Trying to read up on statistics can be like trying to decide where you want to start eating the elephant and what’s the most digestible way to get it down. This book is written to give bite-size nuggets of insight based on our experiences grappling with datasets large and small. It is intended to bridge the gap between the formal equations and the practicalities of generating a research manuscript. We won’t pretend reading it will answer all your questions but it will help explain what questions need to be asked for your study and how you can address them with both accuracy and clarity. The size, detail and (ostensible) organization of this book allow for easy reading and can give a leg (or at least a half-step) up for those seeking more detailed study later.
Features include:
- Excel sheets to allow exploration of topics raised
- Emphasis on intuitive explanations over formulas.
- Consideration of issues specific to clinical and surgical studies
Our audience is someone who may or may not have enjoyed formal statistics education (that is, you may have had it and not enjoyed it!) who may like seeing a more dressed-down presentation of the topics. Actual statisticians may pick this up at risk of a chuckle (with us or at us) and may find some useful ways to present topics to non-statisticians.
Author(s): Mitchell G. Maltenfort, Camilo Restrepo, Antonia F. Chen
Publisher: CRC Press
Year: 2020
Language: English
Pages: 152
City: Boca Raton
Cover
Half Title
Title Page
Copyright Page
Dedication
Table of Contents
Preface
Authors’ Biographies
Chapter 1 Introduction – Why Does a Surgeon Need Statistics?
Chapter 2 Interpreting Probability: Medical School Axioms of Probability
Horses before Zebras
The Simplest Explanation Is Most Likely
The Patient Can Have as Many Diseases as They Please
There Are More Differences between Bad Medicine and Good Medicine; ThAn There Is between Good Medicine and No Medicine
Chapter 3 Statistics, the Law of Large Numbers, and the Confidence Interval
Chapter 4 The Basics of Statistical Tests
Care and Feeding of p-Values
The Perils of Productivity
Sample Size versus p-Values
Always Include the Confidence Interval
Chapter 5 How Much Data Is Enough?
Chapter 6 Showing the Data to Yourself First – Graphs and Tables, Part 1
Chapter 7 How Normal Is a Gaussian Distribution? What to Do with Extreme Values?
Non-Gaussian Distributions
Extreme Values
Ordinal Data
Chapter 8 All Probabilities Are Conditional
Chapter 9 Quality versus Quantity in Data
Know What You’re Getting
Proper Layout
To Categorize or Not to Categorize
Chapter 10 Practical Examples
Example 1: Blood Loss
Example 2: Comorbidities and Mortality
Example 3: Minimal Clinically Important Difference
Example 4: The Particular Problem of BMI
Chapter 11 All Things Being Equal – But How? (Designing the Study)
Random Assignment Is Not Always an Option
Matching and Stratification
Selecting Multiple Predictors
Propensity Scores
Also Consider
Chapter 12 Binary and Count Outcomes
Chapter 13 Repeated Measurements and Accounting for Change
Chapter 14 What If the Data Is Not All There?
Chapter 15 Showing the Data to Others – Graphs and Tables, Part 2
Organizing the Presentation
Presenting the Narrative
Keeping Numbers in Context
Tables versus Graphs: Scale and Style
Articulating the Story
Visual Lingo
Chapter 16 Further Reading
Glossary
References
Index
