[Those] who have an excessive faith in their theories or in their ideas are not only poorly disposed to make discoveries, but they also make very poor observations.

A contemporary poet has characterized this sense of the personality of art and of the impersonality of science in these words,-'Art is myself; science is ourselves. '

As soon as the circumstances of an experiment are well known, we stop gathering statistics. ... The effect will occur always without exception, because the cause of the phenomena is accurately defined. Only when a phenomenon includes conditions as yet undefined,Only when a phenomenon includes conditions as yet undefined, can we compile statistics. ... we must learn therefore that we compile statistics only when we cannot possibly help it; for in my opinion, statistics can never yield scientific truth.

We must alter theory to adapt it to nature, but not nature to adapt it to theory.‎

When a physician is called to a patient, he should decide on the diagnosis, then the prognosis, and then the treatment. ... Physicians must know the evolution of the disease, its duration and gravity in order to predict its course and outcome. Here statistics intervene to guide physicians, by teaching them the proportion of mortal cases, and if observation has also shown that the successful and unsuccessful cases can be recognized by certain signs, then the prognosis is more certain.

The investigator should have a robust faith - and yet not believe.

Even mistaken hypotheses and theories are of use in leading to discoveries. This remark is true in all the sciences. The alchemists founded chemistry by pursuing chimerical problems and theories which are false. In physical science, which is more advanced than biology, we might still cite men of science who make great discoveries by relying on false theories.