Terms in this set (35)
Looks at relationships between two variables, but does not influence the response. Used to make guesses or inferences about the population.
The entire group about which we want information.
The subset of the population from which we collect information.
Only members of the population who are easily accessible are selected. Unlikely that the sample actually represents the population.
Certain outcomes are favored.
Voluntary response sample
People choose themselves to be in the sample. Often people with strong opinions respond.
Simple random sample
Individuals are chosen in a way that every set of the same size has an equal chance to be in the sample.
Stratified random sample
The population is divided into groups where members are alike, then a random sample is taken from each group.
The population is divided into groups that resemble the population. Then a random sample of groups is selected— each member of the chosen group is included in the sample.
Drawing conclusions about a population based on a sample.
Sample results vary from sample to sample.
Margin of error
How far off our sample results are from the truth about the population (includes both directions)
Errors that have to do with choosing the sample.
Some groups in the population are left out of the process. The same results may differ from the truth about the population.
Errors that occur after the sample has been selected.
An individual chosen for the sample can't be contacted or refused to participate.
Imposes a treatment to influence the response.
The variable being manipulated
The values of a factor.
The combination of factors and levels.
The value being measured.
A variable not included in a study that may confound the results.
When variables that can't be distinguished from each other both influence the response.
Objects on which treatments are imposed.
People on which treatments are imposed.
Experimental units are assigned to treatments using some type of chance process.
Completely randomized design
Every experimental unit has the same chance to be in each group.
A non-treatment group that provides a baseline for comparing the effects of the treatments. Not always necessary.
Using enough experimental units in each group so that any differences in the effects of the treatments can be distinguished from chance differences between groups.
Experimental results are caused by expectations alone.
One party knows, the other doesn't
neither the subject nor those who interact with them and measure the response variable know which treatment a subject received.
An observed effect so large that it would rarely occur by chance.
A group of experimental units that are known before the experiment to be similar in some way that is expected to affect the response to the treatments.
Matched pairs design
a type of block design for comparing two treatments in which similar experimental units are paired (the treatments are randomly divided within each pair) or individuals are compared to themselves (each individual experiences both treatments, usually in random order).