Tukey, John

Hoaglin DC, Mosteller F, Tukey JW (1983) Understanding Robust and Exploratory Data Analysis. John Wiley and Sons, New York... 

These EDA methods are essentially pictorial and can often be carried out using simple pencil and paper methods. Picturing data and displaying it accurately is an aspect of data analysis which is under utilised. Unless exploratory data analysis uncovers features and structures within the data set there is likely to be nothing for confirmatory data analysis to consider One of the champions of EDA, the American statistician John W. Tukey, in his seminal work on EDA captures the underlying principle in his comment that... 

John w. tukey, Bell Laboratories, Murray Hill, New Jersey, and Department of Statistics, Princeton University, Princeton, New Jersey aafje vos, Laboratorium voor structuurchemie, Rijksuniversiteit Groningen, Groningen, Netherlands... 

One sometimes encounters this claim, but it is illogical. As John Tukey put it, Adjustments are not expected to be perfect - they are only supposed to help (Tukey, 1993, p. 273). Suppose that the true relationship between covariate and outcome is some nonlinear function. It is extremely likely that a linear approximation to this relationship will be better than nothing. One can always regret the fact that the adjustment that has been carried out is less than perfect, but as an approximation to the truth a linear adjustment is likely to be better than nothing. Hence, imperfection in adjustment cannot be grounds for rejecting adjustment altogether. 

Tukey, J. W. In Spectral Analysis of Time Series Harris, B., Ed. John Wiley and Sons New York, 1967 p 25. 

Bloomfield, P. Fourier Analysis of Time Series An Introduction John Wiley and Sons New York, 1976 Chapter 6. Chambers, J. M. Cleveland, W. S. Kleiner, B. Tukey, P. A. Graphical Methods for Data Analysis Wadsworth International Group Belmont, California, 1983 Chapter 3. 

Hoaglin, D.C., Mosteller, E, and Tukey, J.W., Understanding Robust and Exploratory Data Analysis, New York John Wiley, 1983. 

H. F. Trotter, and J. W. Tukey, Conditional Monte Carlo for normal samples, Florida Symposium, John Wiley Sons, 1954, p. 64. 

John W. Tukey. Exploratory Data Analysis. Addison-Wesley, 1977. 

This PhD follows statistician John Tukey s concept of Exploratory Data Analysis [12] the primary purpose of visualizing and exploring is to raise questions and gather insights about a large quantity of data. Unlike most statistical work, which evaluates a priori questions according to a model, exploration by information visualization has the potential to start analysis without assumptions, or open new perspectives on a previously-analyzed dataset. For these purposes, overviews of the whole network are crucial. 

---