Synthetic Datasets for Statistical Disclosure Control
Jorg. Drechsler
Bok Engelsk 2011 · Electronic books.
| Annen tittel | |
|---|---|
| Medvirkende | Drechsler, Jèorg. (Author)
|
| Utgitt | New York, NY : Springer , 2011
|
| Omfang | 1 online resource (147 p.)
|
| Utgave | 1.
|
| Opplysninger | Description based upon print version of record.. - Synthetic Datasets for Statistical Disclosure Control; Foreword; Acknowledgements; Contents; List of Figures; List of Tables; Chapter 1 Introduction; Chapter 2 Background on Multiply Imputed Synthetic Datasets; 2.1 The history of multiply imputed synthetic datasets; 2.2 Advantages of multiply imputed synthetic datasets compared with other SDC methods; Chapter 3 Background on Multiple Imputation; 3.1 Two general approaches to generate multiple imputations; 3.1.1 Joint modeling; 3.1.2 Fully conditional specification (FCS); 3.1.3 Pros and cons of joint modeling and FCS. - 3.2 Real data problems and possible ways to handle them3.2.1 Imputation of semi-continuous variables; 3.2.2 Bracketed imputation; 3.2.3 Imputation under linear constraints; 3.2.4 Skip patterns; Chapter 4 The IAB Establishment Panel; Chapter 5 Multiple Imputation for Nonresponse; 5.1 Inference for datasets multiply imputed to address nonresponse; 5.1.1 Univariate estimands; 5.1.2 Multivariate estimands; 5.2 Analytical validity for datasets multiply imputed to address nonresponse; 5.3 Multiple imputation of the missing values in the IAB Establishment Panel; 5.3.1 The imputation task. - 5.3.2 Imputation models5.3.3 Evaluating the quality of the imputations; Chapter 6 Fully Synthetic Datasets; 6.1 Inference for fully synthetic datasets; 6.1.1 Univariate estimands; 6.1.2 Multivariate estimands; 6.2 Analytical validity for fully synthetic datasets; 6.3 Disclosure risk for fully synthetic datasets; 6.4 Application of the fully synthetic approach to the IAB Establishment Panel; 6.4.1 The imputation procedure; 6.4.2 Measuring the analytical validity; 6.4.3 Assessing the disclosure risk; Chapter 7 Partially Synthetic Datasets; 7.1 Inference for partially synthetic datasets. - 7.1.1 Univariate estimands7.1.2 Multivariate estimands; 7.2 Analytical validity for partially synthetic datasets; 7.3 Disclosure risk for partially synthetic datasets; 7.3.1 Ignoring the uncertainty from sampling; 7.3.2 Accounting for the uncertainty from sampling; 7.4 Application of the partially synthetic approach to the IAB Establishment Panel; 7.4.1 Measuring the analytical validity; 7.4.2 Assessing the disclosure risk; 7.5 Pros and cons of fully and partially synthetic datasets; Chapter 8 Multiple Imputation for Nonresponse and Statistical Disclosure Control. - 8.1 Inference for partially synthetic datasets when the original data are subject to nonresponse8.1.1 Univariate estimands; 8.1.2 Multivariate estimands; 8.2 Analytical validity and disclosure risk; 8.3 Generating synthetic datasets from the multiply imputed IAB Establishment Panel; 8.3.1 Selecting the variables to be synthesized; 8.3.2 The synthesis task; 8.3.3 Measuring the analytical validity; 8.3.4 Caveats in the use of synthetic datasets; 8.3.5 Assessing the disclosure risk; 8.3.5.1 Log-linear modeling to estimate the number of matches in the population. - 8.3.5.2 Results from the disclosure risk evaluations. - The aim of this book is to give the reader a detailed introduction to the different approaches to generating multiply imputed synthetic datasets. It describes all approaches that have been developed so far, provides a brief history of synthetic datasets, and gives useful hints on how to deal with real data problems like nonresponse, skip patterns, or logical constraints. Each chapter is dedicated to one approach, first describing the general concept followed by a detailed application to a real dataset providing useful guidelines on how to implement the theory in practice. The discussed multipl
|
| Emner | |
| Sjanger | |
| Dewey | |
| ISBN | 1461403251
|
