A comparison of the general linear mixed model and repeated measures ANOVA using a dataset with multiple missing data...

Area of Science:

• Nursing Research
• Biostatistics
• Longitudinal Data Analysis

Background:

• Phenomena of interest are often dynamic, requiring advanced statistical methods.
• Traditional statistical methods often assume a linear view of biological and behavioral data.
• Longitudinal datasets frequently contain missing data points and exhibit nonlinear characteristics.

Purpose of the Study:

• To demonstrate the advantages of the general linear mixed model (mixed model) for analyzing nonlinear, longitudinal datasets.
• To compare the mixed model's performance against the repeated measures ANOVA.
• To highlight the mixed model's utility in handling missing data and individual variability.

Main Methods:

• Utilized the general linear mixed model (mixed model) for analyzing longitudinal data.
• Employed repeated measures ANOVA as a comparative statistical method.
• Described decision-making steps for data analysis using both mixed models and repeated measures ANOVA.

Main Results:

• The mixed model accommodates missing data points common in longitudinal studies.
• The mixed model effectively models nonlinear individual characteristics.
• Comparison with repeated measures ANOVA highlights the mixed model's advantages for dynamic phenomena.

Conclusions:

• The mixed model is a powerful tool for analyzing complex, dynamic phenomena in nursing research.
• Researchers should consider the mixed model for longitudinal studies with missing data and nonlinear trends.
• The mixed model provides a more flexible and accurate approach compared to traditional methods like repeated measures ANOVA.