census
a sample that includes everyone and samples the entire population
sample statistics
summaries that are found from data in a sample
population inference
results from the sample that can be generalized to an entire population
casual inference (cause and effect)
the difference in responses is caused by the difference in treatments when comparing the results from two treatment groups
should only make a population inference when we have ______
random sampling
randomizing helps eliminate the effect of:
extraneous factors and bias
simple random samples (SRS)
each sample of size n in the population has the same chance of being selected
sampling variability
differences of samples lead to different values for the variables we measure
stratified random sampling
the population is first divided into different homogeneous groups, called strata; then take an
SRS within each stratum before the results are combined.
systematic random sampling
start from a randomly selected individual, then sample every kth person
-gives a representative sample
cluster random sampling
Splitting the population into similar groups (or clusters), select one or a few clusters at random
and perform a census within each of them.
- This sampling design is called cluster sampling.
bias
tendency for a sample to differ from the corresponding population in some systematic way
-selection bias
-response bias
-voluntary bias
-nonresponse bias
selection bias (undercoverage)
when some of the population is not sampled at all or has a smaller representation in the sample than it has in the population
response bias
refers to anything in the survey design that influences the responses
-responses may lie
voluntary response bias
occurs when individuals can choose on their own whether to participate in the sample
non-response bias
when a large proportion of those sampled fail to respond
we should only make casual (cause and effect) inferences when we have ________
random allocation
lurking variables
variables related to both group membership and the response
observational study
investigator observes individuals and measures variables of interest but does not try to influence the responses
retrospective study
individuals are sampled and information is collected about their past
-historical data is useful when an outcome is rare
prospective study
individuals are followed over time and data about them is collected as their characteristics or circumstances change.
-collect data as events unfold
random allocation/random assignment
individuals are randomly assigned to different treatment groups
we cannot make ______ inferences from observational studies
