Chapter 5: Producing Data Flashcards
Observational study
Observes individuals and measures variables of interest but doesn’t attempt to influence the response
Experiment
Deliberately imposes some treatment on individuals in order to observe they’re responses
Can help eliminate or reduce the effects of lurking variables
Population
Entire group of individuals
Census
Attempting to use every member of the population
Sample
A subgroup of the population
Sampling
Studying a part in order to gain information about the whole
Voluntary response sample
People who chose to be a part of the sample by responding to a general appeal
Convenience sample
Involves choosing the most convenient individuals from a population for your sample
Sample bias
When a sampling system systematically favors certain outcomes
Simple random sample (SRS)
A sample size n is selected in such a way that every individual in the population has an equal chance of being selected
Stratified random sample
1) Divide the population into groups (or strata) of similar individuals
2) Choose a separate SRS for each strata
3) Combine all chosen individuals into the full sample
Cluster sample
1) Divide the population into groups or clusters
2) Randomly select some clusters
3) All individuals from the clusters make up the sample
Multistage sample design
Select successively smaller groups within a population in stages, resulting in a sample consisting of clusters of individuals
Systematic Sample
Inspecting by pattern (i.e. Every 25th unit)
Probability sample
Each member of the population has a chance to be selected (not equal chance necessarily)
Undercoverage
Occurs when some groups in the population are left out of the process of choosing the sample (think a Venn diagram that is not a circle where one circle is the population and the other is the group were taking a sample of)
Nonresponse
An individual does not respond
Response bias
When an individual chooses the survey answer they believe to be best rather than what’s true
Wording of question
May influence a person by leading an individual to a given answer
Experimental Units
Individuals on which the experiment is being done
Treatment
A condition applied to the units
Factors
Explanatory variables
Randomized comparative experiment
An experiment that has random assignment and a control or comparison group
Statistically significant
Observed affect too large to be due to chance
Placebo effect
When a change occurs even when a subject is not given the treatment and only believes they are
Block
A group of units that are determined to be similar before the experiment in a way that may affect the results
Matched pairs design
1) subjects are matched with themselves and receive the treatment in random order
2) subjects are matched with others and receive different treatments
