Statistics How To

Intervening variable (Mediating Variable)

Types of Variable > Intervening Variable

What is an Intervening Variable?

An intervening variable (sometimes called a mediating variable) is a hypothetical variable used to explain causal links between other variables. Intervening variables cannot be observed in an experiment (that’s why they are hypothetical). For example, there is an association between being poor and having a shorter life span. Just because someone is poor doesn’t mean that will lead to an early death, so other hypothetical variables are used to explain the phenomenon. These intervening variables could include: lack of access to healthcare or poor nutrition.


Intervening variables are hypothetical constructs like personality, intelligence or attitude. As they are not “real” variables, one major limitation is that they cannot be measured. It is therefore impossible to quantify how much of the experimental results are due to the independent variables, and how much are due to each of the intervening variables.

Intervening and Independent/Dependent Variables

Boston University defines an intervening variable as “A control variable that follows an independent variable but precedes the dependent variable in a causal sequence.” So you could also look at intervening variables in terms of the independent variable and dependent variable; the intervening variable intervenes or mediates between the two. In the longevity example above, the independent variable is money (or lack of) and the dependent variable is longevity. Lack or access to healthcare or poor nutrition intervene, or fill the gap, between the independent and dependent variable.
intervening variables.


The term intervening was first used for variables by behavioral psychologist Edward C. Tolman in 1938 during studies on rat behavior for food rewards. He suggested that hunger was an intervening variable (it could not be observed during the actual experiments). Tolman’s work on intervening variables was an extremely important contribution to cognitive psychology as the concept made it possible to consider and measure unseen behaviors. Source: (, 2002)

An intervening variable is also called a mediating variable or intermediary variable.

Check out our YouTube channel for hundreds of basic statistics videos.


(n.d.). Edward c. tolman. Retrieved Dec 12 2016, from Web site:


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!
Intervening variable (Mediating Variable) was last modified: October 15th, 2017 by Stephanie

10 thoughts on “Intervening variable (Mediating Variable)

  1. Jayne Mageh

    which are the intervening variables in this title “Socio economic benefits of Merry Go round (Rotating and Savings credit associations) on household livelihoods among the urban.

  2. Andale Post author

    Hi, Jayne,
    Economics isn’t my forte. You would have to known what the links are between those credit associations and household livelihoods. For example, is it possible that membership to those associations is limited in some way? Maybe by work membership?

  3. Aril

    I have a problem in my theoretical framework section. The theory that I intend to employ suggests Domestic Factors to be Intervening Variable with Foreign policy as Dependent Variable. Whereas I wanna investigate Impact of Domestic Factors on Foreign Policy. So how Can I justify that the Intervening Variable in the Proposed theory is my Independent Variable??

  4. Andale Post author

    The intervening variable is a “hypothetical variable…used to explain a phenomenon.” You don’t need to justify an independent variable. That’s because you’ll be investigating it! A simpler example: you suspect that the intervening variable chlorinated water stunts plant growth. Does it *really* stunt plant growth? You test is by setting up an experiment. So you’re in the position of having an intervening variable (domestic factors) that you suspect affects foreign policy. The solution is to set up some kind of experiment. What that experiment would be is outside of my area of expertise (political science is not my forte). But I hope you get the idea.

  5. banke

    I had already coded 200 questionnaires when i realised that there was nothing to test for/ measure my dependent variables. What do I do?

  6. Andale Post author

    What are your null / alternate hypotheses?
    Assuming you know these, that you’ve coded correctly, and your data doesn’t help you answer those questions, then the answer is that you go back to the drawing board.

  7. Andale Post author

    I’m guessing here (I’m not a physician!) — maybe the carcinogens in the cigarettes? The number smoked per day?