4.1
A ______ gives every possible sample of a given size the chance to be chosen.
A simple random sample (SRS) gives every possible sample of a given size the chance to be chosen.
In an experiment, we impose one or more ______ on a group of _________.
In an experiment, we impose one or more treatments on a group of experimental units.
When the observed results of a study are too unusual to be explained by chance alone, we say that the results are __________.
When the observed results of a study are too unusual to be explained by chance alone, we say that the results are statistically significant.
To use ___________, divide the population into groups of individuals called _____ which are similar in some way that might affect their responses.
To use stratified random sampling, divide the population into groups of individuals called strata which are similar in some way that might affect their responses.
Some experiments give a ________ (fake treatment) to a ________ group, whereby some patients get better because they expect the treatment to work.
Some experiments give a placebo (fake treatment) to a control group, whereby some patients get better because they expect the treatment to work.
____________ requires that the individuals taking part in a study be randomly selected from the population.
____________ requires random assignment of treatments.
Inference about a population requires that the individuals taking part in a study be randomly selected from the population.
Inference about cause and effect requires random assignment of treatments.
To use ________, divide the population into groups of individuals that are located near each other, called _______.
To use cluster sampling, divide the population into groups of individuals that are located near each other, called clusters.
A __________ forms groups of experimental units that are similar with respect to a variable that is expected to affect the response.
A randomized block design forms groups of experimental units that are similar with respect to a variable that is expected to affect the response.
_______ refers to the idea that different random samples of the same size from the same population produce different estimates.
Sampling variability refers to the idea that different random samples of the same size from the same population produce different estimates.
When people can't be contacted or refuse to answer, we call this ________.
When people can't be contacted or refuse to answer, we call this nonresponse.
Keep other variables the same for all groups. Helps avoid confounding and reduces the variation in responses, making it easier to decide if a treatment is effective.
Keep other variables the same for all groups. Helps avoid confounding and reduces the variation in responses, making it easier to decide if a treatment is effective.
Control
Any information about the individuals in a study must be kept ________.
Any information about the individuals in a study must be kept confidential.
This happens when some members of the population are less likely to be chosen or cannot be chosen for the sample:
This happens when some members of the population are less likely to be chosen or cannot be chosen for the sample: Undercoverage
A common form of ______________ for comparing two treatments is _____________ design. Sometimes each subject receives both treatments in a random order. In others, two very similar subjects are paired and randomly assigned treatments within the pair.
A common form of randomized block design for comparing two treatments is matched pairs design. Sometimes each subject receives both treatments in a random order. In others, two very similar subjects are paired and randomly assigned treatments within the pair.
What are 5 criteria that can be used for establishing causation when a well-designed experiment is not possible?
What are 5 criteria that can be used for establishing causation when a well-designed experiment is not possible?
Strong association
Consistent association
Larger explanatory variables -> larger responses
Cause precedes effect in time
Cause is plausible