BioStats Basics

Preface: Origin and Overview
Origins
Problems and Balance
A Tutorial-Based Approach
Why Is This Book So Thin?

Who Won’t Like This Book?
Examples and Exercises
      
1. Cause and Effect
Probability and Survival
Probability and Research
Recognizing Differences
Probability and Math
Points to Remember
Exercises
    
2. Data
Why Do We Need Data and Statistics?
Types of Data
Displaying Data
Distribution Types
Distribution Shapes
Sampling
Comparing Distributions
Points to Remember
Exercises
    
3. Binomial Distributions
What Kinds of Measurements Yield Binomial Distributions?
The Product Law and the Importance of Independence
Comparing Distributions
Probability:  Was the Sample Drawn from the Null Distribution?
The Role of Sample Size
The Issue of Tails
Post-hoc Analysis
The Uses of post-hoc Probabilities:  Bayesian Analysis
Binomials With Unequal Probabilities
Binomials With Estimated Probabilities
Looking at the End:  the Poisson Distribution
Points to Remember
Exercises
   
Tests covered in this chapter:
comparing equal-probability binomial distributions
comparing unequal-probability binomial distributions
 Poisson analysis (for rare binomial events)
    
4. Continuous Parametric Distributions--Part I
What is "Parametric"?
What Sorts of Measurements Yield Parametric Distributions?
Computing the Parameters of a Parametric Distribution
How Do We Know If a Distribution is Parametric?
What do Binomial and Parametric Distributions Have in Common?
Comparing a Parent and a Sample Distribution
Points to Remember       
Exercises
  

Tests covered in this chapter:
 test for normality
Gauss tests
one-sample t-test
       
5. Continuous Parametric Distributions--Part II            
Sample Size and Certainty
Comparing Sample Distributions: the Logic of the t-Tests
Checking That Variances are Equal
Other Reasons to Compare Variances
Comparing the Means of Paired Versus Unpaired Data
What Do You Do If the Standard Deviations are not Similar?
The Standard Error and Confidence Intervals
Points to Remember
Exercises
   
Tests covered in this chapter:
F-test
paired two-sample t-test
unpaired two-sample t-test
t-test for unequal SDs
                                       
6. Data Transformations
Why Parametric Is Better
Non-Parametric Is Only Skin Seep
The Catch
Popular Transformations
Sample Means: The Ultimate Transformation?
Comparisons from Sample Means
Points to Remember
Exercises
   
Techniques covered in this chapter:
sampling
transformations
    
         
7. Comparing More Than Two Parametric Distributions
Why It’s Illegal to Perform Multiple t-Tests
Comparing Means Without Comparing Means
But Which One Is Different?
Two-Way ANOVAs
Hoary Extensions of the Two-Way ANOVA
Other Beyond-the-Scope ANOVAs
What to Do with Multiple Pairwise Comparisons
Points to Remember
Exercises
   
Tests/methods covered in this chapter:
one-way ANOVA
Tukey-Kramer method
two-way ANOVA
    
   
8. Categorical Data
Where Do Categorical Data Come From?
Comparing a Sample to a Null Distribution
How Is the Goodness-of-Fit Test Different from the Binomial Test?
Applications of Chi-Square When Category or Binomial Probabilities Are Estimated
Chi-Square and the Quick-but-Dirty Approach
Comparing Two or More Sample Distributions
Points to Remember
Exercises
   
Tests covered in this chapter: 
chi-square goodness of fit
chi-square independence
                  
9. Nonparametric Continuous Data
Why Nonparametric Tests are Less Powerful
Testing Paired Two-Sample Data
Evaluating Grouped Multiple-Sample Data
Testing Unpaired Two-Sample Data
Evaluating Unpaired Multiple-Sample Comparisons
Points to Remember
Exercises
   
Tests covered in this chapter:
signed-rank test
Friedman test
rank-sum test
U-test
Kruskal-Wallis test
    
10. Circular Distributions
Where Do Circular Distributions Come From?
Determining the Mean Bearing and Degree of Dispersion
Testing for Clustering
Testing Against a Null Hypothesis
Comparing Two Samples
Points to Remember
Exercises
   
Tests covered in this chapter:
Rayleigh v-test
Rayleigh z-test
Watson-Williams test
    
   
11. Relationships Between Variables I:  Correlation and Regression
Correlation vs Cause-and-Effect:  When to Draw the Line
Correlating Nonparametric Data
Parametric Correlation Analysis
Linear Regression Analysis
Which Hypothesis to Test?
What If the Data are Nonlinear?
Cause and Effect?
Points to Remember
Exercises
   
Tests covered in this chapter:
parametric correlation analysis
nonparametric correlation analysis
linear regression analysis
    
   
12. Relationships Between Variables II:  Multiple Regression
How Multiple Variables Interact:  Path Analysis
The Goal of Two-Variable Multiple Regression Analysis
Admit or reject?  The problem
Sorting Out the Influence of Multiple Variables
Higher-Level Multiple Regression
Points to Remember
Exercises
   
Tests/techniques covered in this chapter:
path analysis
multiple regression analysis
    
13. None Of The Above
What If None of the "Standard" Tests Is Appropriate?
The Quick-but-Dirty Approach
The Academic Approach
The Hard Way:  Monte Carlo Simulations
Computers:  From Zero to Null in Fourteen Hours
The Theory Behind Statistics
Points to Remember
Exercises
   
Technique covered in this chapter:
Monte-Carlo simulation
     
14. Once Over Lightly
Distribution Types
Types of Data
Characterizing Distributions
Distribution Shapes
Statistical Tests
Which Test Is Appropriate?
Exercises
   
Appendix A:  Answers to Exercises
Appendix B:  Statistics Labs               
Appendix C:  Selected Statistical Tables
Appendix D:  Glossary     
Selected Bibliography
Index