BioStats Basics A Student Handbook

by Gould, James L.; Gould, Grant F.

• ISBN13: 9780716734161
• ISBN10: 0716734168
• Edition: 1st
• Format: Paperback
• Copyright: 2001-12-13
• Publisher: W. H. Freeman

Summary

BioStats Basicsprovides introductory-level biology students with a practical, accessible introduction to statistical research. Engaging and informal, the book avoids excessive theoretical and mathematical detail to focus on how core statistical methods are put to work in biology. Students are given the essentials in probability that enable skillful experiment design and the correct use of statistical tests. Everyday examples, are drawn from ecology, animal physiology, animal behavior, medicine, and other areas of biology, are used the clarify methods. The accompanying Web site, www.whfreeman.com/gould is closely integrated with the text, providing crucial tutorials (explanations of tests alongside simulations) plus data analysis tools for completing the text's exercises.

Table of Contents

Preface Origin and Overview	xvii
Problems and Balance	xvii
Biostats Basics Online: A Tutorial-Based Approach	xviii
Why Is This Book So Thin?	xix
Examples and Exercises	xx
Cause and Effect	1	(12)
Probability and Survival	2	(3)
Probability and Research	5	(4)
Recognizing Differences	9	(2)
Probability and Math	11	(2)
Points to Remember	11	(2)
Data	13	(28)
Why Do We Need Data and Statistics?	13	(3)
Types of Data	16	(2)
Displaying Data	18	(4)
Distribution Types	22	(2)
Distribution Shapes	24	(3)
Sampling	27	(2)
Comparing Distributions	29	(12)
Points to Remember	36	(1)
Exercises	36	(5)
Binomial Distributions	41	(38)
What Kinds of Measurements Yield Binomial Distributions?	41	(3)
The Product Law and the Importance of Independence	44	(4)
Comparing Distributions	48	(1)
Probability: Was the Sample Drawn from the Null Distribution?	48	(7)
The Role of Sample Size	55	(2)
The Issue of Tails	57	(2)
Post Hoc Analysis	59	(1)
The Uses of Post Hoc Probabilities: Bayesian Logic	60	(3)
Binomials with Unequal Probabilities	63	(2)
Binomials with Estimated Probabilities	65	(1)
Looking at the End: The Poisson Distribution	65	(14)
Points to Remember	71	(1)
Exercises	72	(4)
More Than the Basics	76	(1)
Error and significance	76	(1)
From binomial to Poisson	77	(2)
Continuous Parametric Distributions: I	79	(32)
What Is ``Parametric''?	79	(1)
What Sorts of Measurements Yield Parametric Distributions?	80	(3)
Computing the Parameters of a Parametric Distribution	83	(5)
How Do We Know If a Distribution Is Parametric?	88	(3)
What Do Binomial and Parametric Distributions Have in Common?	91	(2)
Comparing a Parent and a Sample Distribution	93	(18)
Points to Remember	101	(1)
Exercises	102	(4)
More Than the Basics	106	(1)
From binomial to bell	106	(1)
Why two sets of symbols?	107	(1)
The parameters	107	(2)
The one-sample t-test	109	(2)
Continuous Parametric Distributions: II	111	(28)
Sample Size and Certainty	111	(1)
Comparing Sample Distributions: The Logic of the t-Tests	112	(3)
Checking That Variances Are Equal	115	(2)
Other Reasons to Compare Variances	117	(4)
Comparing the Means of Paired versus Unpaired Data	121	(2)
What Do You Do If the Standard Deviations Are Not Similar?	123	(3)
The Standard Error and Confidence Intervals	126	(13)
Points to Remember	131	(1)
Exercises	132	(3)
More Than the Basics	135	(1)
Two-sample t-test	135	(1)
Two sample t-test with dissimilar SDs	136	(1)
Variance additivity, and standard error	136	(3)
Data Transformations	139	(12)
Why Parametric Is Better	139	(1)
Nonparametric May Be Only Skin Deep	140	(1)
The Catch	141	(1)
Popular Transformations	141	(2)
Sample Means: The Ultimate Transformation?	143	(2)
Comparisons from Sample Means	145	(6)
Points to Remember	146	(1)
Exercises	146	(2)
More Than the Basics	148	(1)
Additivity	148	(1)
Guiding principles	148	(1)
Sample sets and SEs	149	(2)
