Exam I Flashcards
Conceptual Variable
Abstract concepts expressed in concept level language; what researchers mean when using a specific term.
Confound
When you think one thing caused an outcome, but other things change too, so you’re confused about the real cause.
Intuition is often biased by…
A good story, availability heuristic, failing to think about what you can’t see, bias blind spot, and confirmation bias.
Research is best because conclusions are more likely to be correct and less prone to…
Personal biases, lack of a comparison group, confounds, and individual biases of “authority” figures.
Variable
Something in a study that has two or more levels.
Measured Variable
Researcher observes existing levels and records of them.
Manipulated Variable
Researcher controls these variables, often by assigning participants to different levels.
Confederate
Someone who’s part of the study and know’s what’s being tested.
Operationalize
To go from concepts to a measured or manipulated variable.
What are the three claims scientists can make in a study?
Frequency, association, and causal.
Constant
Something that has only one level in a study, although it could potentially vary.
Frequency Claim
Describe a particular rate or a degree of a single variable; often in political surveys.
Association Claim
One level of one variable is associated with a particular level on a second variable; two measured variables.
Causal Claims
One variable is responsible for changing the second variable; manipulated variables and random assignment.
What are the 3 criteria to establish that variable a caused variable b?
Temporal precedence, covariation, and internal validity.
Temporal Precedence
If variable a causes variable b, then variable a has to happen first in time; the cause needs to happen before the effect.
Covariation
A relationship between variable a and variable b is observed.
Internal Validity
The confidence you have that the effects seen on variable b are done by variable a and not anything else.
What are the four validities in psychology?
Internal, external, construct, and statistical.
Validity
How appropriate is a conclusion or a decision for this study?
Construct Validity
Do the conceptual and operational levels correspond?
Statistical Validity
Are the study’s statistical conclusions accurate and reasonable?
Margin of Error
A range of frequencies that tries to capture the true frequency of the population; smaller samples produce larger margins of error.
An association claim is NOT a _____.
causal claim.
External Validity
Who was sampled and would the findings generalize?
What are the 3 types of measurement operationalization?
Observational, physiological, and self-report.
What are the four scales of measurement?
Nominal, ordinal, interval, and ratio.
Categorical Variables
Numbers assigned have no meaning, they just distinguish groups from each other; manipulated variables.
Quantitative Variables
Numbers meaningfully place scores relative to each other.
Nominal
Numbers assigned are only labels for categories.
Ordinal
A rank ordering (1st, 2nd, 3rd, etc.).
Interval
Each number equidistant from the next, but no 0 point.
Ratio
Each number is equidistant and there is a true 0 point.
Reliability
The consistency of dependability of a measuring technique.
Interrater Reliability
The consistency among two or more researchers who observe and record participants’ behavior.
Test-retest Reliability
Consistency of participants’ responses on a measure over time.
Internal Reliability
Assesses the degree of consistency among the items on a scale taken at one time.
Split-half Reliability
Divide scale items into two sets and assess the correlation.
Cronbach’s alpha coefficient (α)
The average of all possible split half reliabilities
Face Validity
Does it look like it’s measuring what you want to measure?
Content Validity
Does the measure contain all parts that your theory says it should contain?
What are the subjective ways of assessing construct validity?
Face and content.
What are the empirical ways of assessing construct validity?
Criterion, convergent, and discriminant.
Criterion Validity
Is your measure correlated with a relevant behavioral outcome?
Convergent Validity
Is your self-report measure more strongly associated with self-report measures of similar constructs?
Discriminant Validity
Is your self-report measure less strongly associated with self-report measures of similar constructs?
