The p-value merely indicates that there is something going on, but it does not tell you the strength of any correlation. Having a p-value smaller than 0.05 indicates that there is fewer than a 5 out of 100 chance of getting the results that you had obtained at random, so it implies that there is probably SOME sort of relationship between the independent variable - jelly bean color, and the dependent variable - incidence of acne. Assuming we are looking at interval or scalar data from the acne incidents, compared to nominal data in the color of the jelly beans, a regression analysis could be run to obtain Pearson's correlation coefficient (r) that gives the strength of the pull of one variable on the other, and if you square that value, you get the R-squared value or proportional reduction in error, with which if you know the color of the jelly bean, your guessing as to whether or not a person will develop acne will improve by X percent.

Now THAT information would make for a good sensationalist headline.

snort snort

But remember, Chad, Pearson's r is a dirty whore. She opens her legs for everyone. You'd probably want to use one of the many other correlation tests to identify the strength and direction of the correlation.

We haven't learned about Pearson's r yet. In fact, I know how to calculate p values, but I still don't know what they mean because our professor doesn't really tell us.

Still got a 50/50 on my last exam, though.

Rather, you've done a better job of explaining what a p value indicates than my professor ever has.