The more data analysis you do, the more you realise just how important missing data is. It is imperative that you understand where missing values exist in your own data. By following the simple steps in this chapter, you will be able to determine whether the cases (commonly patients) with missing values are a different population to those with complete data. This is the basis for understanding the impact of missing data on your analyses.
Whether you remove cases, remove variables, impute data, or model missing values, always check how each approach alters the conclusions of your analysis. Be transparent when you report your results and include the alternative approaches in appendices of published work.