UX Recorder: Screen capturing software for iOS. Learn more.

Glossary » experiment

experiment

an empirical study designed to relate cause and effect by ruling out as many alternative causes as possible and by actually manipulating the cause to obtain the effect, as opposed to merely finding a correlation between the two that may not be due to causation.

Experiments come in many forms, but a prototypical example is to try to determine if some change will result in an improvement. For instance, if I add a certain button to my word processor, will people be able to write their documents faster. In this example you would have an “experimental condition”, using the word processor with the button added, and a “control condition”, using the word processor without the button. The “independent variable” is the factor you are manipulating, whether or not the button is present. The “dependent variable” is what you are measuring to determine the effect, in this case, the amount of time to produce the same document with each version of the word processor.