This "nuts and bolts" book provides a condensation of biostatistical methods that applied microbiology researchers need to perform data analyses. Based on the author's more than two decades of applied research and teaching experience, it is presented in a straight-forward manner, applicable by practicing microbiologists with minimal backgrounds in mathematics. All methods rely only on the use of a basic hand-held calculator. The overriding goal of this book is to ground one's microbiological expertise and experience in one's research pursuits, using biostatistics not as a black box, but as a tool. The book begins with a broad discussion of the experimental process, leading to one-sample, two-sample, and multi-sample comparisons. Each regression analysis is presented, as well as an example. Nonparametric methods are discussed, as well as when they should be applied. Finally, special topics of statistics in microbiology are presented.
Biostatistics and Microbiology enables the reader to access and apply statistical methods that generally frustrate and intimidate the uninitiated. Statistics, like chemistry, microbiology, woodworking, or sewing, requires that the individual put some time into learning the concepts and methods. This book presents a step-by-step manner that eliminates the greatest obstacle to the learner, which is applying the many processes that comprise a statistical method. The author counters the fear of statistical methods by describing early in the book a step-by-step procedure to perform a statistical method - a process that we will term "the six-step procedure." All of the testing will be performed adhering to six well-defined steps, which will greatly simplify the statistical process. Each step in the sequence must be completed before moving on to the next step. In the context of microbiology, statistics can be extremely useful in making interpretations and decisions concerning collected data. Statistics, then, is a way of formally communicating the interpretation of clinical or experimental data and is particularly important when a treatment result is not clearly differentiable from another treatment.
