Exam 1 Flashcards
Observational Study
observes individuals and measures variables, but doesn’t try to influence the response.
purpose of observational study
describe and compare existing groups or situations
experiments
actively impose a treatment on the subjects
purpose of experiments
study if a treatment causes a change in the response
confounding variables
variables thats effects on a response variable can’t be distinguished from each other
sample
the part of the population from which the the information is actually collected. samples are used to draw conclusions about the entire population
population
the entire group of individuals from which we want the information
sampling design
describes how a sample was chosen from the population
probability sampling
use chance to select a sample
simple random sample (SRS)
basic probability sample- it gives every possible sample of a given size the same chance to be chosen (can be done with software or random digits)
systematic random sampling
every __th individual is selected after the starting point
stratified random sampling
the population is divided into sub-populations and samples are chosen from each of those
multistage random samples
a simple random sample is chosen within a simple random sample (ex: a random classroom within a random school within a random state)
bias
systematic errors in the way the sample represents the population/ systematically favors certain outcomes
voluntary response samples
individuals can choose to participate. the problem is that mostly people with strong opinions would take the time out to participate
convenience sample
the easiest sampling design- the individuals close at hand are selected. the problem is that they cater to specific people (example: all the people are in the same economic class, being an inaccurate representation of the population)
sample surveys
observational studies of a random sample drawn from the population
cluster sample
populations are divided into groups and entire clusters/ groups are chosen at random to be in the sample
unblinded
both the experimenter and the subjects know which treatment is being administered
single blind
either the experimenter or the subjects know which treatment is being administered, but not both
double blind
neither the experimenter nor the subjects know which treatment is being administered
undercoverage bias
when some members of the population are not represented
self selection bias
when individuals choose to participate in a survey, leading to a sample with extreme views
nonresponse bias
when a significant amount of individuals selected for the sample do not respond, resulting in skewed results