Stochastic Expectation Maximization Algorithm for Linear Mixed-Effects Model with Interactions in the Presence of...

Area of Science:

• Statistics
• Biostatistics
• Psychometrics

Background:

• Missing data is a common challenge in statistical modeling.
• Linear mixed-effects models (LMEM) are widely used in various fields, including psychology and medicine.
• Handling unobserved values in LMEM with multiple interactions requires robust algorithms.

Purpose of the Study:

• To introduce a novel algorithm based on stochastic expectation maximization (SEM) for addressing unobserved values in LMEM with multiple interactions.
• To evaluate the performance of the proposed SEM algorithm against existing methods.
• To emphasize the significance of incorporating maximum effects in statistical models.

Main Methods:

• Development of a new algorithm using stochastic expectation maximization (SEM).
• Comparative analysis with stochastic approximation expectation maximization (SAEM) and Monte Carlo Markov chain (MCMC) algorithms.
• Application and validation using simulated psychological data and real-world datasets.

Main Results:

• The proposed SEM algorithm demonstrated superior performance compared to SAEM and MCMC.
• The study highlighted the critical impact of including maximum effects on model accuracy.
• The algorithm effectively managed missing data in complex LMEM scenarios.

Conclusions:

• The novel SEM algorithm is a highly preferable method for handling missing data in LMEM with multiple interactions.
• The findings underscore the importance of robust algorithms for accurate statistical inference.
• The proposed method offers a valuable tool for researchers dealing with incomplete datasets in LMEM.