ABSTRACT
The objective of statistical analysis is to discover what conclusions can be drawn from data and to present these conclusions in as simple and lucid a form as is consistent with accuracy. The more formal statistical procedures are based on a probability model for the data and author begin with some general comments on formulation. The setting up of such a model for a particular application can be a crucial issue and, as with problems of mathematical formulation in general, it is hard to give more than general guidelines on how to proceed. Systematic component is clearly impracticable to give a comprehensive discussion of all the mathematical functions that might be used to describe systematic variation. The formulation of a suitable model for the random component of variability is much more a technical statistical matter than is the discussion of systematic variation. The idea of statistical analysis as a tool for decision making in the face of uncertainty is important.
