Statistics for People Who Think They Hate Statistics 5th edition eBook
Statistics or Sadistics?
It’s Up to You
Difficulty Scale (really easy)
WHAT YOU’LL LEARN ABOUT IN THIS
What statistics is all about
Why you should take statistics
How to succeed in this course
You’ve heard it all before, right? “Statistics is difficult,” “The
math involved is impossible,” “I don’t know how to use a
computer,” “What do I need this stuff for?” “What do I do
next?” and the famous cry of the introductory statistics student,
“I don’t get it!”
Well, relax. Students who study introductory statistics find
themselves, at one time or another, thinking about at least one
of the preceding, if not actually sharing it with another student,
their spouse, a colleague, or a friend.
And all kidding aside, some statistics courses can easily be
described as sadistics. That’s because the books are
repetitiously boring and the authors have no imagination.
That’s not the case for you. The fact that you or your
instructor has selected Statistics for People Who (Think They)
Hate Statistics shows that you’re ready to take the right
approach: one that is unintimidating, informative, and applied
(and even a little fun) and that tries to teach you what you need
to know about using statistics as the valuable tool that it is.
If you’re using this book in a class, it also means that your
instructor is clearly on your side—he or she knows that
statistics can be intimidating but has taken steps to see that it is
not intimidating for you. As a matter of fact, we’ll bet there’s a
good chance (as hard as it may be to believe) that you’ll be
enjoying this class in just a few short weeks.
A 5-MINUTE HISTORY OF STATISTICS
Before you read any further, it would be useful to have some
historical perspective about this topic called statistics. After all,
almost every undergraduate in the social, behavioral, and
biological sciences and every graduate student in education,
nursing, psychology, social welfare and social services, and
anthropology (you get the picture) is required to take this
course. Wouldn’t it be nice to have some idea from whence the
topic it covers came? Of course it would.
Way, way back, as soon as humans realized that counting was
a good idea (as in “How many of these do you need to trade for
one of those?”), collecting information also became a useful
skill. If counting counted, then one would know how many
times the sun would rise in one season, how much food was
needed to last the winter, and what amount of resources
belonged to whom.
That was just the beginning. Once numbers became part of
language, it seemed like the next step was to attach these
numbers to outcomes. That started in earnest during the 17th
century, when the first set of data pertaining to populations was
collected. From that point on, scientists (mostly
mathematicians but then physical and biological scientists as
well) needed to develop specific tools to answer specific
questions. For example, Francis Galton (a cousin of Charles
Darwin, by the way), who lived from 1822 to 1911, was very
interested in the nature of human intelligence. To explore one
of his primary questions regarding the similarity of intelligence
among family members, he used a specific statistical tool
called the correlation coefficient (first developed by
mathematicians), and then he popularized its use in the
behavioral and social sciences. You’ll learn all about this tool
in Chapter 5.
In fact, most of the basic statistical procedures that you will
learn about were first developed and used in the fields of
agriculture, astronomy, and even politics. Their application to
human behavior came much later.
The past 100 years have seen great strides in the invention of
new ways to use old ideas. The simplest test for examining the
differences between the averages of two groups was first
advanced during the early 20th century. Techniques that build
on this idea were offered decades later and have been greatly
refined. And the introduction of personal computers and such
programs as SPSS® (now made by an IBM company; see
Appendix A, available online at www.sagepub.com/salkind5e)
and Excel (from Microsoft) have opened up the use of
sophisticated techniques to anyone who wants to explore these
The introduction of powerful personal computers has been
both good and bad. It’s good because most statistical analyses
no longer require access to a huge and expensive mainframe
computer. Instead, a simple personal computer costing less than
$500 can do 95% of what 95% of the people need. On the other
hand, less than adequately educated students (such as your
fellow students who passed on taking this course!) will take any
old data they have and think that by running them through some
sophisticated SPSS or Excel analysis, they will have reliable,
trustworthy, and meaningful outcomes—not true. What your
professor would say is, “Garbage in, garbage out.” In other
words, if you don’t start with reliable and trustworthy data,
what you’ll have after your data are analyzed are unreliable and
Today, statisticians in all different areas, from criminal
justice to geophysics to psychology, find themselves using
basically the same techniques to answer different questions.
There are, of course, important differences in how data are
collected, but for the most part, the analyses (the plural of
analysis) that are done following the collection of data (the
plural of datum) tend to be very similar, even if they are called
different things. The moral here? This class will provide you
with the tools to understand how statistics are used in almost
any discipline. Pretty neat, and all for just three or four credits.
If you want to learn more about the history of statistics and
see a historical time line, a great place to start is at Saint
Anselm’s College website at
and the University of California at Los Angeles at
http://www.stat.ucla.edu/history/. You’ll find tons of good stuff
at both places.
STATISTICS: WHAT IT IS (AND ISN’T)
Statistics for People Who (Think They) Hate Statistics is a book
about basic statistics and how to apply them to a variety of
different situations, including the analysis and understanding of
In the most general sense, statistics describes a set of tools
and techniques that is used for describing, organizing, and
interpreting information or data. Those data might be the scores
on a test taken by students participating in a special math
curriculum, the speed with which problems are solved, the
number of patient complaints when health care providers use
one type of drug rather than another, the number of errors in
each inning of a World Series game, or the average price of a
dinner in an upscale restaurant in Sante Fe, New Mexico.
