Statistics in medicine
-
Statistics in medicine · Apr 1991
ReviewMultiple imputation in health-care databases: an overview and some applications.
Multiple imputation for non-response replaces each missing value by two or more plausible values. The values can be chosen to represent both uncertainty about the reasons for non-response and uncertainty about which values to impute assuming the reasons for non-response are known. This paper provides an overview of methods for creating and analysing multiply-imputed data sets, and illustrates the dramatic improvements possible when using multiple rather than single imputation. A major application of multiple imputation to public-use files from the 1970 census is discussed, and several exploratory studies related to health care that have used multiple imputation are described.
-
A few large clinical information databases have been established within larger medical information systems. Although they are smaller than claims databases, these clinical databases offer several advantages: accurate and timely data, rich clinical detail, and continuous parameters (for example, vital signs and laboratory results). ⋯ In addition, practice databases can be used to identify subjects for prospective studies. Further methodologic developments are necessary to deal with the prevalent problems of missing data and various forms of bias if such databases are to grow and contribute valuable clinical information.