The notion of making any decisions without know something about the cost of that decision, the schedule impacts or the resulting impacts on delivered capabilities is like the guys here in the picture. They stared building their bridge. Will run out of materials, can't see the destination and likely have the wrong tools.
The continued insistence that we can make decisions in the absence of estimates needs to be tested in the market place by those providing the money, not by those consuming the money.
When mentioned that cost can be fixed through a budget process, this still leaves the schedule and delivered capabilities as two random variables that need to be estimated if we are to provide those funding our work with a credible confidence that we'll show up on time with the needed capabilities.