Quotations compiled by Gordon Hilton Fick

An experiment is a considered course of action aimed at answering one or more carefully framed questions. (W.J. Youden)

It is a mistake to believe that research is done in the laboratory. It is done in the head; the laboratory merely confirms or rejects what the mind conceives. Wisdom consists not so much in knowing the right answers, as in knowing the right questions to ask. If we lack concept, we run the risk of monumentally achieving what was not worth doing in the first place. (Sidney Harris)

It does not follow that if quantitative methods be indiscriminately applied to inexhaustible quantities of data, scientific understanding will necessarily emerge. (M.K. Hubbert)

...results very often [are] merely a demonstration of our ignorance and a clearer statement of what we do not know. (Gunnar Myrdal)

You will meet with several observations and experiments which will disappoint your expectation, either not at all succeeding constantly, or at least varying much from what you expected. (Robert Boyle)

Statistical theory deals, paradoxically, with minimizing or controlling by design as much of the variation as is possible while using the remainder of the variation as a device to weigh experimental evidence. (J.L. Gill)

Truth is so large a target that nobody can wholly miss hitting it, but at the same time, nobody can hit all of it with one throw. (Aristotle)

...statistics are like garbage: one should have in mind what is to be done with the stuff before collecting it. (Mark Twain)

"Data! Data! Data!" he cried impatiently. "I can't make bricks without clay". (Sherlock Holmes)

The country is hungry for information; everything of a statistical character, or even statistical appearance, is taken up with an eagerness that is almost pathetic; the community have not learned to be half-sceptical and critical enough in respect to such statements. (F.A. Walker)

Nous devons croire au hasard. Autrement, comment pourrions-nous expliquer le succes de ceux que nous n'aimons pas? (Jean Cocteau)

Observation is a passive science, experimentation is an active science. (Claude Bernard)

People in general have no notion of the sort and amount of evidence often needed to prove the simplest matter of fact. (Peter Mere Latham)

Statistical thinking will one day be as necessary for efficient citizenship as the ability to read and write. (H.G. Wells)

He uses statistics as a drunken man uses lampposts - for support rather than for illumination. (Andrew Lang)

Don't ask what it means, but rather how it is used. (L. Wittenstein)

Writing and talking obscurely is the refuge and disguise of incompetence. (A.L. Kitselman)

He that leaveth nothing to chance will do few things ill, but he will do very few things. (Marquis of Halifax)

No statistics should stand in the way of an experimenter keeping his eyes open, his mind flexible, and on the lookout for surprises. (William Feller)

Man has a capacity that is nearly infinite for reading the evidence in the light of his own interests and passions. (Donald Price)

The goal of science is the systematic organization of knowledge about the universe on the basis of explanatory principles that are genuinely testable. (F.J. Ayala)

The advantage of a certain amount of ignorance is that it keeps you from 'knowing' that the results that you observe 'could not have happened'. (Hopkinson)

An erroneous assumption of ignorance is not innocuous. (R.A. Fisher)

Men have been martyred for the difference between two wrong answers. (A.J. Moroney)

Inspiration has never been known to descend on a committee. (Halmos)

Until the phenomena of any branch of knowledge have been submitted to measurement and number it cannot assume the dignity of a science. (Francis Galton)

How is it possible for a population to remain alike in its features, as a whole, during many successive generations, if the average produce of each couple resemble their parents? Their children are not alike, but vary: therefore some would be taller, some shorter than the average height; so among the issue of a gigantic couple there would be usually some children more gigantic still. Conversely as to very small couples. But from what I could thus far find, parents had issue less exceptional than themselves. (Francis Galton)

...during the many years I have been responsible for the analysis of split plot experiments I have never considered the two components [of subplot error] worth separation...it may be noted that [] arguments [for separation] have really little to do with split plots. The same partition of error d.f. can be made in an ordinary AXB factorial experiment, and the same confused situation would arise if [the] arguments were valid. (Frank Yates)

...as a matter statistical decency, we never average things that differ through more than error. To do so is to distort and deceive. (D.B. DeLury)

...[a], rather extreme, view shows itself occasionally: If the replications sum of squares is not significant, it may be pooled with the error sum of squares to augment the degrees of freedom allotted to error. This kind of self indulgence is intolerable. It is simply a way of saying: Choose the error you like best. (D.B. DeLury)

