22 Terms Flashcards
(22 cards)
Reliability
Repeated observations yield the same results
Validity
An experiment measures what it is supposed to measure
External Validity
To what extent is a sample representative of an entire population
Internal Validity
Extent to which the Independent variable affects the dependent variable
Cronbach’s Alpha
Indicator that measures internal consistency or if all items relate to the same concept; average inter-correlation of all items (e.g., random sample with low CA of <0.5 does not relate to what is measured)
Deductive approach
Theory -> quantitive observation (positivism)
Inductive approach
Observation -> theory (systematic - qualitative)
Critical rationalism
How science works - pitfalls of induction and positivism
(Falsification), empirical evidence - reject hypothesis
Non-reactive measurement
No reactions by tested subjects due to unawareness (operationalization)
Item-total-correlation (ITC)
ITC equals correlation of total score with single item
Types of systematic observation
Open, participating, hidden, field, lab, non-participating
Causality
Causation indicates a relationship between two events where one event is affected by the other.
Correlation does not mean causation.
Correlation
Describes the linear relationship between two variables.
Correlation does not mean causation.
Cross-sectional design
Test compares different groups of subjects
Double Blind
Researcher not aware of assignment of subject
Population
Group of people that conclusions are about
Quota sampling
Represents sample of different sub groups
Sampling error
Difference between sample and population
Simple random sample (SRS)
Each unit has an equal probability of being selected - but difficult to implement in reality
Statistical significance
Stat significance is the likelihood that a relationship between two or more variables is caused by something other than chance.
P-value of 5% or lower is considered to be stat significant
Factor analysis
Multivariate statistical procedure which bundles items into independent factors and thereby reduces complexity
Multiple regression analysis
Multiple regression explains the relationship between multiple independent or predictor variables and one dependent or criterion variable.
