Difference between extraneous and confounding variables examples
A confounding variable (a.
lurking variable) is a phenomenon that isnt being measured (extraneous to your data set) that has a high degree of correlation with both your dependent variable and one or more of your independent variables.
,For example, say youre studying the relationship, in a wide sample, between scores on a general knowledge test and number of hours spent on Quora per week.
You find a high positive correlation -- clearly spending time on Quora makes you really knowledgeable! But it may in fact be that people with more years of schooling do better on the test, and people with more years of schooling also spend more time on Quora.
,For more examples and a more rigorous discussion of different types of confounding, see the Wikipedia article: Confounding.
Confounding variables Psychology
Confounding Variables are factors other than the Independent Variable that affect the Dependent Variable.
For example, in study to test how far a ball can travel, the Independent Variable would be the force applied to the ball and the Dependent Variable would be the distance the ball travels.
A Confounding Variable can be the fact that the ball is on a slanted piece of wood which would ensure a longer distance traveled, ultimately affecting the outcome of the experiment, or the Dependent Variable.
Confounding variable in research
Confounded variables are those whose effects cannot be distinguished from the effects of the independent variables.
Hereu2019s an example.
Suppose that people who are better educated are also healthier.
This might mean that their knowledge somehow leads them to make healthier choices.
But, people who are better educated also typically make more money and, thus, have better health insurance.
Maybe the reason they are healthier is simply because they have better insurance.
Because wealth and education covary (move in predictable ways relative to each other), they are confounded.