Categories &

Functions List

Class Definition: GeneralizedLinearMixedModel

statistics: GeneralizedLinearMixedModel

Generalized linear mixed-effects model fitted to data.

A GeneralizedLinearMixedModel object represents a fitted generalized linear mixed-effects model: a generalized linear model whose linear predictor X*beta + Z*b includes normally distributed random effects b ~ N(0, Psi). Objects are created with fitglme.

The model is fitted by penalized quasi-likelihood. The fixed-effects estimates and their statistics are available through the Coefficients table, the covariance parameters through covarianceParameters, and predictions, residuals, and hypothesis tests through the predict, residuals, anova, coefTest, and coefCI methods.

See also: fitglme, fitlme, GeneralizedLinearModel

Source Code: GeneralizedLinearMixedModel

The GeneralizedLinearMixedModel class contains the following properties:

A character vector naming the distribution of the response, one of 'binomial', 'poisson' and 'normal'. This property is read-only.

A character vector naming the link, one of 'logit', 'log' and 'identity'. This property is read-only.

A character vector naming the method that fitted the model, one of 'MPL', 'REMPL', 'Laplace' and 'ApproximateLaplace'. This property is read-only.

A positive scalar. It is estimated for a normal response and fixed at 1 for a binomial or Poisson one. This property is read-only.

A positive integer counting the observations used for the fit. This property is read-only.

A positive integer counting the fixed-effects coefficients of the model. This property is read-only.

A table with one row per fixed-effects coefficient, its row names taken from CoefficientNames, and the variables Estimate, SE, tStat, DF, pValue, Lower and Upper. Lower and Upper bound a 95% confidence interval. This property is read-only.

A square numeric matrix, one row and column per fixed-effects coefficient, holding the estimated covariance of the estimates in Coefficients. This property is read-only.

A cell array of character vectors with one name per fixed-effects coefficient. This property is read-only.

A scalar. It is a pseudo log-likelihood when FitMethod is 'MPL' or 'REMPL', and a Laplace approximation to the log-likelihood otherwise. This property is read-only.

A scalar structure with the fields AIC, BIC, LogLikelihood and Deviance. The parameter count behind AIC and BIC holds the fixed-effects coefficients, the covariance parameters and the dispersion. This property is read-only.

A nonnegative integer, NumObservations less NumCoefficients. This property is read-only.

A character vector describing the model. It is empty for a fit built from design matrices, which carries no formula. This property is read-only.

A character vector naming the response. It is empty for a fit built from design matrices. This property is read-only.

The GeneralizedLinearMixedModel class offers the following public methods:

GeneralizedLinearMixedModel: glme = GeneralizedLinearMixedModel (info)

GeneralizedLinearMixedModel: [beta, names] = fixedEffects (glme)

GeneralizedLinearMixedModel: b = randomEffects (glme)

GeneralizedLinearMixedModel: [psi, disp] = covarianceParameters (glme)

GeneralizedLinearMixedModel: yf = fitted (glme)

GeneralizedLinearMixedModel: r = residuals (glme)
GeneralizedLinearMixedModel: r = residuals (glme, "ResidualType", type)

GeneralizedLinearMixedModel: ypred = predict (glme, Xnew, Znew, Gnew)

GeneralizedLinearMixedModel: tbl = anova (glme)

GeneralizedLinearMixedModel: [p, F, df1, df2] = coefTest (glme, H)

GeneralizedLinearMixedModel: ci = coefCI (glme, alpha)

GeneralizedLinearMixedModel: D = designMatrix (glme, type)