Biostatistics For Dummies®
Visit www.dummies.com/cheatsheet/biostatistics to view this book's cheat sheet.
Table of Contents
Part I: Beginning with Biostatistics Basics
Part II: Getting Down and Dirty with Data
Part IV: Looking for Relationships with Correlation and Regression
Part V: Analyzing Survival Data
Part I: Beginning with Biostatistics Basics
Brushing Up on Math and Stats Basics
Doing Calculations with the Greatest of Ease
Concentrating on Clinical Research
Drawing Conclusions from Your Data
A Matter of Life and Death: Working with Survival Data
Figuring Out How Many Subjects You Need
Getting to Know Statistical Distributions
Chapter 2: Overcoming Mathophobia: Reading and Understanding Mathematical Expressions
Breaking Down the Basics of Mathematical Formulas
Displaying formulas in different ways
Checking out the building blocks of formulas
Focusing on Operations Found in Formulas
Factorials and absolute values
Simple and complicated formulas
Counting on Collections of Numbers
Sums and products of the elements of an array
Chapter 3: Getting Statistical: A Short Review of Basic Statistics
Taking a Chance on Probability
Thinking of probability as a number
Comparing odds versus probability
Some Random Thoughts about Randomness
Picking Samples from Populations
Recognizing that sampling isn’t perfect
Digging into probability distributions
Introducing Statistical Inference
Homing In on Hypothesis Testing
Understanding the meaning of “p value” as the result of a test
Examining Type I and Type II errors
Going Outside the Norm with Nonparametric Statistics
Chapter 4: Counting on Statistical Software
Desk Job: Personal Computer Software
Checking out commercial software
On the Go: Calculators and Mobile Devices
Scientific and programmable calculators
Gone Surfin’: Web-Based Software
Chapter 5: Conducting Clinical Research
Identifying aims, objectives, hypotheses, and variables
Deciding who will be in the study
Choosing the structure of the study
Defining analytical populations
Determining how many subjects to enroll
Collecting and validating data
Incorporating interim analyses
Chapter 6: Looking at Clinical Trials and Drug Development
Not Ready for Human Consumption: Doing Preclinical Studies
Testing on People during Clinical Trials to Check a Drug’s Safety and Efficacy
Phase I: Determining the maximum tolerated dose
Phase II: Finding out about the drug’s performance
Phase III: Proving that the drug works
Phase IV: Keeping an eye on the marketed drug
Holding Other Kinds of Clinical Trials
Pharmacokinetics and pharmacodynamics (PK/PD studies)
Part II: Getting Down and Dirty with Data
Chapter 7: Getting Your Data into the Computer
Looking at Levels of Measurement
Classifying and Recording Different Kinds of Data
Assigning subject identification (ID) numbers
Organizing name and address data
Checking Your Entered Data for Errors
Creating a File that Describes Your Data File
Chapter 8: Summarizing and Graphing Your Data
Summarizing and Graphing Categorical Data
Locating the center of your data
Describing the spread of your data
Showing the symmetry and shape of the distribution
Structuring Numerical Summaries into Descriptive Tables
Showing the distribution with histograms
Summarizing grouped data with bars, boxes, and whiskers
Depicting the relationships between numerical variables with other graphs
Chapter 9: Aiming for Accuracy and Precision
Beginning with the Basics of Accuracy and Precision
Getting to know sample statistics and population parameters
Understanding accuracy and precision in terms of the sampling distribution
Thinking of measurement as a kind of sampling
Expressing errors in terms of accuracy and precision
Improving Accuracy and Precision
Getting more accurate measurements
Increasing the precision of your measurements
Calculating Standard Errors for Different Sample Statistics
Chapter 10: Having Confidence in Your Results
Feeling Confident about Confidence Interval Basics
Taking sides with confidence intervals
Calculating Confidence Intervals
Before you begin: Formulas for confidence limits in large samples
The confidence interval around a mean
The confidence interval around a proportion
The confidence interval around an event count or rate
The confidence interval around a regression coefficient
Relating Confidence Intervals and Significance Testing
Chapter 11: Fuzzy In Equals Fuzzy Out: Pushing Imprecision through a Formula
Understanding the Concept of Error Propagation
Using Simple Error Propagation Formulas for Simple Expressions
Adding or subtracting a constant doesn’t change the SE
Multiplying (or dividing) by a constant multiplies (or divides) the SE by the same amount
For sums and differences: Add the squares of SEs together
For averages: The square root law takes over
For products and ratios: Squares of relative SEs are added together
For powers and roots: Multiply the relative SE by the power
Handling More Complicated Expressions
Using the simple rules consecutively
Checking out an online calculator
Simulating error propagation — easy, accurate, and versatile
Chapter 12: Comparing Average Values between Groups
Knowing That Different Situations Need Different Tests
Comparing the mean of a group of numbers to a hypothesized value
Comparing two groups of numbers
Comparing three or more groups of numbers
Analyzing data grouped on several different variables
Adjusting for a “nuisance variable” when comparing numbers
Comparing sets of matched numbers
Comparing within-group changes between groups
Trying the Tests Used for Comparing Averages
Running Student t tests and ANOVAs from summary data
Estimating the Sample Size You Need for Comparing Averages
Chapter 13: Comparing Proportions and Analyzing Cross-Tabulations
Examining Two Variables with the Pearson Chi-Square Test
Understanding how the chi-square test works
Pointing out the pros and cons of the chi-square test
Modifying the chi-square test: The Yates continuity correction
Focusing on the Fisher Exact Test
Understanding how the Fisher Exact test works
Noting the pros and cons of the Fisher Exact test
Analyzing Ordinal Categorical Data with the Kendall Test
Studying Stratified Data with the Mantel-Haenszel Chi-Square Test
Chapter 14: Taking a Closer Look at Fourfold Tables
Focusing on the Fundamentals of Fourfold Tables
Choosing the Right Sampling Strategy
Producing Fourfold Tables in a Variety of Situations
Describing the association between two binary variables
Evaluating diagnostic procedures
Looking at inter- and intra-rater reliability
Chapter 15: Analyzing Incidence and Prevalence Rates in Epidemiologic Data
Understanding Incidence and Prevalence
Prevalence: The fraction of a population with a particular condition
Understanding how incidence and prevalence are related
Expressing the precision of an incidence rate
Comparing incidences with the rate ratio
Calculating confidence intervals for a rate ratio
Comparing two event counts with identical exposure
Estimating the Required Sample Size
Chapter 16: Feeling Noninferior (Or Equivalent)
Understanding the Absence of an Effect
Defining the effect size: How different are the groups?
