| A | B |
|---|
| population | entire group of ind. we are concerned with |
| sample | representative subset of a population |
| sample survey | study that asks question of a sample drawn from some population in hope of learning something about the entire popultion |
| Bias | systematic failure of a sampling method to represent its population is bias |
| common errors that inroduce bias | voluntary response, undercoverage, nonresponse, response |
| randomization | best defense against bias |
| matching | any attempt to force a sample to resemble specified attributes |
| census | sample consisting of entire population |
| population parameter | rearely expect to know this - hope to est. from sample |
| statistic | values calculated from sample data |
| SRS | each set of n elements in the population has an equal chance of selection |
| sampling frame | list of individuals from whom the sample is drawn |
| sampling variability | natural tendency of randomly drawn samples to differ from each other |
| stratified random sample | divide pop. into subgroups and sample subgroups |
| cluster sample | census of a randomly selected group |
| multistage sample | combine several methods |
| systematic sample | every nth item or person |
| voluntary response bias | individuals can choose whether to participate - always biased |
| convenience sample | not representative because every ind. in pop. is not equally convenient to sample |
| undercoverage | leaves part of pop. underrepresented by sample |
| nonreponse bias | bias introduce when a large fractin of those sampled fail to respond |
| response bias | anything in survey design that influences responses |
