Never make a calculation until you know the answer. Make an estimate before every calculation, try simple physical argument, (symmetry!, invariance!, conservation!) before every derivation., guess the answer to every puzzle.
Courage: no one else needs to know what the guess is. Therefore make it quickly, by instinct. a right guess reinforces this instinct. A wrong guess brings the refreshment of surprise. In either case life as a speculative expert, however long, is more fun.
From Taylor and Wheeler, Spacetime Physics, page 60.
This is not only how one becomes an expert on estimation, but also how one avoids embarrassing mistakes. Estimation must be trained, one must develop and calibrate mental models. It requires practice, feedback, and repetition.
When you can do this, you also find that a lot your detailed calculations have mistakes. Poor models are exposed, Early on, only a rough estimate is needed. Do it quickly. If your detailed estimate is very different, look at both the rough estimate and your detailed estimate. Try to learn why they differed. You may be surprised.
I saw a fragment following of a link from eight2late so I dug out my copy of Spacetime Physics, to remind myself of exactly what Wheeler said. Glen Alleman also referenced Wheeler’s rule recently, along with a nice picture of John Archibald Wheeler.