn about treatment and become competitive with treated cases." |
|
Definition
|
|
Term
| what is Compensatory equalization of treatment |
|
Definition
a threat to internal validity: when Cases in one condition demand to be assigned
to the other condition or be compensated. |
|
|
Term
what is the term for when Cases in one condition demand to be assigned
to the other condition or be compensated. |
|
Definition
| Compensatory equalization of treatment |
|
|
Term
| what is Resentful demoralization |
|
Definition
| a threat to internal validity: Control cases learn about treatment become resentful and stop trying or withdraw from study. |
|
|
Term
| what is the term for when Control cases learn about treatment become resentful and stop trying or withdraw from study. |
|
Definition
|
|
Term
| what are Novelty and disruption effects (Hawthorne effect) |
|
Definition
a threat to internal validity: Cases respond well to a novel treatment or poorly to one that interrupts
their routines. |
|
|
Term
| what is the term for when Cases respond well to a novel treatment or poorly to one that interrupts their routines. (e.g. being observed at work) |
|
Definition
| Novelty and disruption effects (Hawthorne effect) |
|
|
Term
| what is Selection-maturation |
|
Definition
| a threat to internal validity: Different rates of change (or growth) between groups |
|
|
Term
| what is the term for Different rates of change (or growth) between groups |
|
Definition
|
|
Term
| what is Selection-attrition |
|
Definition
| a threat to internal validity: Rate of missing data is higher in one group than another. |
|
|
Term
| what is the term for when "Rate of missing data is higher in one group than another." |
|
Definition
|
|
Term
| what is Selection-regression |
|
Definition
| a threat to internal validity: There are different rates of regression to the mean across groups. Example, only treatment group is selected based on extreme scores. |
|
|
Term
| what is the term for when There are different rates of regression to the mean across groups. Example, only treatment group is selected based on extreme scores. |
|
Definition
|
|
Term
|
Definition
| inferences about whether the results of a study will hold over variations in participants, treatments, settings, and outcomes (measures). |
|
|
Term
| what are Quasi-experimental designs? |
|
Definition
| when participants are assigned to groups by a method other than random assignment. |
|
|
Term
| What are the two types of Quasi-experimental designs? |
|
Definition
–Non-equivalent-group design
–Regression-discontinuity designs |
|
|
Term
| what is a Non-equivalent-group design |
|
Definition
a quasi-experimental design where
Treatment and control groups are already formed.
• Existing groups
• Experimenter has no control
• Groups should be as similar as possible.
• Research randomly chooses what group
receives the treatment. |
|
|
Term
| what is a Regression-discontinuity design |
|
Definition
| a quasi-experimental design where Participants are assigned to conditions based on a cut-off score on an assignment variable (can be any variable that is measured before treatment) |
|
|
Term
| what is a quasi-experimental design where Participants are assigned to conditions based on a cut-off score on an assignment variable (can be any variable that is measured before treatment) |
|
Definition
| a Regression-discontinuity design |
|
|
Term
| what is a a quasi-experimental design whereTreatment and control groups are already formed. |
|
Definition
| a Non-equivalent-group design |
|
|
Term
|
Definition
|
|
Term
what does
O1 X O2
refer to? |
|
Definition
| One group pretest-posttest design. |
|
|
Term
what does
O1 O2 X O3 O4
refer to? |
|
Definition
| One group pretest-posttest design. |
|
|
Term
what does
O1 O2 X O3 O4 X O5 O6
refer to? |
|
Definition
| Repeated-treatment design (Introduce and remove treatment within the same participants over time.) |
|
|
Term
| what is a weakness of a Posttest-only design? |
|
Definition
the weakness is there is no pretest
–Makes it susceptible to all forms of selection threats. |
|
|
Term
what threats is this design susceptible to?
NR O1 X O2 |
|
Definition
susceptible to internal validity threats:
– Selection-regression
– Selection-maturation
• Multiple group threats apply as well. |
|
|
Term
what kind of design is this? (and what are the benefits?)
NR O1 O2 X O3 |
|
Definition
Double-Pretest design
Allows researchers to asses some threats
before treatment occurs.
–Selection – maturation |
|
|
Term
| for Non-equivalent-group designs what are the benefits of Switching of Treatments Design |
|
Definition
• Eliminates many threats to internal validity.
• Added benefit is that it allows researchers to test if effects of treatment are maintained.
• Ethical advantage of giving everyone the treatment. |
|
|
Term
| How are Regression-Discontinuity Designs analyzed? |
|
Definition
| using multiple regression |
|
|
Term
|
Definition
correlational designs
• multiple measures within
people.
• Test effects at different level of analysis.
