Sampling Etc Flashcards
Define theory
coherent explanation or interpretation of one or more phenomena
Hypothesis
is a specific prediction about a new phenomenon that should be observed if a particular theory is accurate
Attributes of a good theory
falsifiable: a theory must be formulated precisely enough to be falsifiable
Parsimonious: A theory must be formulated so that it includes the minimum number of constructs and assumptions needed to explain the phenomenon adequately and predict future research outcomes
Construct
- a psychological construct is a label for a cluster or domain of covarying behaviours
- it is a tool to facilitate understanding of human behaviour
- constructs are not directly observable
Operational definition
A description of a construct in terms of the operations (procedures, actions, or processes) by which it could be observed and measured
What is sampling used for?
to try to draw conclusions about the population
when is a sample representative?
when it reflects the attributes of the target population
when is a sample biased?
when it does not reflect the attributes of the target population
simple random sampling
Each member of a population has an equal chance of being selected.
problem of simple random sampling
specific features of the population might not be represented
probability sampling
Each member of the population has a defined probability of being selected for the sample.
problem of probability sampling
the probability of selecting each individual in the population needs to be known
stratified sampling
The proportion of important features in the population are represented precisely.
problem of stratified sampling
The researcher has to decide which features of the population should be proportionally represented in the sample.
clustered sampling
The researcher randomly selects a cluster of people all having some features in common.
nonprobability sampling
Each member of the population does not have a defined probability of being selected for the sample.
convenience sample
A group of individuals who meet the general requirements of the study and is recruited in a variety of non-random ways.
purposive sampling
A group with specific features is selected.
quota sampling
Represents specific features proportionally but in a non-random way.
snowball sampling
Participants recruit other participants.
measurement
the assignment of numerals to objects or events according to rules
types of measures
self report, behavior, physiology
self report measure
Questionnaire, Conversation, Interview, Text/ narratives
behavior measure
Reaction time, Errors, Kinematics, Eye movements, Traces of behavior in environment or text
physiology measure
activity of CNS, autonomous activity, somatic activity, hormonal activity
reliability
the consistency of a measure
Validity
a measure is said to be valid if it measures what it is designed to measure
forms of reliability
test-retest reliability
split-half reliability
inter-rater reliability
test-retest reliability
test-retest reliability measures the consistency of results when you repeat the same test on the same sample at a different point in time
what measures is test-retest reliability good for?
measures that are assumed to be relatively stabile over time
what is essential for test-retest reliability?
timing
why is timing essential for test-retest reliability?
- if too long, the measured construct might have changed
- if too short, participants might remember how they answered at T1
split-half reliability
- split measure into two halves and compute the correlation
- measures the internal consistency of a test
what is the advantage of split-half reliability? and when ist it good?
- is quick and easy to apply
- good if all items measure the same construct and there are many items
inter-rater reliability
- interrater reliability (also called interobserver reliability) measures the degree of agreement between different people observing or assessing the same thing
- assesses the external consistency of a test
content validity
Does the content of a measure make sense in terms of the construct being measured
face validity
- Concerns whether the measure seems valid to those who are taking it
- Not very essential from a measurement perspective.
- Sometimes one even wants to avoid it (e.g. implicit measures)
criterion validity
determines whether the measure is related to some behavioural outcome or criterion that has been established by prior research
predictive validity
whether the measure can accurately forecast some future behavior
concurrent validity
whether the measure can accurately predict present criteria
construct validity
- determines whether a test adequately measures some construct
- because constructs cannot be observed directly, construct validity has to be established indirectly
convergent validity
scores on a test measuring some construct should relate to scores on other tests that are theoretically related to the construct
discriminant validity
test measuring some construct should not be related to scores on other measures that are theoretically unrelated to the construct