Introduction to Statistical Analysis

Lloyd S. Nelson

Journal of Quality Technology · 1984 · 611 citations · 2 references

Concepts

TL;DR

Students in applied fields often lack deep mathematical training, so a textbook must balance minimal math with clear theoretical justification to avoid becoming a mere recipe book. The second edition successfully addresses this balance, presenting ANOVA and Neyman–Pearson hypothesis testing with minimal mathematics yet sufficient theoretical grounding.

Abstract

The limited mathematical preparation of the student and the need for some understanding of the theoretical justification of methods of analysis are the two sides of a dilemma that one has to face in writing a textbook in applied statistics. The student in an applied field is not often accustomed to mathematical manipulations, whereas a pure description of statistical methods may very well turn the book into a collection of recipes. The authors of the second edition of Introduction to Statistical Analysis handled this dilemma quite beautifully. Although a student with a meager “knowledge of algebraic addition, subtraction, and multiplication” may not necessarily find all parts of the text easy to follow, most of the arguments are presented with a minimum amount of mathematics but with adequate rationale. The fine treatments of analysis of variance and the Neyman-Pearson theory of testing hypotheses are good examples.

References

2