The only time I think people should drop out of college is if they're building a company that's becoming crazy successful and making a boatload of money to the point that running that business makes more sense then college.
One data point: Mark Zuckerberg did not drop out of Harvard when he left to do Facebook. He took a leave of absence and he did not permanently drop out until November 2005, by which time Facebook was well on its way to success, with a 100MM valuation and a position as the 10th most trafficked website.
So at least for him, he was probably pretty sure of his success (a cushy acquisition as the very least).
Although true that they couldn't have been sure, they were better off than 99% of dropouts. Zuckerberg was just taking a leave of absence and planned on returning. Before entering Harvard, he had already been noted on Slashdot and in PC Magazine. Gates entered with a nearly perfect SAT course and took the legendary Math 55 course. (http://en.wikipedia.org/wiki/Math_55)
In other words, they were already exceptional before dropping out. That key point gets lost a lot of times. I think the exception is probably Jobs and WoZ.
> Risk is high almost always, with some exceptions.
The exception is taking on high risk with your startup.
I can imagine a pretty low risk scenario where you finish school, and start working in a relevant field programming. As you're making money and learning valuable skills you can spend your free time building your business. Unlimited runway and learning from your day job would increase your probability of being successful massively.
The billionaires and facebooks of the world are bad data points to model your future success by.
When it comes to startups there are no guarantees. Risk is high almost always, with some exceptions.