Important: Read this before posting to this forum

  1. This forum is for questions related to the use of Apollo. We will answer some general choice modelling questions too, where appropriate, and time permitting. We cannot answer questions about how to estimate choice models with other software packages.
  2. There is a very detailed manual for Apollo available at http://www.ApolloChoiceModelling.com/manual.html. This contains detailed descriptions of the various Apollo functions, and numerous examples are available at http://www.ApolloChoiceModelling.com/examples.html. In addition, help files are available for all functions, using e.g. ?apollo_mnl
  3. Before asking a question on the forum, users are kindly requested to follow these steps:
    1. Check that the same issue has not already been addressed in the forum - there is a search tool.
    2. Ensure that the correct syntax has been used. For any function, detailed instructions are available directly in Apollo, e.g. by using ?apollo_mnl for apollo_mnl
    3. Check the frequently asked questions section on the Apollo website, which discusses some common issues/failures. Please see http://www.apollochoicemodelling.com/faq.html
    4. Make sure that R is using the latest official release of Apollo.
  4. If the above steps do not resolve the issue, then users should follow these steps when posting a question:
    1. provide full details on the issue, including the entire code and output, including any error messages
    2. posts will not immediately appear on the forum, but will be checked by a moderator first. This may take a day or two at busy times. There is no need to submit the post multiple times.

Latent class fail with "No covariance matrix to compute"

Ask questions about the results reported after estimation. If the output includes errors, please include your model code if possible.
Post Reply
JoeSu
Posts: 4
Joined: 10 Mar 2022, 00:18

Latent class fail with "No covariance matrix to compute"

Post by JoeSu »

Hi

I am using the Latent class with continuous random parameters. The model failed saying "Estimation failed. No covariance matrix to compute" and the results come out with NaNs.

Could you please kindly let me know what should I do to solve this problem? Many thanks in advance.

Code for my model:

Code: Select all

apollo_control = list(
  modelName       = "mangrove restoration CE",
  modelDescr      = "Latent Class method on mangrove restoration CE data",
  indivID         = "ID", 
  mixing = TRUE ,
  nCores          = 6,
  outputDirectory = "/Users/pw123456ifi/Desktop/Apollo"
)

# ################################################################# #
#### LOAD DATA AND APPLY ANY TRANSFORMATIONS                     ####
# ################################################################# #

### Loading data from package
### if data is to be loaded from a file (e.g. called data.csv), 
### the code would be: database = read.csv("data.csv",header=TRUE)

### for data dictionary, use ?apollo_swissRouteChoiceData

# ################################################################# #
#### DEFINE MODEL PARAMETERS                                     ####
# ################################################################# #

