INTRODUCTION TO BASIC CONCEPTS IN EXPERIMENTAL DESIGN

concepts, and a presentation of statistical tools used throughout the re-
mainder of the book. The reader is encouraged to review the introductory
chapters after reading subseguent chapters.

This book emphasizes those experimental designs that are most
useful in the behavioral sciences. Many of the chapters conclude with a
selected bibliography of contemporary research, which indicates diverse
applications of the designs discussed in the chapter. The reader should
consult the bibliographies to gain an over-all view of the way experimental
designs are used in research.

The validity of inductive inferences that an experimenter draws from
research rests on the fulfillment of certain assumptions. These assumptions
are explicitly stated for each design as it is presented. Procedures for
determining whether or not the assumptions are tenable in the light of
sample data are also described.

A list of advantages and disadvantages for each design is provided
to aid an experimenter in the selection of an appropriate design. Subseguent
sections of this chapter treat general concepts basic to the selection of the
best design for a particular research application.

DEFINITION OF BASIC TERMS

A number of terms must be defined before concepts basic to the
selection of an experimental design can be discussed. It is assumed that
the reader already has some familiarity with most of the terms that follow.
Therefore, the material in this section is intended only to ensure a common
vocabulary for the subseguent discussion. The definitions of some terms
are oversimplified, but the assumed mathematical background does not
permit rigorous definitidns for all terms. Additional definitions are listed
in the glossary.

Population. A collection of ali observations identifiable by a set of rules.
Sample. A subset of observations from a population.

Random Sample. A sample drawn from a population in such a way that all
possible samples of size n have the same probability of being selected.

Parameter. A measure computed from all observations in a population.
Parameters are designated by Greek letters. For example, the symbols for a popula-
tion mean and standard deviation are ji and g, respectively.

Statistic. A measure computed from observations in a sample. Statistics are
designated by Latin letters. For example, the symbols for a sample mean and
standard deviation are X and S, respectively.

Random Variable. A guantity, say X, which may assume a range of possible
values, each having an associated probability, say p(X).
Estimator. The particular function of observations in a sample that is chosen

to estimate a population parameter. For example, the sample mean is used to
estimate the population mean. The numerical value obtained is called an estimate.