Week 2: Measuring Variables, Sampling, Validity and Reliability Flashcards
Population
Everyone the results will eventually be related to.
Sample
A segment of the population which has been selected to be used in the study.
Sampling Frame
A list of people which will be sampled from.
Statistic
Characteristic of the sample data.
e.g. sample mean, sample SD
Parameter
A numeric characteristic of the population data.
Sample error
An error which takes place when there is a difference between the value of the sample statistic and the value of the population parameter.
Probability sampling
A way of sampling which ensures that your sample is representative of the population.
Helps overcome sampling bias.
Simple random sampling
A probability sampling method where participants are selected at random. Each participant has an equal chance of being selected for the sample.
Systematic random sampling
A probability sampling method in which participants are selected with a random starting point but with fixed, periodic intervals.
Stratified random sampling
A probability sampling method in which the population if divided by different subpopulations (strata) then a random sample is taken from each group.
Multi-stage cluster sampling
A probability sampling method in which the population is divided in subgroups, but samples are not necessarily taken from all subpopulations.
Non-probability sampling
Not every member of the population has an equal chance of being included in the sample
Convenience sampling
Non-probability sampling method.
A sample is taken from all available participants.
Pros: easy, inexpensive
Cons: no control over representatives, and bias
Snowball sampling
Non-probability sampling method.
Involves collecting data from targeted members of the population, then asking those members to provide information/contacts for other members of the population.
Used to study hard populations
Quota sampling
Sample groups are divided into subgroups and samples are selectively taken.
Non-probability equivalent of stratified random sampling.
Purposive/judgement sampling
Non-probability sampling method.
Selecting individuals who meet criterion of study.
Face Validity
on face-value this measure seems to relate to the construct
content validity
captures the entire meaning (all elements of definition) of a construct
Criterion validity
agrees with external source
Concurrent validity
agrees with pre-existing “gold-standard” measure
Predictive validity
agrees with future behaviour
Constructive validity
how well multiple indicators relate to each other (consistent with theory)
Convergent validity
Similar measures (or measures of theoretically related constructs) are related
Divergent validity
Different measures (or measures of theoretically unrelated constructs) are unrelated
Test-retest reliability
same questions given on two occasions and data correlated
Split Half reliability
split questions in half and correlate data from two halves
Conbach’s Alpha reliability
equivalent to average of all possible split-half reliabilities for that test with that sample
Inter-rater reliability
checking for agreement between multiple raters or judges
