Sampling, Experiments, and Observational Studies – Flashcards
Unlock all answers in this set
Unlock answersquestion
entire group of individuals/instances about one hopes to learn
answer
population
question
numerically valued attribute of a model for a population
answer
population parameter
question
list of individuals from who sample is drawn; any possible individual who has a chance of being selected in the sample
answer
sampling frame
question
representative subset of population--subjects actually polled/examined
answer
sample
question
study that asks questions of sample drawn from a population in hopes of learning about entire population
answer
sample survey
question
SYSTEMIC failure of a sampling method to represent its population
answer
bias
question
bias introduced when individuals can choose to participate of their own volition
answer
voluntary response bias
question
sampling scheme that biases sample in that it gives part of the population less representation than it has in the population
answer
undercoverage
question
when a large fraction of sampled individuals fail to respond (respondants not likely to represent entire population)
answer
nonresponse bias
question
anything in a survey design that influences responses (wording of questions)
answer
response bias
question
sample consisting of individuals conveniently available
answer
convenience sample
question
sample drawn by selecting individuals systematically from a sampling frame
answer
systematic sample
question
sampling schemes that combine several sampling methods
answer
multistage sample
question
entire groups (clusters) are chosen at random; usually used for convenience, practicality, or cost
answer
cluster sample
question
population is divided into several sub-populations (strata) and random samples are drawn from each stratum
answer
stratified random sample
question
each sample of size n is a sample in which each set of n elements in the population has an equal chance of selection
answer
simple random sample
question
sample consisting of entire population
answer
census
question
study based on data in which no factors have been manipulated
answer
observational study
question
(observational study) subjects selected and previous conditions or behaviors are studied
answer
retrospective study
question
(observational study) subjects are followed to observe future outcomes
answer
prospective study
question
manipulates factor levels to create treatments, randomly assigns treatments, then compares responses of subject groups
answer
experiment
question
specific values an experimenter chooses for a factor
answer
level
question
process, intervention, or other controlled circumstance applied to randomly assigned experimental units
answer
treatment
question
control, randomness, replication, and blocking
answer
principles of experimental design
question
experimental units assigned a baseline treatment level (placebo or similar)
answer
control group
question
when an individual associated with an experiment is not aware of how subjects have been allocated to treatment groups
answer
blinding
question
either those who could influence the results (subjects, treatment administrators, techs) or those who evaluate the results (judges, physicians) are blinded
answer
single-blind
question
both those who could influence results and those who evaluate them are blinded
answer
double-blind
question
gathering similar EXPERIMENTAL units together to isolate variability attributable to differences between blocks
answer
blocking
question
in a retrospective or prospective STUDY, subjects who are similar in ways under study may be matched and then compared to each other an the variables of interest
answer
matching
question
when levels of one factor are associated with levels of another factor in ways that their effects cannot be separated
answer
confounding
