Page 22 - Intermediate Statistics for Dummies

03_045206 intro.qxd 2/1/07 9:40 AM Page 1
Introduction
eady to load your statistical toolbox with a new level of tools?
RIntermediate Statistics For Dummies picks up where Statistics For
Dummies (or your introductory statistics course) leaves off, and keeps you
moving along the road of statistical ideas and techniques in a positive step-
by-step way.
The focus of intermediate statistics is on building and testing models based
on data. You’re trying to estimate, investigate, correlate, and congregate cer-
tain variables based on the information at hand. The process for doing this is
two-fold. First you build a model that you think describes your situation (the
model-building phase), and then you test your model, using the data you’ve
collected (the data analysis phase).
The techniques presented in intermediate statistics are used even more heav-
ily in medical and scientific studies than the introductory topics were. The
reason is that most real-world studies have more complex problems to solve;
they ask more questions and collect more data. Given that the results of
these more complex studies are used to make decisions in a host of different
areas (including medical science, biology, engineering, business, and politics
to name a few) most anyone can benefit from reading this book. You can see
applications that give you exposure to real problems and to the process of
interpreting and understanding other people’s results.
About This Book
This book is designed for people who want to get into (or at least be able to
understand and interpret) some of the more involved techniques in statistics,
beyond medians and means, the Central Limit Theorem, and confidence
intervals and hypothesis tests. (However, I do add some brief overviews of
introductory statistics as needed, just to remind everyone of what was cov-
ered and get new readers up to speed.) The topics this time around are many
flavors of regression (including simple, multiple, nonlinear, and logistic);
ANOVA (one-way and two-way); Chi-square tests (for independence and
goodness-of-fit); and nonparametric procedures.
I also include interpretation of computer output for data analysis purposes. I
do show how to use the software to get the results, but I focus more on how
to interpret the results found in the output. It’s likely that more people will
be interpreting this kind of information rather than doing the programming
specifically. And because the equations and calculations can get too involved