Statistics How To

Manipulated Variable: Definition

Types of Variable > Manipulated Variable

What is a Manipulated Variable?

A manipulated variable is the independent variable in an experiment. It’s called “manipulated” because it’s the one you can change. In other words, you can decide ahead of time to increase it or decrease it. In an experiment you should only have one manipulated variable at a time.

The manipulated variable is the independent variable in an experiment.

The manipulated variable is the independent variable in an experiment.

An experiment generally has three variables:

  1. The manipulated or independent variable is the one that you control.
  2. The controlled variable is the one that you keep constant.
  3. The responding variable or variables is what happens as a result of the experiment (i.e. it’s the output variable).

Example: You want to find out what the effect is of changing lesson lengths is on student exam performance. The manipulated variable would be the lesson times, as that’s what you’re going to change. Controlled variables would be things like ensuring the exam times are the same, or that the students aren’t hungry (perhaps they should all be tested at the same time). The responding variable is exam success, measured by actual scores on exams.

Manipulated Variables in Process Control

In process control there are two types of input variables: manipulated variables and disturbance variables. In this context, the manipulated variable is the input that is controlled by the process operator or control system. The manipulated variables are adjusted by the process operator (or control system) to keep the controlled variables in the system at constant settings. The disturbance variable is a second type of input, and it affects the process outputs. However, unlike manipulated variables they can’t be adjusted by the control system.

As a simple example, let’s say you wanted to keep speed constant in a car. External factors like acceleration, friction or tire pressure cause it to change. An accelerator (gas pedal) can keep the speed constant — figuring out when to use the accelerator is the control. The state of the accelerator is the manipulated variable. The process is speeding up, via the accelerator and the speed itself is the controlled variable.

------------------------------------------------------------------------------

If you prefer an online interactive environment to learn R and statistics, this free R Tutorial by Datacamp is a great way to get started. If you're are somewhat comfortable with R and are interested in going deeper into Statistics, try this Statistics with R track.

Comments are now closed for this post. Need help or want to post a correction? Please post a comment on our Facebook page and I'll do my best to help!
Manipulated Variable: Definition was last modified: October 15th, 2017 by Stephanie Glen

17 thoughts on “Manipulated Variable: Definition

  1. Andale Post author

    Maddie, thanks for your comment. We are always up for improvement :) Anything in particular you feel is missing?

  2. Andale Post author

    Hi, Sajad,
    Could you point me to the place where you get confused? For example, was there a specific sentence you found confusing?
    Thanks!

  3. Andale Post author

    I’ve never heard of an error variable. Could you give me some more context about where you found that term?

  4. Olanrewaju Kamiludeen

    Why do we assume that all manipulated variables are measurable? Is this assumption correct and how do we use the values of manipulated variables in a control system?

  5. Andale Post author

    If you can’t measure a manipulated variable, how could you tell if your experiment was a success or failure? (You couldn’t). I’m adding a little more to the article about how these variables are used in a control system. Thanks for the question :)

  6. Olanrewaju Kamiludeen

    Thanks for the answer,pls I still need answer to how to find the number of alternative loop configurations for a process with N controlled variables and M manipulated variables, where M>N