Principles of Applied Statistics

by Cox, D. R.; Donnelly, Christl A.

• ISBN13: 9781107644458
• ISBN10: 1107644453
• Format: Paperback
• Copyright: 2011-09-30
• Publisher: Cambridge Univ Pr

Summary

Applied statistics is more than data analysis, but it is easy to lose sight of the big picture. David Cox and Christl Donnelly distil decades of scientific experience into usable principles for the successful application of statistics, showing how good statistical strategy shapes every stage of an investigation. As you advance from research or policy question, to study design, through modelling and interpretation, and finally to meaningful conclusions, this book will be a valuable guide. Over a hundred illustrations from a wide variety of real applications make the conceptual points concrete, illuminating your path and deepening your understanding. This book is essential reading for anyone who makes extensive use of statistical methods in their work.

Author Biography

D. R. Cox is one of the world's pre-eminent statisticians. Author or coauthor of numerous books and papers, his work on the proportional hazards regression model is one of the most cited and most influential papers in modern statistics: In 2010 he won the Copley Medal of the Royal Society 'for his seminal contributions to the theory and application of statistics'. Christl A. Donnelly is a Professor of Statistical Epidemiology in the MRC Centre for Outbreak Analysis and Modelling at imperial College London and was deputy chair of the Independent Scientific Group on Cattle TB (1998 to 2007). She has worked on a range of other infectious diseases, including BSE/vCJD, foot and mouth disease, SAKS, influenza, malaria and neglected tropical diseases.

Table of Contents

Preface	p. ix
Some general concepts	p. 1
Preliminaries	p. 1
Components of investigation	p. 2
Aspects of study design	p. 5
Relationship between design and analysis	p. 5
Experimental and observational studies	p. 6
Principles of measurement	p. 8
Types and phases of analysis	p. 9
Formal analysis	p. 10
Probability models	p. 10
Prediction	p. 11
Synthesis	p. 12
Design of studies	p. 14
Introduction	p. 14
Unit of analysis	p. 18
Types of study	p. 20
Avoidance of systematic error	p. 21
Control and estimation of random error	p. 24
Scale of effort	p. 25
Factorial principle	p. 26
Special types of study	p. 29
Preliminaries	p. 29
Sampling a specific population	p. 30
Experiments	p. 37
Cross-sectional observational study	p. 46
Prospective observational study	p. 48
Retrospective observational study	p. 48
Principles of measurement	p. 53
Criteria for measurements	p. 53
Classification of measurements	p. 55
Scale properties	p. 56
Classification by purpose	p. 58
Censoring	p. 61
Derived variables	p. 62
Latent variables	p. 64
Preliminary analysis	p. 75
Introduction	p. 75
Data auditing	p. 76
Data screening	p. 77
Preliminary graphical analysis	p. 82
Preliminary tabular analysis	p. 86
More specialized measurement	p. 87
Discussion	p. 88
Model formulation	p. 90
Preliminaries	p. 90
Nature of probability models	p. 92
Types of model	p. 97
Interpretation of probability	p. 104
Empirical models	p. 108
Model choice	p. 118
Criteria for parameters	p. 118
Nonspecific effects	p. 124
Choice of a specific model	p. 130
Techniques of formal Inference	p. 140
Preliminaries	p. 140
Confidence limits	p. 141
Posterior distributions	p. 142
Significance tests	p. 145
Large numbers of significance tests	p. 152
Estimates and standard errors	p. 156
Interpretation	p. 159
Introduction	p. 159
Statistical causality	p. 160
Generality and specificity	p. 167
Data-generating models	p. 169
Interaction	p. 171
Temporal data	p. 177
Publication bias	p. 180
Presentation of results which inform public policy	p. 181
Epilogue	p. 184
Historical development	p. 184
Some strategic issues	p. 185
Some tactical considerations	p. 186
Conclusion	p. 187
References	p. 189
Index	p. 198
Table of Contents provided by Ingram. All Rights Reserved.