Independent Variable: Predicting the Response Values

alpharithms wallpaper

Independent variables describe values that are unchanged by other values within the context of a given experiment. These variables are commonly used to describe measures of time or distance. For example, when measuring the human population—time is the independent variable and population count is the dependent.

Independent variables are often denoted as X and placed on the horizontal axis when charted. Of course, this is not always the case and varies from experiment to experiment. One rule of thumb to remember is that independent variables are those that an experimenter can manipulate. Consider the illustration below:

indpendent vs dependent variables histogram sample
This chart illustrates an independent variable on the x-axis and a dependent value on the y-axis

Different Naming Conventions

Independent variables may be referred to by several other names depending on the context of experimentation. The field of statistics, in particular, is known to use a wide range of context-dependent names for the independent variable (Upton, 2014):

  • Target Variable – machine learning (supervised), data mining
  • Regular Variable – machine learning
  • Predictor Variable
  • Regressor
  • Explanatory Variable
  • Exposure Variable – reliability theory
  • Risk Factor – medical statistics
  • Feature – Machine learning
  • Input Variable – general terminology
  • Control Variable

In addition to these, there are still plenty of other context-derived terms that ultimately serve to describe independent variables. Whether a study, analysis, or presentation uses any of the above terms know the reference is to the independent variable.

References

  1. Upton, Graham, and Ian Cook. A Dictionary of Statistics 3e. Oxford, United Kingdom, Oxford University Press, 2014.
Zack West
Entrepreneur, programmer, designer, and lifelong learner. Can be found taking notes from Mother Nature when not hammering away at the keyboard.