LMMmap is the output of iMap4 core function imapLMM. The fields of LMMmap are nearly identical to the output from LinearMixedModel class. For each modelled pixel, iMap4 saves the model criterion, variances explained, error sum of squares, coefficient estimates and their covariance matrix for both fixed and random effects, and the ANOVA results on the LMM. Additional modelling specifications, as well as other model parameters including LMM formula, design matrix for fixed and random effect, and residual degrees of freedom, are also saved in LMMmap. Linear contrasts and other analyses based on variance or covariance can be performed afterwards from the model fitting information. Any other computation on the LinearMixedModel output can also be replicated on LMMmap.

For example, the LMMmap in Example 1 is shown below:

% LMMmap =  
%                    runopt: [1x1 struct]  
%              VariableInfo: [6x4 dataset]  
%                 Variables: [118x6 dataset]  
%                 FitMethod: 'REML'  
%                   Formula: [1x1 classreg.regr.LinearMixedFormula]  
%                    modelX: [118x6 double]  
%                FitOptions: {'DummyVarCoding'  'effect' 'Fitmethod' 'REML'}  
%                  modelDFE: 112  
%          CoefficientNames: {1x6 cell}  
%                     Anova: [1x1 struct]  
%                SinglePred: [1x1 struct]  
%             RandomEffects: [1x1 struct]  
%     CoefficientCovariance: [4-D double]  
%                       MSE: [205x256 double]  
%                       SSE: [205x256 double]  
%                       SST: [205x256 double]  
%                       SSR: [205x256 double]  
%                  Rsquared: [2x205x256 double]  
%            ModelCriterion: [4x205x256 double]  
%              Coefficients: [4-D double]  

results matching ""

    No results matching ""