Free Trial

Safari Books Online is a digital library providing on-demand subscription access to thousands of learning resources.

  • Create BookmarkCreate Bookmark
  • Create Note or TagCreate Note or Tag
  • PrintPrint

15.7. Multiple imputation

Multiple imputation (MI) provides an approach to missing values that’s based on repeated simulations. MI is frequently the method of choice for complex missing values problems. In MI, a set of complete datasets (typically 3 to 10) is generated from an existing dataset containing missing values. Monte Carlo methods are used to fill in the missing data in each of the simulated datasets. Standard statistical methods are applied to each of the simulated datasets, and the outcomes are combined to provide estimated results and confidence intervals that take into account the uncertainty introduced by the missing values. Good implementations are available in R through the Amelia, mice, and mi packages. In this section we’ll focus on the approach provided by the mice (multivariate imputation by chained equations) package.

To understand how the mice package operates, consider the diagram in figure 15.5.


  

You are currently reading a PREVIEW of this book.

                                                                                                                    

Get instant access to over $1 million worth of books and videos.

  

Start a Free Trial


  
  • Safari Books Online
  • Create BookmarkCreate Bookmark
  • Create Note or TagCreate Note or Tag
  • PrintPrint