Multiple Parametric Distributions: ANOVA	151	(38)
Why It's Illegal to Perform Multiple t-tests within a Data Set	151	(3)
Comparing Means without Comparing Means	154	(9)
But Which One Is Different?	163	(2)
Two-Way ANOVAs	165	(4)
Hoary Extensions of the Two-Way ANOVA	169	(3)
Other Beyond-the-Scope ANOVAs	172	(2)
What to Do with Multiple Pairwise Comparisons	174	(15)
Points to Remember	178	(2)
Exercises	180	(2)
More Than the Basics	182	(1)
The F-distribution	182	(1)
One-way ANOVA computation	183	(1)
The Tukey-Kramer Method	184	(1)
Two-way ANOVA computation	185	(1)
Additivity revisited	186	(1)
ANOVA III	186	(3)
Categorical Data	189	(26)
Where Do Categorical Data Come From	189	(1)
Comparing a Sample to a Null Distribution	190	(4)
How Is the Goodness-of-Fit Test Different from the Binomial Test?	194	(2)
Applications of Chi-Square When Category or Binomial Probabilities Are Estimated	196	(2)
Chi-Square and the Quick-but-Dirty Approach	198	(1)
Comparing Two or More Sample Distributions	199	(16)
Points to Remember	205	(1)
Exercises	206	(5)
More Than the Basics	211	(1)
Chi-square goodness-of-tit computation	211	(1)
Chi-square independence computation	212	(1)
Fishers Exact Test	212	(3)
Nonparametric Continuous Data	215	(20)
Why Nonparametric Tests Are Less Powerful	215	(2)
Testing Paired Two-Sample Data	217	(3)
Evaluating Grouped Multiple-Sample Data	220	(2)
Testing Unpaired Two-Sample Data	222	(2)
Evaluating Unpaired Multiple-Sample Data	224	(11)
Points to Remember	226	(1)
Exercises	227	(5)
More Than the Basics	232	(1)
The signed-rank computation	232	(1)
The Friedman computation	232	(1)
The rank-sum computation	233	(1)
The U-test	233	(1)
The Kruskal-Wallis computation	233	(2)
Circular Data	235	(20)
Where Do Circular Distributions Come From?	235	(1)
Determining the Mean Bearing and Degree of Dispersion	236	(4)
Testing for Clustering	240	(2)
Testing a Specific Hypothesis	242	(3)
Comparing Two Samples	245	(10)
Points to Remember	248	(1)
Exercises	248	(4)
More Than the Basics	252	(1)
Circular distributions	252	(1)
The Rayleigh z-computation	252	(1)
The Rayleigh u-test	252	(1)
The Watson-Williams computation	253	(2)
Relationships between Variables I: Correlation and Regression	255	(34)
Correlation versus Cause and Effect: When to Draw the Line	255	(5)
Correlating Nonparametric Data	260	(5)
Parametric Correlation Analysis	265	(2)
Linear Regression Analysis	267	(6)
Which Hypothesis to Test?	273	(2)
What If the Data Are Nonlinear?	275	(2)
Cause and Effect?	277	(12)
Points to Remember	279	(1)
Exercises	280	(6)
More Than the Basics	286	(1)
Calculating nonparametric correlation values	286	(1)
Additivity once more	286	(1)
Calculating parametric correlation values	286	(1)
Calculating linear regression values	287	(2)
Relationships between Variables II: Multiple Regression	289	(20)
How Multiple Variables Interact: Path Analysis	289	(5)
The Goal of Two-Variable Multiple Regression	294	(1)
Admit or Reject? The Problem	295	(3)
Sorting Out the Influence of Multiple Variables	298	(4)
Higher-Level Multiple Regression	302	(7)
Points to Remember	303	(1)
Exercises	304	(2)
More Than the Basics	306	(1)
Accounting for variance	306	(1)
Calculating multiple regression	307	(2)
None of the Above	309	(16)
The Quick-but-Dirty Approach	310	(3)
The Academic Approach	313	(1)
The Hard Way: Monte Carlo Simulations	314	(3)
Computers: From Zero to Null in 14 Hours	317	(1)
The Theory behind Statistics	318	(7)
Points to Remember	321	(1)
Exercises	322	(3)
Once Over Lightly	325	(10)
Distribution Types	325	(1)
Types of Data	326	(1)
Characterizing Distributions	326	(1)
Distribution Shapes	327	(1)
Statistical Tests	328	(1)
Which Test Is Appropriate?	329	(6)
Exercises	333	(2)
Answers to Exercises	335	(26)
Statistics Labs	361	(8)
Selected Statistical Tables	369	(36)
Glossary	405	(12)
Bibliography	417	(2)
Index	419