### Provisional Script for LCGA, one class, following Ram, Grimm & Estabrook (2017) script on GMM, pg. 148

class1 <- mxModel('Class1', type='RAM',
                  manifestVars=c('depression_scale_2','depression_scale_3','depression_scale_4','depression_scale_5','depression_scale_6','depression_scale_7','depression_scale_8','depression_scale_9'),
                                 latentVars=c('eta_1','eta_2'),
                                 # residual variances
                                 mxPath(from=c('depression_scale_2','depression_scale_3','depression_scale_4','depression_scale_5','depression_scale_6','depression_scale_7','depression_scale_8','depression_scale_9'),arrows=2,
                                 free=TRUE, values=1, labels='theta'),
                                 # latent variances and covariance
                                 mxPath(from=c('eta_1','eta_2'), arrows=2, connect='unique.pairs',
                                 free=TRUE, values=c(0,0,0), labels=c('psi_11', 'psi_12', 'psi_22')),
                                 # intercept loadings
                                 mxPath(from='eta_1', to=c('depression_scale_2','depression_scale_3','depression_scale_4','depression_scale_5','depression_scale_6','depression_scale_7','depression_scale_8','depression_scale_9'), arrows=1,
                                 free=FALSE, values=1),
                                 # slope loadings
                                 mxPath(from='eta_2', to=c('depression_scale_2','depression_scale_3','depression_scale_4','depression_scale_5','depression_scale_6','depression_scale_7','depression_scale_8','depression_scale_9'), arrows=1,
                                 free=FALSE, values=c(-3,-2,-1,0,1,2,3,4)),
                                 # latent variable means
                                 mxPath(from='one', to=c('eta_1', 'eta_2'), arrows=1,
                                 free=TRUE, values=c(1, 6), labels=c('alpha_1_c1', 'alpha_2_c1')),
                  # ML Fit Function to run for each individual
                  mxFitFunctionML(vector=TRUE)
) # close model for class 1

classRP1 <- mxMatrix('Full', 1, 1, free=c(TRUE),
                    values=1, lbound=0.001, labels=c('p1'), name='RProps')
classP1 <- mxAlgebra(RProps %x% (1 / sum(RProps)), name='Props')
algObj1 <- mxAlgebra(-2* sum(log(Props[1,1] %x% Class1.objective)),
                    name='mixtureObj1')
obj1 <- mxFitFunctionAlgebra('mixtureObj1')

lcga.1.means <- mxModel('1Class Means LCGA',
                       mxData(observed=ML_dfwide, type='raw'),
                       class1,classRP1, classP1, algObj1, obj1, mxComputeSimAnnealing())
lcga.1.means.fit <- mxRun(lcga.1.means)
mxTryHard_lcga.1.means.fit <- mxTryHard(lcga.1.means, intervals = TRUE, exhaustive = TRUE) # Run the model, returning the result into model
summary(mxTryHard_lcga2cl_Fit)
mxStandardizeRAMpaths(mxTryHard_lcga.1.means.fit, SE=FALSE)