Approaches for dealing with missing data in health care studies

Aim. The aims of this study were to highlight the problems associated with missing data in healthcare research and to demonstrate the use of several techniques for dealing with missing values, through the use of an illustrative example. Background. In healthcare research studies, it is almost impossible to avoid at least some missing values during data collection, which in turn can threaten the validity of the study conclusions. A range of methods for reducing the impact of missing data on the validity of study findings have been developed, depending on the nature and patterns which the missing values may take. Design. A discursive study. Methods. Several techniques designed to deal with missing data are described and applied to an illustrative example. These methods include complete-case analysis, available-case analysis, as well as single and multiple imputation. Conclusions. If research data contain missing values that are not randomly distributed, then the study results are likely to be biased unless an effective approach to dealing with the missing values is implemented. Relevance to clinical practice. If nursing and healthcare practice is to be informed by research findings, then these findings must be reliable and valid. Researchers should report the details of missing data, and appropriate methods for dealing with missing values should be incorporated into the data analysi