Experimentation

test or procedure carried out under controlled conditions to determine the validity of a hypothesis or make a discovery

Correlation

research that tests for a statistical relationship between two or more variables

Research

Involves a relationship among variables, but instead focuses on manipulating one of the variables to see if one has an effect on the other

Quasi-experiments

Usually related to demographic variables cannot be varied explicitly, and must be either selected during pre-sampling or from the sample you happen to get

Correlational

Confounding

Factor that is correlated or related to an IV that prevents you from concluding that your IV caused an effect that was observed, or perhaps prevents a true effect of the IV from showing up

Hypothesis

Testable prediction or possible explanation in an experiment, based on prior knowledge and/or observation

Null Hypothesis

Alternative Hypothesis

Implies that there was no observed effect on
the dependent variable in the experiment

Implies that there was an observable
effect in the experiment

Falsibility

Ability for a hypothesis or theory to be proven false

True Experiment

One in which a researcher manipulates one or more independent variables in order to measure the effect on a dependent variable

Randomly Assigned

Conditions selected, not participants

Placebo

Simulated treatment that lacks any active ingredient or element, and a placebo effect is a positive effect of such a treatment

A-B Testing

term used within advertising and usability design to describe simple experiments that compare a simple manipulation

Causation

Correlation

Logical relationship between events

Statistical measure of the relationship between two variables

Correlation does not mean causation!