Variable

A variable represents a class of outcomes that can take on more than one value. For example, car make is a variable that can take on the values of Pontiac,[Page 1036] Volvo, or Chevrolet, among others. Other examples of variables are height (expressed as short or tall or 5 feet or 6 feet, etc.), income (expressed as more than $60,000 or less than $60,000, for example), age at menarche, number of badges earned, time in rank, speed for the 100-yard dash, and favorite type of food. All these characteristics can take on any one of several values.

Table 1 Types of Variables
Type	Definition	Other Terms You Might See
Dependent variable	A variable that is measured to see whether the treatment or manipulation of the independent variable had an effect	Outcome variable Results variable Criterion variable
Independent variable	A variable that is manipulated to examine its impact on a dependent variable	Treatment Factor Predictor variable
Control variable	A variable that is related to the dependent variable, the influence of which needs to be removed	Restricting variable
Extraneous variable	A variable that is related to the dependent variable or independent variable and that is not part of the experiment	Threatening variable
Moderator variable	A variable that is related to the dependent variable or independent variable and has an impact on the dependent variable	Interacting variable

Table 1 lists types of variables, definitions, and alternative terms for the variables.

The two most important variables are dependent and independent variables.

A dependent variable represents the measure that reflects the outcomes of a research study. For example, if the difference between two groups of adults on how well they can remember a set of 10 single digits after a 5-hour period is measured, the number of digits remembered is the dependent variable.

A dependent variable is the outcome measure that depends on the experimental treatment or on what the researcher changes or manipulates.

An independent variable represents the treatments or conditions that the researcher controls, either directly or indirectly, to test their effects on a particular outcome. An independent variable is also known as a treatment variable; it is in this context that the term treatment is most often used. An independent variable is manipulated in the course of an experiment to understand the effects of this manipulation on the dependent variable.

For example, the effectiveness of three different reading programs on children's reading skills may be tested. Method A includes tutoring, Method B includes tutoring and rewards, and Method C includes neither tutoring nor rewards (these kids just spend some time with the teacher). In this example, the method of reading instruction is manipulated, and it is the independent variable. The outcome, or dependent, variable could be reading scores. This experiment includes three levels of one independent variable (method of teaching) and one dependent variable (reading score).

The distinction between direct and indirect manipulation of the independent variable(s) has to do with whether the researcher actually creates the levels (such as Method A, Method B, and Method C above) or whether the levels occur naturally and cannot be manipulated directly but only tested. Examples of naturally occurring variables include differences such as gender (we cannot very well assign that trait to people) or age (we cannot make people younger or older).

...