CONTENTS
Preface = xi
01 Who should read this book and why? = 1
What we cover in this book = 1
What can you expect in this book? = 3
Data versus information = 6
What is important? = 8
The methods we will be discussing = 10
Implicit views of people and biases = 11
One way of comparing these methods = 13
Sense and sensibility with predictions = 15
Where we will not be going = 20
Summary of key points = 21
02 Getting the project going = 27
At the beginning = 27
Know who you are talking about or talking to = 28
What is the most you can expect from each method? = 31
How do you judge the result? = 35
What is significant? = 36
On to correlations = 43
How do I plan to evaluate the results? = 45
Know what sensible goals might look like = 50
Summary of key points = 51
03 Conjoint, discrete choice and other trade-offs : let''''s do an experiment = 55
The reasons we need these methods = 55
The basic thinking behind the experimentally designed methods = 59
What the methods ask - and get = 60
What is a designed experiment? = 66
The great measurement power of experiments = 70
Getting more from experiments : HB to the rescue = 71
A brief talk about origins = 74
Applications in brief = 78
Summary of key points = 80
04 Creating the best, newest thing : discrete choice modelling = 85
Key features = 85
Thinking through and setting up the problem = 90
How many people you need = 103
Utility and share = 105
Market simulations = 107
Making more than one choice : allocating purchases = 114
Using the simulator program in the online resources = 114
Rounding out the picture = 118
Summary of key points = 120
05 Conjoint analysis and its uses = 127
Thinking in conjoint versus thinking in choices = 127
Conjoint analysis for single-product optimization = 132
Using the single product simulator in the online resources = 133
Conjoint remains an excellent method for messages = 136
Conjoint analysis for the best service delivery = 147
Using the message optimization simulator in the online resources = 152
Conjoint analysis and interactions = 154
Variants of conjoint analysis = 156
Summary of key points = 159
06 Predictive models : via classifications that grow on trees = 165
Classification trees : understanding an amazing analytical method = 165
Seeing how trees work, step by step = 166
Strong, yet weak = 173
A case study : let''''s take a cruise = 174
CHAID and CART (and CRT, C＆RT, QUEST, J48 and others) = 191
Summary : applications and cautions = 194
07 Remarkable predictive models with Bayes Nets = 197
What are Bayes Nets and how do they compare with other methods? = 197
Let''''s make a deal = 205
Our first example : Bayes Nets linking survey questions and behaviour = 213
Bayes Nets confirm a theoretical model, mostly = 218
What is important to buyers of children''''s apparel = 223
Summary and conclusions = 226
08 Putting it together : what to use when = 229
The tasks the methods do = 230
Thinking about thinking = 235
Bibliography = 237
Index = 249
