Definition: Population
All individuals or items under consideration in a statistical study.
Definition: Sample
That part of the population from which information is collected.
Definition: Inferential statistics
methods for drawing and measuring the reliability of conclusions about a population based on information obtained from a sample of the population.
Definition: Probability sampling
Used to eliminate unintentional sample selection bias.
Definition: Simple random sampling (SRS)
Each possible sample of a given size is equally likely to be the one obtained.
Definition: Simple random sample
A sample obtained by simple random sampling.
SRS (simple random sample)
• With replacement - each item picked in a random sample can picked again in that random sample.
• Without replacement - each item picked in a random sample cannot be picked again in that random sample.
Definition: Representative sample
Should fit as close as possible to the population under study.
Definition: Census
A study on all items in a population
(There are other sampling procedures.)
Definition: Observational study
A study which establishes association through observation.
Definition: Designed experiment
A study which hopes to establish causation through design.
A designed experiment will include:
• Control group
• Treatment group
• Treatment
Principles of Experimental Design
Control: e.g., are there other factors that could be causing the outcome?
Randomization: separate groups should be as similar as possible to avoid unintentional bias
Replication: a sufficient number of subjects decreases the odds of "fluke" findings