| |
| |
Preface | |
| |
| |
Foreword | |
| |
| |
| |
Hypotheses, Data, Stratification | |
| |
| |
| |
General considerations | |
| |
| |
| |
Two main hypotheses in drug trials: efficacy and safety | |
| |
| |
| |
Different types of data: continuous data | |
| |
| |
| |
Different types of data: proportions, percentages and contingency tables | |
| |
| |
| |
Different types of data: correlation coefficient | |
| |
| |
| |
Stratification issues | |
| |
| |
| |
Randomized versus historical controls | |
| |
| |
| |
Factorial designs | |
| |
| |
| |
References | |
| |
| |
| |
The Analysis of Efficacy Data of Drug Trials | |
| |
| |
| |
Overview | |
| |
| |
| |
The principle of testing statistical significance | |
| |
| |
| |
Unpaired T-Test | |
| |
| |
| |
Null hypothesis testing of 3 or more unpaired samples | |
| |
| |
| |
Three methods to test statistically a paired sample | |
| |
| |
| |
Null-hypothesis testing of 3 or more paired samples | |
| |
| |
| |
Paired data with a negative correlation | |
| |
| |
| |
Rank testing | |
| |
| |
| |
References | |
| |
| |
| |
The Analysis of Safety Data of Drug Trials | |
| |
| |
| |
Introduction, summary display | |
| |
| |
| |
Four methods to analyze two unpaired proportions | |
| |
| |
| |
Chi-square to analyze more than two unpaired proportions | |
| |
| |
| |
McNemar's test for paired proportions | |
| |
| |
| |
Survival analysis | |
| |
| |
| |
Conclusions | |
| |
| |
| |
Equivalence Testing | |
| |
| |
| |
Introduction | |
| |
| |
| |
Overview of possibilities with equivalence testing | |
| |
| |
| |
Equivalence testing, a new gold standard? | |
| |
| |
| |
Validity of equivalence trials | |
| |
| |
| |
Statistical Power and Sample Size | |
| |
| |
| |
What is statistical power | |
| |
| |
| |
Emphasis on statistical power rather than null-hypothesis testing | |
| |
| |
| |
Power computations | |
| |
| |
| |
Example of power computation using the T-Table | |
| |
| |
| |
Calculation of required sample size, rationale | |
| |
| |
| |
Calculations of required sample size, methods | |
| |
| |
| |
Testing not only superiority but also inferiority of a new treatment (type III error) | |
| |
| |
| |
References | |
| |
| |
| |
Interim Analyses | |
| |
| |
| |
Introduction | |
| |
| |
| |
Monitoring | |
| |
| |
| |
Interim analysis | |
| |
| |
| |
Group-sequential design of interim analysis | |
| |
| |
| |
Continuous sequential statistical techniques | |
| |
| |
| |
Conclusions | |
| |
| |
| |
References | |
| |
| |
| |
Multiple Statistical Inferences | |
| |
| |
| |
Introduction | |
| |
| |
| |
Multiple comparisons | |
| |
| |
| |
Primary and secondary variables | |
| |
| |
| |
Conclusions | |
| |
| |
| |
References | |
| |
| |
| |
Principles of Linear Regression | |
| |
| |
| |
Introduction | |
| |
| |
| |
More on paired observations | |
| |
| |
| |
Using statistical software for simple linear regression | |
| |
| |
| |
Multiple linear regression | |
| |
| |
| |
Another real data example of multiple linear regression | |
| |
| |
| |
Conclusions | |
| |
| |
| |
Subgroup Analysis Using Multiple Linear Regression: Confounding, Interaction, Synergism | |
| |
| |
| |
Introduction | |
| |
| |
| |
Example | |
| |
| |
| |
Model | |
| |
| |
| |
(I.) Increased precision of efficacy | |
| |
| |
| |
(II.) Confounding | |
| |
| |
| |
(III.) Interaction and synergism | |
| |
| |
| |
Estimation, and hypothesis testing | |
| |
| |
| |
Goodness-of-fit | |
| |
| |
| |
Selection procedures | |
| |
| |
| |
Conclusions | |
| |
| |
| |
References | |
| |
| |
| |
Curvilinear Regression | |
| |
| |
| |
Summary | |
