I think you're overestimating the marginal cost of doing one of them after you've already done the other. If a company has a bunch of ad-buying customers and a bunch of transparent ads, putting together some work to make a bunch of opaque ones for the exact same customers is not necessarily going to be that hard. I don't see how you can claim that it's mathematically guaranteed that the number of customers who decide that they'd pay more to have both is not enough to make that work turn a profit.
First that i should have said correlated rather than proportional.
Second that even if there's an inverse influence, there's also a positive influence between both forms of advertisement.
But in terms of proportion I still maintain that if you eliminate one type of advertisement the ratio will become 100% of the other, which is as undeniable as it is tautological.