### Vector of parameters, including any that are kept fixed in estimation
apollo_beta = c(asc = -10,
                sigma_asc = 0,
                beta_area_a       = 0.02,
                sigma_area_a   = 0,
                beta_area_b       = 0.02,
                sigma_area_b   = 0,
                beta_area_c       = 0.02,
                sigma_area_c   = 0,
                beta_area_d       = 0.02,
                sigma_area_d   = 0,
                #beta_area_e       = 0,
                beta_fish_a   = 0.002,
                sigma_fish_a  = 0,
                beta_fish_b   = 0.002,
                sigma_fish_b    = 0,
                beta_fish_c   = 0.002,
                sigma_fish_c   = 0,
                beta_fish_d    = 0.002,
                sigma_fish_d  = 0,
                #beta_fish_e    = 0,
                beta_CO2_a      = 0.002,
                sigma_CO2_a      = 0,
                beta_CO2_b      = 0.002,
                sigma_CO2_b  = 0,
                beta_CO2_c      = 0.002,
                sigma_CO2_c     = 0,
                beta_CO2_d      = 0.002,
                sigma_CO2_d     = 0,
                #beta_CO2_e      = 0,
                beta_typhoon_a      = 0.15,
                sigma_typhoon_a     = 0,
                beta_typhoon_b      = 0.15,
                sigma_typhoon_b     =0,
                beta_typhoon_c      = 0.15,
                sigma_typhoon_c       = 0,
                beta_typhoon_d      = 0.15,
                sigma_typhoon_d     = 0,
                #beta_typhoon_e      = 0,
                beta_Aes_a      = 0.15,
                sigma_Aes_a    = 0,
                beta_Aes_b      = 0.15,
                sigma_Aes_b     = 0,
                beta_Aes_c      = 0.15,
                sigma_Aes_c     = 0,
                beta_Aes_d      = 0.15,
                sigma_Aes_d     = 0,    
                #beta_Aes_e      = 0,
                beta_mosquito_a      = -0.3,
                sigma_mosquito_a    = 0,
                beta_mosquito_b      = -0.3,
                sigma_mosquito_b    = 0,
                beta_mosquito_c      = -0.3,
                sigma_mosquito_c     = 0,
                beta_mosquito_d      = -0.3,
                sigma_mosquito_d      = 0,
                #beta_mosquito_e      = 0,
                beta_log_Cost_a      = -3,
                sigma_log_Cost_a     = 1,
                beta_log_Cost_b      = -3,
                sigma_log_Cost_b     = 1,
                beta_log_Cost_c      = -3,
                sigma_log_Cost_c     = 1,
                beta_log_Cost_d      = -3,
                sigma_log_Cost_d     = 1,
                #beta_Cost_e      = 0,
                delta_a_mu      =  0,
                delta_a_sig     =  0,
                #gamma_age_a       = 0,
                #gamma_gender_a     =0,
                gamma_residence_a       = 0,
                gamma_income_a       = 0,
                gamma_acknowledgement_a     =0,
                gamma_frequency_a       = 0,
                gamma_education_a       = 0,
                delta_b           = 0,
                #gamma_age_b       = 0,
                #gamma_gender_b     =0,
                gamma_residence_b       = 0,
                gamma_acknowledgement_b     =0,
                gamma_income_b       = 0,
                gamma_frequency_b       = 0,
                gamma_education_b       = 0,
                delta_c           = 0,
               # gamma_age_c    = 0,
                #gamma_gender_c     =0,
                gamma_residence_c       = 0,
                gamma_acknowledgement_c     =0,
                gamma_income_c       = 0,
                gamma_education_c       = 0,
                gamma_frequency_c       = 0,
                delta_d           = 0,
                #gamma_age_d    = 0,
                #gamma_gender_d     =0,
                gamma_residence_d       = 0,
                gamma_acknowledgement_d     =0,
                gamma_income_d       = 0,
                gamma_education_d       = 0,
                gamma_frequency_d       = 0)
                #delta_e           = 0,
                #gamma_age_e    = 0,
                #gamma_gender_e     =0,
                #gamma_residence_e       = 0,
                #gamma_acknowledgement_e     =0,
                #gamma_income_e       = 0,
                #gamma_education_e       = 0,
                #gamma_frequency_e       = 0)

### Vector with names (in quotes) of parameters to be kept fixed at their starting value in apollo_beta, use apollo_beta_fixed = c() if none
apollo_beta_fixed = c()
apollo_fixed = c("delta_d","gamma_acknowledgement_d","gamma_income_d","gamma_education_d","gamma_frequency_d","gamma_residence_d")


### Set parameters for generating draws
apollo_draws = list(
  interDrawsType = "halton",
  interNDraws    = 500,
  interUnifDraws = c(),
  interNormDraws = c("draws_area","draws_fish","draws_CO2","draws_typhoon","draws_Aes",
                     "draws_mosquito","draws_Cost","draws_asc","draws_pi"),
  intraDrawsType = "halton",
  intraNDraws    = 0,
  intraUnifDraws = c(),
  intraNormDraws = c()
)