It should not be necessary to emphasize that the criteria for blocking must be based on dependable knowledge, presumably gained through prior experience. Irresponsible blocking can be costly and even calamitous. (D.B. DeLury)

An exercise that makes no provision for the definition and estimation of error cannot properly be called an experiment. (D.B. DeLury)

...if this example is the only one that makes {Neyman} doubt the adequacy of his well-established theories, he is, I am sure, entitled to think again, and I hope most sincerely that he will do so. (E.C. Fieller)

Bias [can be defined as] weighing the facts with your thumb on the scale. (Leo Aikman)

...those who are not accustomed to original enquiry entertain a hatred and horror of statistics...but it is the triumph of scientific men...to desire tests by which the value of beliefs may be ascertained, and to feel sufficiently masters of themselves to discard contemptuously whatever may be found untrue. (Francis Galton)

The chosen null hypothesis is often such that no rational man could seriously entertain it. (A.W.F. Edwards)

The greatest and noblest pleasure which man can have in this world is to discover new truths; and the next is to shake off old prejudices. (Frederick the Great)

Results! Why man, I have gotten a lot of results. I know several thousand things that won't work. (Thomas Edison)

...when mathematical language is used to model natural phenomena, considerable distortion, often spoken of politely as simplification, or approximation, is inevitable. (J.G. Skellam)

...the optimum is a slowly evolving dialogue between vague concept and mathematically precise notion. (John Tukey)

Theory without fact is fantasy, but fact without theory is chaos. (Anonymous)

A regression coefficient can be invaluable for purposes of estimation, but it does not provide the material out of which scientific laws are fashioned. (S.C. Pearce)

Not ignorance, but ignorance of ignorance is the death of knowledge. (Whitehead)

Sometimes the greatest wisdom is shown by refusing to start an experiment because the number of animals available are insufficient to secure a reliable result. (H.H. Holman)

Logic, precision, explicitness, agreement with experience, usefulness for deductions...determine whether a new mental construct becomes science or science fiction. (Ernst Cohn)

Many a study, launched on the ways of elegant statistical design, later boggled in execution, ends up with results to which the theory of probability can contribute little. (W.E. Deming)

[this collection of my papers has] severely practical orientation, as is to be expected when the subject is being developed for practical use in actual research rather than as an academic exercise. (Frank Yates)

The decision to reject observations should never be reached lightly. The decision to reject is a decision that the error system is out of control and we lose the essential basis for reaching assured conclusions. In a way, the concern is less about the observations we remove than the ones we retain. How trustworthy are they if the error system is not to be trusted? (D.B. DeLury)

The occurrence of observations we do not like is the commonest feature of all experimental and other statistical inquiries. (D.B. DeLury)

Fisher was of course a fine mathematician but difficult to follow. He would leap over intermediate stages in a calculation, leaving his colleagues floundering. I have several times heard a distinguished mathematician say, "He has evidently solved the problem correctly, but I don't see how he has done it." (E.B. Ford)

The only luxury worth having is that of worthy human environment. (R.A. Fisher)

We are as far as ever from any ultimate solution of the specialization problem; but I would like to suggest that, for the moment, the problem is not too acute to be met by a greatly increased versatility - if possible actual adult versatility. So that not only in youth, but throughout life, we may retain full sympathy with our neighbours. (R.A. Fisher)

That's not an experiment you have there, that's an experience. (R.A. Fisher)

It is particularly to be noted that those [systematic] methods of arrangement, at which experimenters have consciously aimed, and which reduce real errors, will appear from their (falsely) estimated standard errors to be not more but less accurate than if a random arrangement had been applied; whereas, if the experimenter is sufficiently unlucky, as must often be the case, to increase by his systematic arrangement the real errors, then the (falsely) estimated standard error will now be smaller, and will indicate that the experiment is not less but more accurate. Opinion will differ as to which event is, in the long run, the more unfortunate; it is evident that in both cases quite misleading conclusions will be drawn from the experiment. (R.A. Fisher)

No aphorism is more frequently repeated in connection with field trials, than that we must ask Nature few questions or, ideally, one question, at a time. The writer is convinced that this view is wholly mistaken. Nature, he suggests, will best respond to a logical and carefully thought out questionnaire; indeed, if we ask her a single question, she will often refuse to answer until some other topic has been discussed. (R.A. Fisher)

I wish I knew what sort of organization would suit the subject, for it would be deadly to it to be isolated as a self-contained study...What we need is a fairly intensive mathematical training, together with very wide scientific interests, not so much in established knowledge as in the means of establishing it. (R.A. Fisher)