| |
| |
| |
An example: curvilinear regression analysis of ambulatory blood pressure measurements | |
| |
| |
| |
Methods, statistical model | |
| |
| |
| |
Results | |
| |
| |
| |
Discussion | |
| |
| |
| |
References | |
| |
| |
| |
Meta-Analysis | |
| |
| |
| |
Introduction | |
| |
| |
| |
Examples | |
| |
| |
| |
Clearly defined hypotheses | |
| |
| |
| |
Thorough search of trials | |
| |
| |
| |
Strict inclusion criteria | |
| |
| |
| |
Uniform data analysis | |
| |
| |
| |
Discussion, where are we now? | |
| |
| |
| |
References | |
| |
| |
| |
Crossover Studies with Continuous Variables: Power Analysis | |
| |
| |
| |
Summary | |
| |
| |
| |
Introduction | |
| |
| |
| |
Mathematical model | |
| |
| |
| |
Hypothesis testing | |
| |
| |
| |
Statistical power of testing | |
| |
| |
| |
Conclusions | |
| |
| |
| |
References | |
| |
| |
| |
Crossover Studies with Binary Responses | |
| |
| |
| |
Summary | |
| |
| |
| |
Introduction | |
| |
| |
| |
Assessment of carryover and treatment effect | |
| |
| |
| |
Statistical model for testing treatment and carryover effects | |
| |
| |
| |
Results | |
| |
| |
| |
Examples | |
| |
| |
| |
Discussion | |
| |
| |
| |
References | |
| |
| |
| |
Post-Hoc Analysis in Clinical Trials, a Case for Logistic Regression Analysis | |
| |
| |
| |
Multivariate methods | |
| |
| |
| |
Examples | |
| |
| |
| |
Logistic regression equation | |
| |
| |
| |
Conclusions | |
| |
| |
| |
References | |
| |
| |
| |
Quality-of-Life Assessments in Clinical Trials | |
| |
| |
| |
Summary | |
| |
| |
| |
Introduction | |
| |
| |
| |
Some terminology | |
| |
| |
| |
Defining QOL in a subjective or objective way | |
| |
| |
| |
The patients' opinion is an important independent-contributor to QOL | |
| |
| |
| |
Lack of sensitivity of QOL-assessments | |
| |
| |
| |
Odds ratio analysis of effects of patient characteristics on QOL data provides increased precision | |
| |
| |
| |
Discussion | |
| |
| |
| |
References | |
| |
| |
| |
Statistics for the Analysis of Genetic Data | |
| |
| |
| |
Introduction | |
| |
| |
| |
Some terminology | |
| |
| |
| |
Genetics, genomics, proteonomics, data mining | |
| |
| |
| |
Genomics | |
| |
| |
| |
Conclusions | |
| |
| |
| |
References | |
| |
| |
| |
Relationship Among Statistical Distributions | |
| |
| |
| |
Summary | |
| |
| |
| |
Introduction | |
| |
| |
| |
Variances | |
| |
| |
| |
The normal distribution | |
| |
| |
| |
Null-hypothesis testing with the normal or the t-distribution | |
| |
| |
| |
Relationship between the normal distribution and chi-square distribution, null-hypothesis testing with the chi-square distribution | |
| |
| |
| |
Examples of data where variance is more important than mean | |
| |
| |
| |
Chi-square can be used for multiple samples of data | |
| |
| |
| |
Conclusions | |
| |
| |
| |
References | |
| |
| |
| |
Statistics is Not "Bloodless" Algebra | |
| |
| |
| |
Introduction | |
| |
| |
| |
Statistics is fun because it proves your hypothesis was right | |
| |
| |
| |
Statistical principles can help to improve the quality of the trial | |
| |
| |
| |
Statistics can provide worthwhile extras to your research | |
| |
| |
| |
Statistics is not like algebra bloodless | |
| |
| |
| |
Statistics can turn art into science | |
| |
| |
| |
Statistics for support rather than illumination? | |
| |
| |
| |
Statistics can help the clinician to better understand limitations and benefits of current research | |
| |
| |
| |
Limitations of statistics | |
| |
| |
| |
Conclusions | |
| |
| |
| |
References | |
| |
| |
Appendix | |
| |
| |
Index | |