All models are approximations. Essentially, all models are wrong, but some are useful. However, the approximate nature of the model must always be borne in mind.

One important idea is that science is a means whereby learning is achieved, not by mere theoretical speculation on the one hand, nor by the undirected accumulation of practical facts on the other, but rather by a motivated iteration between theory and practice.

Just as the ability to devise simple but evocative models is the signature of the great scientist so overelaboration and overparameterization is often the mark of mediocrity.

Remember that all models are wrong; the practical question is how wrong do they have to be to not be useful.

Statistics is, or should be, about scientific investigation and how to do it better, but many statisticians believe it is a branch of mathematics. Now I agree that the physicist, the chemist, the engineer, and the statistician can never know too much mathematics, but their objectives should be better physics, better chemistry, better engineering, and in the case of statistics, better scientific investigation. Whether in any given study this implies more or less mathematics is incidental.

The old-fashioned idea of a good manager is one who is supposed to know all the answers, can solve every problem himself, and can give appropriate orders to his subordinates to carry out his plans... A good modern manager is like a good coach who leads and encourages his team in never-ending quality improvement.

To find out what happens to a system when you interfere with it you have to interfere with it (not just passively observe it).