I want to perform a test for correlation between the variance of one measurement with different values of a control variable, to the mean (or variance) of another measurement under the same control variable values.

My specific problem is this: under a certain set of conditions (call them A and B), I am measuring the packet delay between two computers. I have about a million measurements for condition A, and another million for condition B. Then, I have another experiment that measures synchronization between the computers, which takes a number of packets exchanged, so it is probably related to the first experiment. The second experiment is conducted under conditions A and B, and has the same number of measurements each (about 1 million).

I want to conduct a set of tests to determine whether there is a correlation, and with what confidence. I *think* that a high variance in the first experiment will result in a higher mean of the second experiment. Can anyone suggest what tests I need to research?

Thanks in advance.