"Exact truth of a null hypothesis is very unlikely except in a genuine uniformity trial." (David R Cox, "Some problems connected with statistical inference", Annals of Mathematical Statistics 29, 1958)
"Assumptions that we make, such as those concerning the form of the population sampled, are always untrue." (David R Cox, "Some problems connected with statistical inference", Annals of Mathematical Statistics 29, 1958)
"Overemphasis on tests of significance at the expense especially of interval estimation has long been condemned." (David R Cox, "The role of significance tests", Scandanavian Journal of Statistics 4, 1977)
"There are considerable dangers in overemphasizing the role of significance tests in the interpretation of data." (David R Cox, "The role of significance tests", Scandanavian Journal of Statistics 4, 1977)
"In any particular application, graphical or other informal analysis may show that consistency or inconsistency with H0 is so clear cut that explicit calculation of p is unnecessary." (David R Cox, "The role of significance tests", Scandanavian Journal of Statistics 4, 1977)
"The central point is that statistical significance is quite different from scientific significance and that therefore estimation [...] of the magnitude of effects is in general essential regardless of whether statistically significant departure from the null hypothesis is achieved." (David R Cox, "The role of significance tests", Scandanavian Journal of Statistics 4, 1977)
"At a simpler level, some elementary but important suggestions for the clarity of graphs are as follows: (i) the axes should be clearly labelled with the names of the variables and the units of measurement; (ii) scale breaks should be used for false origins; (iii) comparison of related diagrams should be made easy, for example by using identical scales of measurement and placing diagrams side by side; (iv) scales should be arranged so that systematic and approximately linear relations are plotted at roughly 45° to the x-axis; (v) legends should make diagrams as nearly self-explanatory, i.e. independent of the text, as is feasible; (vi) interpretation should not be prejudiced by the technique of presentation, for example by superimposing thick smooth curves on scatter diagrams of points faintly reproduced." (David R Cox,"Some Remarks on the Role in Statistics of Graphical Methods", Applied Statistics 27 (1), 1978)
"Most graphs used in the analysis of data consist of points arising in effect from distinct individuals, although there are certainly other possibilities, such as the use of lines dual to points. In many cases of exploratory analysis, however, the display of supplementary information attached to some or all of the points will be crucial for successful interpretation. The primary co-ordinate axes should, of course, be chosen to express the main dependence explicitly, if not initially certainly in the final presentation of conclusions." (David R Cox,"Some Remarks on the Role in Statistics of Graphical Methods", Applied Statistics 27 (1), 1978)
"So far as is feasible, diagrams should be planned so that (a) departures from "standard" conditions should be revealed as departures from linearity, or departures from totally random scatter, or as departures of contours from circular form; (b) different points should have approximately independent errors; (c) points should have approximately equal errors, preferably known and indicated, or, if equal errors cannot be achieved, major differences in the precision of individual points should be indicated, at least roughly; (d) individual points should have clearcut interpretation; (e) variables plotted should have clearcut physical interpretation; (f) any non-linear transformations applied should not accentuate uninteresting ranges; (g) any reasonable invariance should be exploited." (David R Cox,"Some Remarks on the Role in Statistics of Graphical Methods", Applied Statistics 27 (1), 1978)
"There are two general decisions to be made when displaying supplementary information, the first concerning the amount of such information and the second the precise technique to be used. The amount of supplementary information that it is sensible to show depends on the number of points. The possibility of showing such information only for relatively extreme points and possibly for a sample of the more central points should be considered when the number of points is large; thus in a probability plot of contrasts from a large factorial experiment it may be enough to label only the more extreme values." (David R Cox,"Some Remarks on the Role in Statistics of Graphical Methods", Applied Statistics 27 (1), 1978)
"It is very bad practice to summarise an important investigation solely by a value of P." (David R Cox, "Statistical significance tests", British Journal of Clinical Pharmacology 14, 1982)
"The criterion for publication should be the achievement of reasonable precision and not whether a significant effect has been found." (David R Cox, "Statistical significance tests", British Journal of Clinical Pharmacology 14, 1982)
"The continued very extensive use of significance tests is alarming." (David R Cox, "Some general aspects of the theory of statistics", International Statistical Review 54, 1986)
"It has been widely felt, probably for thirty years and more, that significance tests are overemphasized and often misused and that more emphasis should be put on estimation and prediction. While such a shift of emphasis does seem to be occurring, for example in medical statistics, the continued very extensive use of significance tests is on the one hand alarming and on the other evidence that they are aimed, even if imperfectly, at some widely felt need." (David R Cox, "Some general aspects of the theory of statistics", International Statistical Review 54, 1986)
"Most real life statistical problems have one or more nonstandard features. There are no routine statistical questions; only questionable statistical routines." (David R Cox)
No comments:
Post a Comment