The risk is small, because for most CDs the withdrawal penalty is small. My credit union allows partial withdrawals and charges a fee of 6 months’ interest (about 0.625%) on the amount withdrawn, so if the market tanks 30% and you have to redeposit say 20% into the margin account, you have lost a negligible 0.125% and the box spread trick still comes out ahead for the year. 6 months’ interest is typical. It’s important to choose a bank or credit union that has reasonably lenient terms, though.
The risk is small, but so is the benefit. As a result this was not a trivial analysis for me. I doubt if it’s low risk to redeposit just 20% at a 30% market drop due to volatility (the recent intraday crash movements exceeded 10%, and you get a margin call at a 40% with the 250k/150k example). After mulling it over I think I agree that it is worth it anyways though.
Here’s some more examples that I ran over. A better person would figure out the probabilities and equations to integrate over to calculate the expected value.
Withdrawing 75% at 0 months should be the break even (you lose .625% * 37.5k = 700 to penalties, but you get back a bit more than that with interest of .625% * 112.5k * 3 years = 700).
If you don’t need to withdraw within the first 6 months, you are ahead. Let’s look at the 100 percentage withdrawal case first to keep it simple. So the actual break even is withdraw 100% at month 6, and any time before this you lose money. If this happens at day 0 you lose .625% * 150k, or .375% of your portfolio as the worst case scenario. So the interesting loss scenarios range from 75% immediately to 100% in 6 months.
I don’t have the probabilities of these events happening, but casually looking at it, it seems like they happen at a significantly lower probability than the equal or greater gains case. Though it should reduce your expected value by a small amount.