Defining an important effect size: How close is close enough?
Recognizing effects: Can you spot a difference if there really is one?
Proving Equivalence and Noninferiority
Some precautions about noninferiority testing
Part IV: Looking for Relationships with Correlation and Regression
Chapter 17: Introducing Correlation and Regression
Correlation: How Strongly Are Two Variables Associated?
Lining up the Pearson correlation coefficient
Analyzing correlation coefficients
Regression: What Equation Connects the Variables?
Understanding the purpose of regression analysis
Talking about terminology and mathematical notation
Classifying different kinds of regression
Chapter 18: Getting Straight Talk on Straight-Line Regression
Knowing When to Use Straight-Line Regression
Understanding the Basics of Straight-Line Regression
Running a Straight-Line Regression
Interpreting the Output of Straight-Line Regression
Seeing what you told the program to do
Making your way through the regression table
Wrapping up with measures of goodness-of-fit
Scientific fortune-telling with the prediction formula
Recognizing What Can Go Wrong with Straight-Line Regression
Figuring Out the Sample Size You Need
Chapter 19: More of a Good Thing: Multiple Regression
Understanding the Basics of Multiple Regression
Defining a few important terms
Knowing when to use multiple regression
Being aware of how the calculations work
Running Multiple Regression Software
Preparing categorical variables
Recoding categorical variables as numerical
Creating scatter plots before you jump into your multiple regression
Taking a few steps with your software
Interpreting the Output of a Multiple Regression
Examining typical output from most programs
Checking out optional output available from some programs
Deciding whether your data is suitable for regression analysis
Determining how well the model fits the data
Watching Out for Special Situations that Arise in Multiple Regression
Collinearity and the mystery of the disappearing significance
Figuring How Many Subjects You Need
Chapter 20: A Yes-or-No Proposition: Logistic Regression
Understanding the Basics of Logistic Regression
Gathering and graphing your data
Fitting a function with an S shape to your data
Handling multiple predictors in your logistic model
Running a Logistic Regression with Software
Interpreting the Output of Logistic Regression
Seeing summary information about the variables
Assessing the adequacy of the model
Checking out the table of regression coefficients
Predicting probabilities with the fitted logistic formula
Heads Up: Knowing What Can Go Wrong with Logistic Regression
Don’t fit a logistic function to nonlogistic data
Watch out for collinearity and disappearing significance
Check for inadvertent reverse-coding of the outcome variable
Don’t misinterpret odds ratios for numerical predictors
Don’t misinterpret odds ratios for categorical predictors
Beware the complete separation problem
Figuring Out the Sample Size You Need for Logistic Regression
Chapter 21: Other Useful Kinds of Regression
Analyzing Counts and Rates with Poisson Regression
Introducing the generalized linear model
Interpreting the Poisson regression output
Discovering other things that Poisson regression can do
Anything Goes with Nonlinear Regression
Distinguishing nonlinear regression from other kinds
Checking out an example from drug research
Running a nonlinear regression
Using equivalent functions to fit the parameters you really want
Smoothing Nonparametric Data with LOWESS
Adjusting the amount of smoothing
Part V: Analyzing Survival Data
Chapter 22: Summarizing and Graphing Survival Data
Understanding the Basics of Survival Data
Knowing that survival times are intervals
Recognizing that survival times aren’t normally distributed
Looking at the Life-Table Method
Graphing hazard rates and survival probabilities from a life table
Digging Deeper with the Kaplan-Meier Method
Heeding a Few Guidelines for Life Tables and the Kaplan-Meier Method
Recording survival times the right way
Recording censoring information correctly
Interpreting those strange-looking survival curves
Doing Even More with Survival Data
Chapter 23: Comparing Survival Times
Comparing Survival between Two Groups with the Log-Rank Test
Understanding what the log-rank test is doing
Running the log-rank test on software
Considering More Complicated Comparisons
Coming Up with the Sample Size Needed for Survival Comparisons
Chapter 24: Survival Regression
Knowing When to Use Survival Regression
Explaining the Concepts behind Survival Regression
The steps of Cox PH regression
Interpreting the Output of a Survival Regression
Testing the validity of the assumptions
Checking out the table of regression coefficients
Homing in on hazard ratios and their confidence intervals
Assessing goodness-of-fit and predictive ability of the model
Focusing on baseline survival and hazard functions
How Long Have I Got, Doc? Constructing Prognosis Curves
Running the proportional-hazards regression
Estimating the Required Sample Size for a Survival Regression
Chapter 25: Ten Distributions Worth Knowing
Chapter 26: Ten Easy Ways to Estimate How Many Subjects You Need
Comparing Means between Two Groups
Comparing Means among Three, Four, or Five Groups
Comparing Proportions between Two Groups
Testing for a Significant Correlation
Comparing Survival between Two Groups
Scaling from 80 Percent to Some Other Power
Scaling from 0.05 to Some Other Alpha Level