Missing Data Essentials Part 1: Detecting and Evaluating Patterns of Missingness in Longitudinal Cardiovascular Studies

Missing data are common in cardiovascular nursing and allied health research, especially in longitudinal studies. Common problems associated with missing data are reduced sample size, reduced statistical power and precision, and potentially biased results. There are several design strategies that can help minimize missing data including minimizing unnecessary items and incorporating reminders. It is important to understand common types of missingness, including item nonresponse, item-level missingness, wave nonresponse, and structural missingness, and to understand common mechanisms of missingness, including missing completely at random, missing at random, and missing not at random. This methods paper provides worked examples to illustrate several of these design and methodological considerations.