Deductivism in mathematical literature and inductivism in scientific papers are simply the postures we choose to be seen in when the curtain goes up and the public sees us. The theatrical illusion is shattered if we ask what goes on behind the scenes. In real life discovery and justification are always different processes. . . . Methodologist who have no personal experience of scientific research have been gravely handicapped by their failure to realize that nearly all scientific research leads nowhere — or if it does lead somewhere, then not in the direction it started off with. In retrospect, we tend to forget the errors, so that "The Scientific Method" appears very much more powerful than it really is, particularly when it is presented to the public in the terminology of breakthroughs, and to fellow scientists with the studied hypocrisy expected of a contribution to a learned journal. I reckon that for all the use it has been to science about four-fifths of my time has been wasted, and I believe this to be the common lot of people who are not merely playing follow-my-leader in research. . .science in its forward motion is not logically propelled. . . . The process by which we come to formulate a hypothesis is not illogic, but non-logical, i.e., outside logic. But once we have formed an opinion, we can expose it to criticism, usually by experimentation; this episode lies within and makes use of logic.
"Induction and Intuition in Scientific Thought," American Philosophical Society, Philadelphia, 1969, cited in A History of Immunology by Arthur Silverstein, page xviii-xiv