ABSTRACT
The first section of this book began with the proposition that good science and good statistics must go hand in hand. Its two chapters provided a framework for evaluating the scientific integrity of procedures used to collect data for the types of studies that healthcare executives and caregivers typically consult when deciding whether a certain decision might make a desired difference in organizational or clinical performance. A common theme appeared in the discussions of both scientific method and experimental design: Good statistics cannot be used to compensate for bad science. To borrow an old metaphor that makes the same point in considerably more picturesque language, you cannot make a silk purse out of a sow’s ear.
