Res Meth Final Exam - Flashcards

Personal experience

A method for learning, could come from your own or from others’

Confounding variable

Something else that could have caused an observed relationship

Problems with learning from personal experience

No comparison group, has confounds

Intuition

Doesn’t matter if it’s true as much as it does that it sounds true

Biases of intuition

Confirmation bias, “cherry-picking” evidence, availability heuristic, present/present bias, bias blind spot

Cherry-picking evidence

More inclined to pay attention to or to believe evidence that lines up with our hypotheses

Availability heuristic

How easily something comes to mind can bias us

Present/present bias

Fail to consider what isn’t there (present treatment and present outcome)

Bias blind spot

Blind to our own biases

Learning from authority

Authority figures telling us things, believe it because we believe that the person can be trusted

Empiricism

Based on systematic, direct, unbiased observations that are used to draw conclusions about the world

Confederate

Someone hired by the research team to act a certain way

Testable

Observed with real world data

Falsifiable

Possible to observe results contrary to the theory

Parsimonious

The simplest explanation, makes the fewest assumptions

Hypothesis

Specific prediction about what needs to happen for the theory to be true

Probabilistic

Conclusions are based on probability theory

Two types of hypotheses

Null hypothesis, alternative hypothesis

Null hypothesis

There is no effect

Alternative hypothesis

There is an effect, this hypothesis is consistent with the research theory

Noise

Random things that effect the thing you’re studying

Test statistic

Is there enough influence from something that it surpasses the other random things that effect the thing you’re studying

Test statistic calculation

Signal/noise

Large p value, and its indication

p=0.6, likely you would have gotten those results if the null was truea

Indication of small p value

Unlikely you could have gotten these results if the null was true

p-value

The probability of getting the observed result or a LARGER result if the null is true

Threshold for rejecting the null

p less than 0.05

Type 1 error

Rejecting the null hypothesis when it is true (false positive)

Type 2 error

Retaining the null hypothesis when it is false (false negative)

Effect size

Strength or magnitude of the effect, how big the difference is, how meaningful the results are

Smaller Cohen’s d, and its indication

0.20 or less, small effect

Medium Cohen’s d

0.50

Larger Cohen’s d, and its indication

0.80 or more, large effect

Universalism

Claims are made based on merit not credentials

Communality

Science is shared with and belongs to the communityDis

interestedness

Seek the truth regardless of personal opinions

Organized skepticism

Question everything and seek evidence

How psychologists approach their work

• Act as empiricists

• Test theories through research and revise

• Take an empirical approach to both applied and basic research

• Do further research on what they discover

• Make their work public

Empiricism

Involves using evidence from the senses (sight, hearing, touch) or from instruments that assist the senses (thermometers, timers, photographs, weight scales, and questionnaires) s the basis for conclusions

Theory

Set of statements that describes general principles about how variables relate to one another

Hypothesis

Specific outcome the researcher expects to observe in a study if the theory is accurate

Data

A set of observations

Falsifiability

A theory must lead to hypotheses that, when tested, could actually fail to support the theory

Parsimony

If two theories explain the data equally well, scientists should opt for the simpler one

Applied research

Done with a practical problem in mind, the researchers conduct their work in a particular real-world context

Basic research

Not intended to address a specific, practical problem. The goal is to enhance the general body of knowledge

Translational research

Use of lessons from basic research to develop and test applications to health care, psychotherapy, or other forms of treatment ant intervention

Scientific journals

Usually come out every month and contain articles written by various qualified contributors

Journalism

Includes the kind of news and commentary that most of us read or hear on television, in magazines and newspapers, and on internet sites

Categories of unethical treatment

Participants not treated respectfully, participants harmed, researchers targeted a disadvantaged social group

In a debrief

Participants are carefully informed about the study’s hypotheses

2 provisions of the principle of respect for persons

Informed consent, special protection for those with less autonomy

Anonymous studies

Researchers do not collect any potential identifying information

Confidential studies

Researchers collect some identifying information but prevent it from being disclosed

Principle of justice

Calls for a fair balance between the kinds of people who participate in research and the kinds of people who benefit from it

Institutional review board

Committee responsible for interpreting ethical principles and ensuring that research using human participants is conducted ethically

Two types of deception

Omission, commission

Omission

Researchers withhold some details of the study from participants

Commission

Researchers actively lied to the participants

Data fabrication

Occurs when researchers invent data that fits their hypotheses

Data falsification

Occurs when researchers influence a study’s results, perhaps by selectively deleting observations from a data set or by influencing their research subjects to act in the hypothesized way

Plagiarism

Representing the ideas or words of others as one’s own

The 3 R’s

Replacement, refinement, reduction

Replacement

Researchers should find alternatives to animals in research whenever possible

Refinement

Researchers must modify experimental procedures and other aspects of animal care to minimize or eliminate animal distress

Reduction

Researchers should adopt experimental designs and procedures that require the fewest animal subjects possible

Equitability

Distributing the burdens and benefits of research

Additional consent

Allow participants to withdraw their data after the debrief if they so choose

Desensitizing

Providing resources to help participants work through any distress

Dehoaxing

Informing participants what was actually being studied, revealing confederates

Debrief

Full disclosure of the research purpose to participants following a study

Third party consent and assent

Guarding for a child must consent, but the child still has to consent as well

Undue influence

Researchers offer an incentive that is too great to turn down

Issues with conformed consent

Lack of transparency, undue influence, coercion, special consideration for persons with less autonomy

Informed consent includes

Necessary information, understanding, voluntary participation

Concern for welfare

Protect participant welfare and minimize risks

Federal Research Council

Tri-agency council

Justice

Fairness in who pays costs and who gains benefits

Beneficience

Minimize risk, maximize benefits

Respect for persons includes

• right to informed consent

• no coercion or unnecessary deception

• protect vulnerable individuals

4 types of validity

Construct validity, external validity, statistical validity, internal validity

Construct

Any conceptual variable that you are interested in

Operational definition

Defines construct by specifying exactly how it is measured or manipulated

Frequency claims

Describe the rate or frequency of a variable

Association claims

Predict the relationship between two variables

Correlational study

A study that measures the relationship between two variables

r

Correlation coefficient

Causal claims

Explains the relationship between variables

Covariance

Cause and effect co-occur

Temporal precedence

Cause precedes effect

Internal validity

Rules out confounds third variables

Criteria for making a causal claim

Covariance, temporal precedence, internal validity

Construct validity

How well a conceptual variable is operationalized

External validity

Are the findings generalizable to other people, contexts, and methods than those in the original study

Statistical validity

The extent to which a study’s statistical conclusions are accurate and reasonable

Statistical validity of a frequency claim

Margin of error (confidence interval)

Statistical validity of association and causal claims

Strength of the association (effect size)

r value for small effect size

0.10

r value for medium effect size

0.30

r value for large effect size

0.50