Chapter 4 Flashcards
Designing Studies
Census
ask EVERY member of a population
Sample
the part of the population
Sampling
selection of a subset of individuals from within a population to estimate characteristics of the whole population
Simple Random Sample (SRS)
each individual has an equal chance of being selected, each possible sample has an equal chance of being selected
Stratified Sampling
each strata contain similar individuals, there are large differences between the strata. Choose a SRS in each strata to form the full sample
Cluster Sampling
Divide the whole population into small groups that mirror the population (clusters). Choose a SRS of the clusters. All individuals in selected clusters are sampled.
convenience sampling
target the easiest individuals to reach (not random)
Voluntary Response Sampling
people choose to respond to the question themselves
Random sampling error (sampling error)
you collected a SRS but by accident your sample ends up not being very random
Undercoverage (sampling error)
a segment of the population is left out of the sample
Non-Response (non-sampling error)
A person is chosen to be in the sample but is unavailable, won’t respond
Response Bias (non-sampling error)
A person in the sample gives an incorrect or untrue response
Wording (non-sampling error)
wording of questions are confusing or leading/loaded
observational study
observes individuals but does not try to influence the response, cannot establish cause and effecte
Experiment
imposes a treatment, the determine whether the treatment causes a change in response