### Create random parameters
apollo_randCoeff = function(apollo_beta, apollo_inputs){
  randcoeff = list()
  
  randcoeff[["b_area_a"]] =beta_area_a + sigma_area_a * draws_area 
  randcoeff[["b_area_b"]] =beta_area_b + sigma_area_b * draws_area 
  randcoeff[["b_area_c"]] =beta_area_c + sigma_area_c * draws_area 
  randcoeff[["b_area_d"]] =beta_area_d + sigma_area_d * draws_area 
  randcoeff[["b_fish_a"]] =  beta_fish_a + sigma_fish_a * draws_fish 
  randcoeff[["b_fish_b"]] =  beta_fish_b + sigma_fish_b * draws_fish 
  randcoeff[["b_fish_c"]] =  beta_fish_c + sigma_fish_c * draws_fish 
  randcoeff[["b_fish_d"]] =  beta_fish_d + sigma_fish_d * draws_fish 
  randcoeff[["b_CO2_a"]] = beta_CO2_a + sigma_CO2_a * draws_CO2 
  randcoeff[["b_CO2_b"]] = beta_CO2_b + sigma_CO2_b * draws_CO2 
  randcoeff[["b_CO2_c"]] = beta_CO2_c + sigma_CO2_c * draws_CO2 
  randcoeff[["b_CO2_d"]] = beta_CO2_d + sigma_CO2_d * draws_CO2 
  randcoeff[["b_typhoon_a"]] =  beta_typhoon_a + sigma_typhoon_a * draws_typhoon
  randcoeff[["b_typhoon_b"]] =  beta_typhoon_b + sigma_typhoon_b * draws_typhoon 
  randcoeff[["b_typhoon_c"]] =  beta_typhoon_c + sigma_typhoon_c * draws_typhoon 
  randcoeff[["b_typhoon_d"]] =  beta_typhoon_d + sigma_typhoon_d * draws_typhoon 
  randcoeff[["b_Aes_a"]] =  beta_Aes_a + sigma_Aes_a * draws_Aes
  randcoeff[["b_Aes_b"]] =  beta_Aes_b + sigma_Aes_b * draws_Aes
  randcoeff[["b_Aes_c"]] =  beta_Aes_c + sigma_Aes_c * draws_Aes
  randcoeff[["b_Aes_d"]] =  beta_Aes_d + sigma_Aes_d * draws_Aes
  randcoeff[["b_mosquito_a"]] =  beta_mosquito_a + sigma_mosquito_a * draws_mosquito 
  randcoeff[["b_mosquito_b"]] =  beta_mosquito_b + sigma_mosquito_b * draws_mosquito 
  randcoeff[["b_mosquito_c"]] =  beta_mosquito_c + sigma_mosquito_c * draws_mosquito 
  randcoeff[["b_mosquito_d"]] =  beta_mosquito_d + sigma_mosquito_d * draws_mosquito 
  randcoeff[["b_Cost_a"]] =  -exp(beta_log_Cost_a + sigma_log_Cost_a * draws_Cost)
  randcoeff[["b_Cost_b"]] =  -exp(beta_log_Cost_b + sigma_log_Cost_b * draws_Cost)
  randcoeff[["b_Cost_c"]] =  -exp(beta_log_Cost_c + sigma_log_Cost_c * draws_Cost)
  randcoeff[["b_Cost_d"]] =  -exp(beta_log_Cost_d + sigma_log_Cost_d * draws_Cost)
  randcoeff[["ec"]] =  sigma_asc * draws_asc
  randcoeff[["delta_a"]] = delta_a_mu  + delta_a_sig*draws_pi
  
  return(randcoeff)
}


# ################################################################# #
#### DEFINE LATENT CLASS COMPONENTS                              ####
# ################################################################# #


apollo_lcPars=function(apollo_beta, apollo_inputs){
  lcpars = list()
  lcpars[["beta_area"]] = list(b_area_a, b_area_b, b_area_c, b_area_d)
  lcpars[["beta_fish"]] = list(b_fish_a, b_fish_b, b_fish_c, b_fish_d)
  lcpars[["beta_CO2"]] = list(b_CO2_a, b_CO2_b, b_CO2_c, b_CO2_d)
  lcpars[["beta_typhoon"]] = list(b_typhoon_a, b_typhoon_b, b_typhoon_c, b_typhoon_d)
  lcpars[["beta_Aes"]] = list(b_Aes_a, b_Aes_b, b_Aes_c, b_Aes_d)
  lcpars[["beta_mosquito"]] = list(b_mosquito_a, b_mosquito_b, b_mosquito_c, b_mosquito_d)
  lcpars[["beta_Cost"]] = list(b_Cost_a, b_Cost_b, b_Cost_c, b_Cost_d)
  
  
  V=list()
  V[["class_a"]] = delta_a + gamma_acknowledgement_a*acknowledgement2 +gamma_income_a*income_HH3+
    gamma_education_a*education3+gamma_frequency_a*frequency3 + gamma_residence_a*residence2
  V[["class_b"]] = delta_b + gamma_acknowledgement_b*acknowledgement2+gamma_income_b*income_HH3+
    gamma_education_b*education3+gamma_frequency_b*frequency3 +gamma_residence_b*residence2
  V[["class_c"]] = delta_c + gamma_acknowledgement_c*acknowledgement2+gamma_income_c*income_HH3+
    gamma_education_c*education3+gamma_frequency_c*frequency3+gamma_residence_c*residence2
  V[["class_d"]] = delta_d + gamma_acknowledgement_d*acknowledgement2+gamma_income_d*income_HH3+
    gamma_education_d*education3+gamma_frequency_d*frequency3+gamma_residence_d*residence2
  #V[["class_e"]] = delta_e + gamma_acknowledgement_e*acknowledgement2+gamma_income_e*income_HH3+gamma_education_e*education3+gamma_frequency_e*frequency3
  
