Related Experiment Videos
Examining solutions to missing data in longitudinal nursing research
Mary B Roberts1, Mary C Sullivan2, Suzy B Winchester2
1Memorial Hospital of Rhode Island, Center for Primary Care and Prevention, Pawtucket, RI, USA.
Insights
Missing data in pediatric longitudinal studies can be addressed using a three-step approach. Fully conditional specification (FCS) imputation is recommended for both continuous and categorical variables to maintain data integrity.
Area of Science:
- Pediatric research
- Longitudinal study design
- Biostatistics
Background:
- Longitudinal studies are crucial for understanding child development and health patterns.
- Missing data can significantly compromise the integrity and value of research findings.
- Effective strategies are needed to manage missing data in pediatric research.
Purpose of the Study:
- To introduce a novel three-step methodology for assessing and managing missing data.
- To demonstrate the application of this approach using real-world data from a longitudinal study of premature infants.
- To evaluate imputation methods for both continuous and categorical variables.
Main Methods:
- A three-step approach incorporating simulations was employed.
- Missing data patterns (Missing Completely at Random, Missing at Random, Not Missing at Random) were analyzed.
- Imputation techniques including mean replacement, stochastic regression, multiple imputation, and fully conditional specification (FCS) were evaluated.
Main Results:
- Missingness rates ranged from 16-23% for continuous and 1-28% for categorical variables.
- Fully conditional specification (FCS) imputation yielded the smallest differences in mean and standard deviation estimates for continuous data.
- FCS imputation proved acceptable for categorical data, with simulation results confirming these findings.
Conclusions:
- Properly handling missing data is essential to protect investments in longitudinal data collection.
- The proposed three-step approach and FCS imputation can enhance the scientific value of pediatric longitudinal studies.
- Implementing robust missing data strategies is vital for reliable research outcomes in child health.
Purpose:
Longitudinal studies are highly valuable in pediatrics because they provide useful data about developmental patterns of child health and behavior over time. When data are missing, the value of the research is impacted. The study's purpose was to (1) introduce a three-step approach to assess and address missing data and (2) illustrate this approach using categorical and continuous-level variables from a longitudinal study of premature infants.
Methods:
A three-step approach with simulations was followed to assess the amount and pattern of missing data and to determine the most appropriate imputation method for the missing data. Patterns of missingness were Missing Completely at Random, Missing at Random, and Not Missing at Random. Missing continuous-level data were imputed using mean replacement, stochastic regression, multiple imputation, and fully conditional specification (FCS). Missing categorical-level data were imputed using last value carried forward, hot-decking, stochastic regression, and FCS. Simulations were used to evaluate these imputation methods under different patterns of missingness at different levels of missing data.
Results:
The rate of missingness was 16-23% for continuous variables and 1-28% for categorical variables. FCS imputation provided the least difference in mean and standard deviation estimates for continuous measures. FCS imputation was acceptable for categorical measures. Results obtained through simulation reinforced and confirmed these findings.
Practice Implications:
Significant investments are made in the collection of longitudinal data. The prudent handling of missing data can protect these investments and potentially improve the scientific information contained in pediatric longitudinal studies.