# What is a test of independence?

I need to define what a test of independence is, without the use of heavily statistic terms.

I would start by defining what you mean by independence. For example,

If two variables are independent this means that knowing the value of one variable does not tell you anything about the value of the other variable.

Then I would describe the test:

To test for independence we construct a table of values that we would expect to see if the variables were independent. If we observed something "very" different from these expected values, we would conclude that the variables are unlikely to be independent.

• It rather does not change your knowledge about distribution of other variable. Definition of independence: P(Y|X)=P(Y). We know value of other variable only in rare cases of perfect prediction (correlation equals 1 or -1). Commented Aug 17, 2010 at 6:10

Why don't you take the definition of wikipedia. It's quite short und doesn't use heavily statistic terms.

A test of independence assesses whether paired observations on two variables, expressed in a contingency table, are independent of each other – for example, whether people from different regions differ in the frequency with which they report that they support a political candidate.