iv Tables for Statisticians and Biometricians 



apt to get soiled and otherwise damaged, to know that they can refer their readers 

 to a handy and easily replaceable collection of the tables themselves. 



Apart from these secondary considerations, the aim of this book is precisely 

 that of Part I. It is not intended as a text-book of modern statistical theory. The 

 reproduction of theory is reduced to a minimum, the formulae involved being only 

 given where they are needful in order to follow the description of the use of the 

 tables. The book is intended primarily for the student or research worker who 

 has been through complete courses of lectures on the theory of statistics. The 

 former needs a guide in his practical laboratory work, and the latter some aid in 

 choosing and applying methods to the reduction of his own data. 



The teacher of statistics will find it not without advantage to set his students 

 problems similar to -the illustrations in the two Parts of the Tables for Statisticians 

 and Biometricians, and let them by aid of this book find their solutions in the 

 hours devoted to practical work. The Editor is aware by the letters that have 

 reached him concerning difficulties or errors found in Part I, that a good many 

 workers are training themselves by independent reworking of the illustrations 

 given in that part. The present part will provide a wider, if stiffer, field of 

 statistical exercises*. 



The adjective 'stiffer' is used advisedly. The majority of the methods in 

 Part II are somewhat harder of application than those discussed in Part I. This is 

 a natural result of the development of statistical theory. The easier problems call 

 first for solution; the harder follow in their train. It is accordingly all the more 

 important to repeat the words of the Preface to the first edition of Part I. 



"The Introduction gives a brief description of each individual table; it is by no 

 means intended to replace actual instruction in the use of the tables such as is 

 given in a statistical laboratory, nor does it profess to provide an account of the 

 innumerable uses to which they may be put, or to warn the reader of the many 

 difficulties which may arise from inept handling of them. Additional aid may be 

 found in the text which usually accompanies the original publication of the tables." 



Much of recent work in statistical theory deals with the problem of "small 

 samples," and involves some interesting and brilliant mathematics. This work is 

 undoubtedly of importance from the standpoint of practical statistics. If we must 

 have small samples, and they are undoubtedly necessary in certain experimental 

 work, then by all means let us deduce by accurate theory as much as we can from 

 them. But the student should recognise that from sparse data really little can be 

 learnt, although that is no excuse for not learning it. The danger is that he may 



* It is proposed to issue shortly a volume of collected statistical problems for laboratory use, which 

 may be of service to both instructor and student as indicating the type of questions where the Tables 

 are of service. 



