GLMMOptions<T>

Options & Configuration · AiDotNet.Models.Options

Configuration options for Generalized Linear Mixed-Effects Models (GLMM).

Inheritance: ModelOptions → RegressionOptions<T> → GLMMOptions<T>

For Beginners

GLMMs let you model grouped/nested data when your outcome isn’t continuous and normally distributed.

Common scenarios:

  • Binary outcome (pass/fail): Use Binomial family with Logit link
  • Count data (# of events): Use Poisson family with Log link
  • Overdispersed counts: Use NegativeBinomial family
  • Continuous positive: Use Gamma family with Log link

Key settings:

  • Family: The distribution of your response variable
  • LinkFunction: How to connect predictors to the mean response
  • EstimationMethod: PQL is faster, Laplace is more accurate

How It Works

GLMMs combine generalized linear models with random effects for hierarchical data with non-Gaussian responses (binary, count, etc.).

Constructors

Constructor Summary
GLMMOptions() Initializes a new instance of GLMMOptions with sensible defaults.

Properties

Property Summary
GLMMEstimationMethod EstimationMethod { get; set; } Gets or sets the estimation method.
GLMMFamily Family { get; set; } Gets or sets the response distribution family.
GLMMLinkFunction LinkFunction { get; set; } Gets or sets the link function.
T NegBinomialTheta { get; set; } Gets or sets the theta parameter for Negative Binomial family.
bool BoundVarianceComponents { get; set; } Gets or sets whether to bound variance components to be non-negative.
bool ComputeConfidenceIntervals { get; set; } Gets or sets whether to compute confidence intervals for fixed effects.
bool Verbose { get; set; } Gets or sets whether to print verbose output.
double ConfidenceLevel { get; set; } Gets or sets the confidence level.
double Tolerance { get; set; } Gets or sets the convergence tolerance.
int MaxIterations { get; set; } Gets or sets the maximum number of iterations.

Methods

Method Summary
GLMMOptions<T> ForBinaryClassification() Creates options for logistic mixed-effects model (binary outcomes).
GLMMOptions<T> ForCountData() Creates options for Poisson mixed-effects model (count data).
GLMMOptions<T> ForPositiveContinuous() Creates options for Gamma mixed-effects model (positive continuous).