Quantitative Data: Data is collected numerically or intended to be coded numerically
Categorial Scales: Nominal scales, nominal= name
Ordinal Variables: Ranked, Numbers have meaning/quantitative value
Ordinal: Interval, No “true zero”
Interval: Ratio,“True zero” means nothing
Test-retest reliability: Participants get the same results every time it’s measured
Interrater reliability: Same results no matter who measures variables
Interval reliability: Consistent patterns no matter how the question is phrased
Correlation coefficient (r)
Strength of coefficient
Positive or negative
r-0.0-1.0
Face validity: Does it look like a good measure?
Content validity: have we addressed all the different components?
Criterion validity: does it correlate with key behaviors?
Convergent validity: does the measure correlate with other measures for the same variable or related measures?
Discriminant validity: the measure shouldn’t relate with opposite variables
Reliability: consistency and dependable
validity: accuracy
relationship between validity and reliability: there can’t be validity without reliability
likert scale: agrees or disagrees with a statement.
Semantic differential formal: a type of measurement scale that captures people's attitudes or feelings
Response rate bias: participants don’t answer truthfully
Selection-bias: samples don’t represent the population of interest
Response sets (shortcut)
Acquiescence (yes/strongly agree to everything)
Fence sitting (answering in the middle)
Observer bias: when observers see what they expect to see
Observer effects: when participants confirm observer expectations
Sampling only those who are easy to contact : Convenience sampling
Sampling only those who volunteer: Self-selection
Probability sampling: Sample random sampling
Nonprobability sampling: Biased sample
Systematic sampling (computer/random number)
Cluster sampling (random sample)
Multistage sampling (randomly sample the random sample)
Stratified random sampling (selects demographic categories)
Convenience sampling: easy to find
Purposive sampling: select specific participants
Snowball sampling: rare individuals, have them recruit more participants
Quota sampling: set number of participants from multiple demographics