The mechanism of statistics

Abstract

It has fallen to my lot to serve in a Department where every variety of statistical work is to be found, and where the practical problems of how information is to be collected, tabulated, and published at a minimum expenditure of time, labour, and cost, have to be solved. As public attention has been much directed recently to this subject, especially in connection with the approaching Census, it has occurred to me that it would be a useful service to embody in a paper the results of many years thought and practical experience in the manipulation of figures, and that such a work might not only be acceptable to Statisticians in these countries, but helpful to the many statistical authorities in foreign lands.

I offer my contribution therefore, not by any means as an exhaustive treatise on the subject, but in the hope that it may lead to the reciprocation of ideas and the comparison of methods of working, and thus conduce to the interests of statistical science.