• Use multilevel regression techniques. |
|
|
Term
what are inferences about whether
the results of a study will hold over variations in participants, treatments, settings, and outcomes (measures). |
|
Definition
|
|
Term
| What are the two types of external validity? |
|
Definition
| population validity and ecological validity |
|
|
Term
| what is Population validity |
|
Definition
| can you generalize from your sample to the population or to another defined population? |
|
|
Term
| what is ecological validity |
|
Definition
| concerns whether the combination of manipulation, settings, or outcomes approximate those in real life situation under investigation. |
|
|
Term
| how is external validity established |
|
Definition
We can establish external validity through replication (empirical approach)
–probability sampling techniques. |
|
|
Term
| what is Simple random sampling |
|
Definition
A Probability Sampling Technique.
Researchers try and select participants at random from the population.
–All observations have equal opportunity to be selected. |
|
|
Term
| what is Stratified sampling |
|
Definition
A Probability Sampling Technique.
Population is divided into homogeneous, mutually exclusive groups (strata; e.g., neighbourhoods).
–observations are randomly selected from within each stratum. |
|
|
Term
|
Definition
A Probability Sampling Technique.
Population is divided into clusters
(groups) and entire clusters are randomly selected.
–Simple random sampling with “clusters.” |
|
|
Term
| what is Accidental sampling (AKA called ad hoc, convenience, or locally available samples) |
|
Definition
A Non-Probability Sampling Technique.
Cases are selected because they are available.
–Very practical approach.
–Samples are not representative (i.e., there is some systematic difference between those in the study and those not in the study). |
|
|
Term
| what is Purposive sampling |
|
Definition
A Non-Probability Sampling Technique.
Researcher intentionally selects cases from defined groups (e.g., sick/not sick, managers, employed people, single parents).
–groups are typically linked to hypotheses in a meaningful way.
–Non-equivalent design
–Regression discontinuity design |
|
|
Term
| what are Threats to external validity? |
|
Definition
| any characteristic of a sample, treatment, setting, or measure that leads the results to be specific to a particular study and not generalizable |
|
|
Term
| What is Treatment - unit interaction |
|
Definition
A Threat to External Validity.
An effect only holds for certain types people (e.g., men vs. women) |
|
|
Term
| What is the term for when An effect only holds for certain types people (e.g., men vs. women) |
|
Definition
| Treatment - unit interaction |
|
|
Term
| What is Treatment - setting interaction |
|
Definition
A Threat to External Validity.
An effect only holds in certain settings (e.g., treatment is more effective in certain contexts than it is in others) |
|
|
Term
| What is the term for when An effect only holds in certain settings (e.g., treatment is more effective in certain contexts than it is in others) |
|
Definition
| Treatment - setting interaction |
|
|
Term
| What is Treatment - outcome interaction |
|
Definition
A Threat to External Validity.
An effect holds for some types of outcome variables but not others (e.g., works on self-report but not observation). |
|
|
Term
| What is the term for when An effect holds for some types of outcome variables but not others (e.g., works on self-report but not observation). |
|
Definition
| Treatment - outcome interaction |
|
|
Term
| What is Treatment - treatment interaction |
|
Definition
A Threat to External Validity.
An effect does not hold over variations in treatment or an effect depends on exposure to previous treatments. |
|
|
Term
What is the term for when An effect
does not hold over variations in treatment or an effect depends on exposure to previous treatments. |
|
Definition
| Treatment - treatment interaction |
|
|
Term
| What is Multiple treatment interference |
|
Definition
| A Threat to External Validity. An effect of a single independent variable does not hold when multiple variables are included. |
|
|
Term
What is the term for when An effect of
a single independent variable does not hold when multiple variables are included. |
|
Definition
| Multiple treatment interference |
|
|
Term
| what is Respect for persons? |
|
Definition
an ethical core principle.
Autonomy (voluntary participation)
vulnerability (using as means to end)
free and informed consent |
|
|
Term
| What are the three ethical core principles? |
|
Definition
-Concern for Welfare
-Respect for Persons
-Justice |
|
|
Term
|
Definition
an ethical core principle.
-balance of power
-vulnerable populations
-participants as collaborators |
|
|
Term
| what is concern for welfare? |
|
Definition
an ethical core principle?
-individual well-being
-Impact of research on all–even those not directly involved
-relative risks and potential benefits
-harms should be minimized
-benefits should be maximized
-privacy (control of information) |
|
|
Term
| Which kind of research requires an ethics review? |
|
Definition
-research involving living human participants
-Research involving human biological materials |
|
|
Term
What kind of risk are
◦Administration of a substance
◦Bodily contact |
|
Definition
|
|
Term
What kind of risk are
◦Embarrassment
upset
demeaned |
|
Definition
|
|
Term
What kind of risk are
loss of status
loss of reputation
loss of privacy |
|
Definition
|
|
Term
|
Definition
| the probability and magnitude of possible harms implied by participation in the research is no greater than those encountered by participants in those aspects of their everyday life that relate to the research. |
|
|
Term
| When is research ethics board approval required? |
|
Definition
| if identifying information is involved |
|
|
