Key Terms 11calculate means and standard deviations, and so on. These techniques will be discussed in
Chapter 2.
Following an exploratory analysis of the data, we will apply several inferential proce-
dures. For example, we will want to compare the mean score on a scale of self-esteem for a
group who received stress-management training with the mean score for a group who did
not receive such training. Techniques for making these kinds of comparisons will be dis-
cussed in Chapters 7, 11, 12, 13, 14, 16, and 18, depending on the complexity of our exper-
iment, the number of groups to be compared, and the degree to which we are willing to
make certain assumptions about our data.
We might also want to ask questions dealing with the relationships between variables
rather than the differences among groups. For example, we might like to know whether a
person’s level of behavior problems is related to his score on self-esteem, or whether a per-
son’s coping scores can be predicted from variables such as her self-esteem and social sup-
port. Techniques for asking these kinds of questions will be considered in Chapters 9, 10,
15, and 17, depending on the type of data we have and the number of variables involved.
Most students (and courses) never seem to make it all the way through any book. In this
case, that would mean skipping Chapter 18 on nonparametric analyses. I think that would
be unfortunate because that chapter focuses on some of the newer, and important, work on
bootstrapping and resampling methods. These methods have become much more popular
with the drastic increases in computing power, and they make considerable intuitive sense.
I would recommend that you at least skim that chapter early on, and go back to it for the
relevant material as you work through the rest of the book. You do not need an extensive
background to understand what is there, and reading it will give you a real step up on
analyses that you will see in the literature. (I believe that it will also give you a much better
understanding of the parametric analyses in the remainder of the book.)
In this edition, I have made a deliberate effort to introduce concepts that are becoming
important in data analysis but are rarely covered in a book at this level. In doing so, I am
not able to devote the space needed for a thorough understanding of the techniques. Instead
I am trying to provide you with underlying concepts and vocabulary so that you can take
on those techniques on your own or have a step up in a subsequent course. Those tech-
niques are important and you need to be prepared.
Figure 1.1 provides an organizational scheme that distinguishes among the various pro-
cedures on the basis of a number of dimensions, such as the type of data, the questions we
want to ask, and so on. The dimensions should be self-explanatory. This diagram is not
meant to be a guide for choosing a statistical test. Rather, it is intended to give you a sense
of how the book is organized.Key Terms
Random sample (1.1)
Randomly assign (1.1)
Population (1.1)
Sample (1.1)
External validity (1.1)
Random assignment (1.1)
Internal validity (1.1)
Variable (1.1)
Independent variable (1.1)
Dependent variable (1.1)
Discrete variables (1.1)
Continuous variables (1.1)
Quantitative data (1.1)
Measurement data (1.1)
Categorical data (1.1)
Frequency data (1.1)
Qualitative data (1.1)
Descriptive statistics (1.2)Exploratory data analysis
(EDA) (1.2)
Inferential statistics (1.2)
Parameter (1.2)
Statistic (1.2)
Nominal scale (1.3)
Ordinal scale (1.3)
Interval scale (1.3)
Ratio scale (1.3)