Displaying Uncertainty In Data Fusion By Multiple Imputation

• Activity Number: 115
• Type: Topic Contributed
• Date/Time: Monday, August 1, 2011 : 8:30 AM to 10:20 AM
• Sponsor: Section on Survey Research Methods
• Author(s): Susanne Rässler*+ and Julia Cielebak
• Companies: Otto-Friedrich-Universität Bamberg and Otto-Friedrich-Universität Bamberg
• Keywords: statistical matching ; bounds ; missing data ; combining data from different sources

Abstract

Data fusion techniques typically aim to achieve a complete data file from different sources which do not contain the same units. Traditionally, data fusion, in the US also addressed by the term statistical matching, is done on the basis of variables common to all files. It is well known that those approaches establish conditional independence of the (specific) variables not jointly observed given the common variables, although they may be conditionally dependent in reality. However, if the common variables are (carefully) chosen in a way that already establishes conditional independence, then inference about the actually unobserved association is valid. Unfortunately, this assumption is not testable yet. Hence, we treat the data fusion situation as a problem of missing data by design and suggest imputation approaches to multiply impute the specific variables using informative prior information to account for violations of the conditional independence assumption. In a simulation study it is also shown that multiple imputation techniques allows to efficiently and easily use auxiliary information.