Nonlinear Mixed-Effects Modeling
A nonlinear mixed-effects (NLME) model is a statistical model that incorporates both fixed effects (population parameters) and random effects (individual variations). It recognizes correlations within sample subgroups and works with small sample sizes. You can estimate population parameters while considering individual variations using various mixed-effects methods, such as stochastic approximation of expectation-maximization (SAEM), first-order conditional estimate (FOCE), first-order estimate (FO), linear mixed-effects (LME), and restrict LME approximation. For details, see Nonlinear Mixed-Effects Modeling.
Perform NLME Estimation
|Perform parameter estimation using SimBiology problem object (Since R2021b)|
|Fit nonlinear mixed-effects model (requires Statistics and Machine Learning Toolbox software)|
|Simulate and evaluate fitted SimBiology model|
|Simulate a SimBiology model, adding variations by sampling the error model|
|Generate parameters by sampling covariate model (requires Statistics and Machine Learning Toolbox software)|
|Sample error based on error model and add noise to input data|
|Return a copy of the covariate model that was used for the nonlinear mixed-effects
estimation using |
|Create dose objects from groupedData object|
|Return the simulation results of a fitted nonlinear mixed-effects model|
|Create design matrix needed for fit|
|Return SimBiology dose object|
|Create structure containing initial estimates fixed effects needed for fit|
|Check covariate model for errors|
Plot NLME Results
|Plot status of nonlinear mixed-effects estimation|
|Create box plot showing the variation of estimated SimBiology model parameters|
|Compare simulation results to the training data, creating a time-course subplot for each group|
|Compare predictions to actual data, creating a subplot for each response|
|Plot the residuals for each response, using the time, group, or prediction as the x-axis|
|Plot the distribution of the residuals|
Data Variables and Problem Object for Fitting
|SimBiology problem object for parameter estimation (Since R2021b)|
|Table-like collection of data and metadata for fitting in SimBiology|
|Object containing information about estimated model quantities|
|Results object containing estimation results from nonlinear mixed-effects modeling|
- Nonlinear Mixed-Effects Modeling
SimBiology allows you to estimate population parameters (fixed effects) while considering individual variations (random effects) using nonlinear mixed-effect techniques.
- Supported Methods for Parameter Estimation in SimBiology
SimBiology® supports a variety of optimization methods for least-squares and mixed-effects estimation problems.
- Error Models
SimBiology supports constant, proportional, combined, and exponential error models.
- Model the Population Pharmacokinetics of Phenobarbital in Neonates
Perform nonlinear mixed-effects modeling using clinical pharmacokinetic data.
- Fit PK Parameters Using SimBiology Problem-Based Workflow
Estimate model parameters using a SimBiology problem object.