Statistics Applied to Clinical TrialsSpringer Science & Business Media, 27. lip 2011. - Broj stranica: 210 In 1948 the first randomized controlled trial was published by the English Medical Research Council in the British Medical Journal. Until then, observations had been uncontrolled. Initially, trials frequently did not confirm hypotheses to be tested. This phenomenon was attributed to low sensitivity due to small samples, as well as inappropriate hypotheses based on biased prior trials. Additional flaws were recognized and subsequently were better accounted for: carryover effects due to insufficient washout from previous treatments, time effects due to external factors and the natural history of the condition under study, bias due to asymmetry between treatment groups, lack of sensitivity due to a negative correlation between treatment responses, etc. Such flaws, mainly of a technical nature, have been largely corrected and led to trials after 1970 being of significantly better quality than before. The past decade has focused, in addition to technical aspects, on the need for circumspection in planning and conducting of clinical trials. As a consequence, prior to approval, clinical trial protocols are now routinely scrutinized by different circumstantial bodies, including ethics committees, institutional and federal review boards, national and international scientific organizations, and monitoring committees charged with conducting interim analyses. This book not only explains classical statistical analyses of clinical trials, but addresses relatively novel issues, including equivalence testing, interim analyses, sequential analyses, and meta-analyses, and provides a framework of the best statistical methods currently available for such purposes. The book is not only useful for investigators involved in the field of clinical trials, but also for all physicians who wish to better understand the data of trials as currently published. |
Sadržaj
2 | |
3 | |
proportions percentages and contingency tables | 8 |
correlation coefficient | 11 |
Stratification issues | 13 |
Randomized versus historical controls | 14 |
Factorial designs | 15 |
References | 16 |
Goodnessoffit | 102 |
Selection procedures | 103 |
References | 104 |
CURVILINEAR REGRESSION 1 Summary | 106 |
Results | 108 |
Discussion | 115 |
References | 116 |
METAANALYSIS 1 Introduction | 120 |
THE ANALYSIS OF EFFICACY DATA OF DRUG TRIALS 1 Overview | 17 |
The principle of testing statistical significance | 18 |
Unpaired TTest | 21 |
Null hypothesis testing of 3 or more unpaired samples | 23 |
Three methods to test statistically a paired sample | 24 |
Nullhypothesis testing of 3 or more paired samples | 28 |
Paired data with a negative correlation | 29 |
Rank testing | 35 |
References | 38 |
THE ANALYSIS OF SAFETY DATA OF DRUG TRIALS 1 Introduction summary display | 39 |
Four methods to analyze two unpaired proportions | 40 |
Chisquare to analyze more than two unpaired proportions | 42 |
McNemars test for paired proportions | 43 |
Survival analysis | 44 |
Conclusions | 46 |
EQUIVALENCE TESTING | 48 |
Introduction | 49 |
Equivalence testing a new gold standard? | 51 |
STATISTICAL POWER AND SAMPLE SIZE What is statistical power | 53 |
Emphasis on statistical power rather than nullhypothesis testing | 54 |
Power computations | 56 |
Example of power computation using the TTable | 57 |
Calculation of required sample size rationale | 59 |
Testing not only superiority but also inferiority of a new treatment type III | 62 |
References | 64 |
CHAPTER 6INTERIM ANALYSES 1 Introduction | 66 |
Groupsequential design of interim analysis | 69 |
Conclusions | 71 |
MULTIPLE STATISTICAL INFERENCES 1 Introduction 73 | 75 |
Primary and secondary variables | 78 |
Conclusions | 81 |
PRINCIPLES OF LINEAR REGRESSION 1 Introduction | 83 |
More on paired observations | 84 |
Using statistical software for simple linear regression | 87 |
Multiple linear regression | 89 |
Another real data example of multiple linear regression | 93 |
Conclusions | 94 |
CONFOUNDING INTERACTION SYNERGISM 1 Introduction | 95 |
Model | 96 |
I Increased precision of efficacy | 98 |
II Confounding | 99 |
III Interaction and synergism | 100 |
Estimation and hypothesis testing | 101 |
Clearly defined hypotheses | 121 |
Strict inclusion criteria | 122 |
Discussion where are we now? | 131 |
References | 132 |
POWER ANALYSIS 1 Summary | 133 |
Mathematical model | 134 |
Hypothesis testing | 135 |
Statistical power of testing | 137 |
Conclusions | 140 |
References | 141 |
CROSSOVER STUDIES WITH BINARY RESPONSES 1 Summary | 143 |
Assessment of carryover and treatment effect | 144 |
Statistical model for testing treatment and carryover effects | 145 |
Results | 146 |
Examples | 148 |
Discussion | 149 |
References | 150 |
Examples | 151 |
Logistic regression equation | 154 |
Conclusions | 155 |
CHAPTER 15QUALITYOFLIFE ASSESSMENTS IN CLINICAL TRIALS 1 Summary 157 | 158 |
Defining QOL in a subjective or objective way | 160 |
Lack of sensitivity of QOLassessments | 162 |
Discussion | 165 |
References | 166 |
STATISTICS FOR THE ANALYSIS OF GENETIC DATA 1 Introduction | 167 |
Some terminology | 168 |
Genetics genomics proteonomics data mining | 170 |
Genomics | 171 |
Conclusions | 175 |
RELATIONSHIP AMONG STATISTICAL DISTRIBUTIONS 1 Summary | 177 |
Variances | 178 |
The normal distribution | 179 |
Nullhypothesis testing with the normal or the tdistribution | 181 |
Relationship between the normal distribution and chisquare distribution | 183 |
Examples of data where variance is more important than mean | 185 |
Chisquare can be used for multiple samples of data | 186 |
Conclusions | 188 |
References | 189 |
Statistical principles can help to improve the quality of the trial | 192 |
207 | |
Ostala izdanja - Prikaži sve
Statistics Applied to Clinical Trials Ton J. M. Cleophas,Aeilko H. Zwinderman,Toine F. Cleophas Ograničeni pregled - 2002 |
Statistics Applied to Clinical Trials Ton J. M. Cleophas,Aeilko H. Zwinderman,Toine F. Cleophas Pregled nije dostupan - 2002 |
Statistics Applied to Clinical Trials Ton J. M. Cleophas,Aeilko H. Zwinderman,Toine F. Cleophas Pregled nije dostupan - 2002 |
Uobičajeni izrazi i fraze
according actual addition adjustment analysis ANOVA Applied approach approximately assessed better blood pressure calculated called carryover effect chance chapter chi-square cholesterol clinical trials coefficient compared comparisons conclusion considered continuous correlation covariates crossover curve demonstrated dependent determine difference distribution drug efficacy equal equivalence error estimate example expressed Figure finding genes given gives graph groups helpful heterogeneity important increased independent individual interim analysis intervals larger less linear regression lower mean measures method multiple negative normal distribution null hypothesis observations odds p-value paired patients performed period placebo polynomes population positive possible probability problem procedure proportions provides Publishers randomized ratio regression reject response risk sample score SEMs sensitivity shows significant similar situation square standard statistical subjects Table term treatment effect usually values variables variance variation zero