How greatly this has become a practical need, in all fields in which biological work is being put upon a quantitative basis, will not be realized without personal contact with the scientific workers, agronomists, entomologists, botanists, geneticists, marine biologists and many others, from Europe, Asia, Africa and America, who, in the first five or ten years of their research experience, discover that their really urgent practical problems are essentially statistical...Diverse as the qualifications of these men are, they all have this in common, that they are of generally high intellectual capacity, they have received, in their university training, no preparation whatever for the statistical problems which are bound to confront them, as soon as they come into touch with the questions they are set to investigate. (R.A. Fisher)

It is the method of reasoning, and not the subject matter, that is distinctive of mathematical thought. A mathematician, if he is of any use, is of use as an expert in the process of reasoning, by which we pass from a theory to its logical consequences, or from an observation to the inferences which must be drawn from it. (R.A. Fisher)

I have frequently been impressed with the advantage a worker has gained, especially in self-confidence and resourcefulness, by being confronted malgré lui with problems of a so-called "applied" or practical nature, which in reality are problems requiring exploration and judgement rather than the application of ready-made formulae. (R.A. Fisher)

...It may be that the question which Dr. Neyman thinks should be answered is more important than the one I have proposed and attempted to answer. I suggest that before criticizing previous work it is always wise to give enough study to the subject to understand its purpose. (R.A. Fisher)

...it would still be true that the Natural Sciences can only be successfully conducted by responsible and independent thinkers applying their minds and their imaginations to the detailed interpretation of verifiable observations. The idea that this responsibility can be delegated to a vast computer programmed with Decision Functions belongs to the fantasy of circles rather remote from scientific research. (R.A. Fisher)

...nothing is more obvious than that the judgement of the relative importance of different lines of work is very ill-developed in many mathematical departments. (R.A. Fisher)

Although [Fisher] had earlier expressed the view that the teaching of ideas "fantastically remote from the natural sciences" had left the [United States] in the position of "a rewarding field for missionary enterprise", the situation appeared even worse than he had supposed; anyway, he was not called to this missionary field. (J.F. Box)

Unless the principles and design of an assay are sound, statistical analysis is at best a tentative numerical evaluation of the data, at worst a groping in the dark that may prove disastrous. (D.J. Finney)

There is nothing to stop those who greatly desire it from believing that lung cancer is caused by smoking cigarettes. They should also believe that inhaling cigarette smoke is a protection. To believe either is, however, to run the risk of failing to recognise and therefore failing to prevent other and more genuine causes... (R.A. Fisher)

To become a statistician, practice statistics and mull Fisher over with patience, respect, and skepticism. (Harold Hotelling)

Education is what you have left over after you have forgotten everything you have learned. (Anonymous)

In order to assert that a natural phenomenon is experimentally demonstrable we need, not an isolated record, but a reliable method of procedure. In relation to the test of significance, we may say that a phenomenon is experimentally demonstrable when we know how to conduct an experiment which will rarely fail to give us a statistically significant result. (R.A. Fisher)

...we are witnessing the emergence of a subculture of economists and social scientists, who are no more qualified or equipped to practice statistics than law or medicine, yet who nonetheless do practice it among their circles of nonstatisticians, without much visible sign of protest from the community of statisticians. (Robert F. Ling)

By definition, when you are investigating the unknown, you do not know what you will find or even when you have found it. (Anonymous)

Lucifer's Statistical Lexicon:

Statistician: 1) One who is to figures what a librarian is to words. 2) One who knows that what he means is at variance to the truth.

Chi-Square test: A procedure any fool can carry out and frequently does.

T-test: Invented by a man who studied beer.

Confidence Interval: A correctly named term if the word 'interval' may be used in phrases such as, 'three card interval', 'hat interval' and 'interval or treat'.

Exploratory Data Analysis: A subject whose benefits to statistics have been bought at great cost to the English language.

Multivariate analysis: A means of finding the answer when you don't know the question.

Non-parametric test: An assumption-free procedure for investigating a hypothesis of no practical interest.

Significance level: A natural constant, like pi and e, whose value is 0.05.

Power: A probability of a possible outcome of a potential decision conditional upon an imaginable circumstance given a conceivable value of an algebraic embodiment of an abstract mathematical idea and the strict adherence to an extremely precise rule.

(S.J. Penn)