In all of these examples, and the million more we could think
of, data are collected, organized, summarized, and then
interpreted. In this book, you’ll learn about collecting,
organizing, and summarizing data as part of descriptive
statistics. And then you’ll learn about interpreting data when
you learn about the usefulness of inferential statistics.
What Are Descriptive Statistics?
Descriptive statistics are used to organize and describe the
characteristics of a collection of data. The collection is
sometimes called a data set or just data.
For example, the following list shows you the names of 22
college students, their major areas of study, and their ages. If
you needed to describe what the most popular college major is,
you could use a descriptive statistic that summarizes their
choice (called the mode). And if you wanted to know the
average age, you could easily compute another descriptive
statistic that identifies this variable (that one’s called the
mean). Both of these simple descriptive statistics are used to
describe data. They do a fine job of allowing us to represent the
characteristics of a large collection of data such as the 22 cases
in our example.
So watch how simple this is. To find the most frequently
selected major, just find the one that occurs most often. And to
find the average age, just add up all the age values and divide
by 22. You’re right—the most often occurring major is
psychology (9 times) and the average age is 20.3 years. Look,
Ma! No hands—you’re a statistician.
What Are Inferential Statistics?
Inferential statistics are often (but not always) the next step
after you have collected and summarized data. Inferential
statistics are used to make inferences from a smaller group of
data (such as our group of 22 students) to a possibly larger one
(such as all the undergraduate students in the College of Arts
and Sciences). Sometimes, it’s just fine to describe outcomes
only; other times, the next step—using inferential statistics—is
This smaller group of data is often called a sample, which is
a portion, or a subset, of a population. For example, all the fifth
graders in Newark, New Jersey, would be a population (all the
occurrences with certain characteristics—being in fifth grade
and living in Newark), whereas a selection of 150 of these
students would be a sample.
Let’s look at another example. Your marketing agency asks
you (a newly hired researcher) to determine which of several
names is most appealing for a new brand of potato chip. Will it
be Chipsters? FunChips? Crunchies? As a statistics pro (we
know we’re moving a bit ahead of ourselves, but keep the
faith), you need to find a small group of potato chip eaters that
is representative of all potato chip fans and ask these munchers
to tell you which one of the three names they like the most.
Then, if you did things right, you can easily apply the findings
to the huge group of potato chip eaters.
Or, let’s say you’re interested in the best treatment for a
particular type of disease. Perhaps you’ll try a new drug as one
alternative, a placebo (or a substance that is known not to have
any effect) as another alternative, and simply nothing as the
third alternative to see what happens. Well, you find out that a
larger number of patients get better when no action is taken and
nature just takes its course! The drug does not have any effect.
Then, with that information, you infer that the same thing is
true for the larger group of patients who suffer from the
disease, given the results of your experiment.
In Other Words . . .
Statistics is a tool that helps us understand the world around us.
It does so by organizing information we’ve collected and then
letting us make certain statements about how characteristics of
those data are applicable to new settings. Descriptive and
inferential statistics work hand in hand, and which one you use
and when depends on the question you want answered.
WHAT AM I DOING IN A STATISTICS CLASS?
There are probably many reasons why you find yourself using
this book. You might be enrolled in an introductory statistics
class. Or you might be reviewing for your comprehensive
exams. Or you might even be reading this on summer vacation
(horrors!) in preparation and review for a more advanced class.
In any case—whether you have to take a final exam at the
end of a formal course, you’re just in it of your own accord, or
you’re taking the course online 500 miles from the instructor—
you are a statistics student.
And there are plenty of good reasons to be studying this
material—some fun, some serious, and some both. Here’s the
list of some of the things that my students hear at the beginning
of our introductory statistics course.
1. Statistics 101 or Statistics 1 or whatever it’s called at
your school looks great listed on your transcript. Kidding
aside, this may be a required course for you to complete
your major. But even if it is not, having these skills is
definitely a big plus when it comes time to apply for a job
or for further schooling. And with more advanced
courses, your résumé will be even more impressive. In
tough job markets, an edge like this is very important.
2. If this is not a required course, taking basic statistics sets
you apart from those students who do not take it. It shows
that you are willing to undertake a course that is above
average in difficulty and commitment.
3. Basic statistics is an intellectual challenge of a kind that
you might not be used to. There’s a good deal of thinking
that’s required, a bit of math (but not lots, and for a tuneup,
see Appendix E), and some integration of ideas and
application. The bottom line is that all this activity adds
up to what can be an invigorating intellectual experience
because you learn about a whole new area or discipline.
4. There’s no question that having some background in
statistics makes you a better student in the social or
behavioral sciences, because you will have a better
understanding not only of what you read in journals but
also what your professors and colleagues may be
discussing and doing in and out of class. You will be
amazed the first time you say to yourself, “Wow, I
actually understand what they’re talking about.” And it
will happen over and over again because you will have
the basic tools necessary to understand exactly how
scientists reach the conclusions they do.
5. If you plan to pursue a graduate degree in education,
anthropology, neuroscience, economics, nursing, urban
planning, sociology, or any one of many other social,
behavioral, and biological pursuits, this course will give
you the foundation you need to go further.
6. Finally, you can brag that you completed a course that
everyone thinks is the equivalent of building and running
a nuclear reactor.