Statistics Unit 3

Convenience sample

individuals in the sample are obtained by ‘proximity’ to the researcher

Voluntary sample

individuals have the choice to be included in the sample

Simple random sample (SRS)

each member of the population has an equal chance of being chosen for the sample

Stratified random sample

the population is separated into groups (strata) and an SRS is collected for each of the strata

Cluster sample

the population is separated into groups (clusters) and a RNG is used to select clusters where every individual in that cluster is sampled

Systematic random sample

A RNG is used to select a random individual (starting point) in the population and every nth individual is selected afterwards

Undercoverage

some people are less likely to be chosen

Nonresponse

people can’t be reached or refuse to answer

Response bias

problems in the data gathering instrument/process

Confounding variable

“extra” variable that affects both the response and explanatory variable

Observational study

no treatment imposed; can NOT prove causation

Experiment

treatment imposed; can prove causation

Experimental units

who/what the treatment is given to

Treatment

what is done/not done to the experimental units

Control group

doesn’t get treatment; used as a baseline

Single-blind experiment

either experimenter or experimental units don’t know who gets the treatments

Randomized block design

separate subjects into blocks and then randomly assign treatments within each block

Matched pairs design

subjects are placed in blocks of size two and then randomly assigned treatment