  ### Settings for class allocation models
  classAlloc_settings = list(
    classes      = c(class_a=1, class_b=2, class_c=3, class_d=4), 
    utilities    = V  
  )
  
  lcpars[["pi_values"]] = apollo_classAlloc(classAlloc_settings)
  
  return(lcpars)
}


# ################################################################# #
#### GROUP AND VALIDATE INPUTS                                   ####
# ################################################################# #

apollo_inputs = apollo_validateInputs()

# ################################################################# #
#### DEFINE MODEL AND LIKELIHOOD FUNCTION                        ####
# ################################################################# #

apollo_probabilities=function(apollo_beta, apollo_inputs, functionality="estimate"){
  
  ### Attach inputs and detach after function exit
  apollo_attach(apollo_beta, apollo_inputs)
  on.exit(apollo_detach(apollo_beta, apollo_inputs))
  
  ### Create list of probabilities P
  P = list()
  
  ### Define settings for MNL model component that are generic across classes
  mnl_settings = list(
    alternatives  = c(low="A", high="B", NB="C"),
    avail         = list(low=1, high=1, NB=1),
    choiceVar     = choice
  )
  
  ### Loop over classes
  for(s in 1:4){
    
    ### Compute class-specific utilities
    ### Compute class-specific utilities
    V=list()
    V[['NB']]  = asc + ec
    V[['low']]  = beta_area[[s]]*areaA/100  + beta_fish[[s]]*fishA  + beta_CO2[[s]]*CO2A + beta_typhoon[[s]]*typhoonA/1000 + 
      beta_Aes[[s]]*AesA + beta_mosquito[[s]]*mosquitoA + beta_Cost[[s]]*CostA
    V[['high']]  = beta_area[[s]]*areaB/100  + beta_fish[[s]]*fishB + beta_CO2[[s]]*CO2B + beta_typhoon[[s]]*typhoonB/1000 +
      beta_Aes[[s]]*AesB + beta_mosquito[[s]]*mosquitoB + beta_Cost[[s]]*CostB
    
    mnl_settings$utilities     = V
    mnl_settings$componentName = paste0("Class_",s)
    
    ### Compute within-class choice probabilities using MNL model
    P[[paste0("Class_",s)]] = apollo_mnl(mnl_settings, functionality)
    
    ### Take product across observation for same individual
    P[[paste0("Class_",s)]] = apollo_panelProd(P[[paste0("Class_",s)]], apollo_inputs ,functionality)
    
    ### Average across inter-individual draws within classes
    P[[paste0("Class_",s)]] = apollo_avgInterDraws(P[[paste0("Class_",s)]], apollo_inputs, functionality)
  }
  
  ### Compute latent class model probabilities
  lc_settings  = list(inClassProb = P, classProb=pi_values)
  P[["model"]] = apollo_lc(lc_settings, apollo_inputs, functionality)
  
  ### Average across inter-individual draws in class allocation probabilities
  P[["model"]] = apollo_avgInterDraws(P[["model"]], apollo_inputs, functionality)
  
  ### Prepare and return outputs of function
  P = apollo_prepareProb(P, apollo_inputs, functionality)
  return(P)
}



# ################################################################# #
#### MODEL ESTIMATION                                            ####
# ################################################################# #

### Optional starting values search
#apollo_beta=apollo_searchStart(apollo_beta, apollo_fixed,apollo_probabilities, apollo_inputs)

model = apollo_estimate(apollo_beta, apollo_fixed, apollo_probabilities, apollo_inputs)

Estimation process:

Code: Select all

Preparing user-defined functions.

Testing likelihood function...
Apollo found a model component of type classAlloc without a componentName. The name was set to
  "classAlloc" by default.
Setting "avail" is missing, so full availability is assumed.

Overview of choices for MNL model component Class_1:
                                     low    high      NB
Times available                  6174.00 6174.00 6174.00
Times chosen                     2903.00 2620.00  651.00
Percentage chosen overall          47.02   42.44   10.54
Percentage chosen when available   47.02   42.44   10.54

Overview of choices for MNL model component Class_2:
                                     low    high      NB
Times available                  6174.00 6174.00 6174.00
Times chosen                     2903.00 2620.00  651.00
Percentage chosen overall          47.02   42.44   10.54
Percentage chosen when available   47.02   42.44   10.54

Overview of choices for MNL model component Class_3:
                                     low    high      NB
Times available                  6174.00 6174.00 6174.00
Times chosen                     2903.00 2620.00  651.00
Percentage chosen overall          47.02   42.44   10.54
Percentage chosen when available   47.02   42.44   10.54

Overview of choices for MNL model component Class_4:
                                     low    high      NB
Times available                  6174.00 6174.00 6174.00
Times chosen                     2903.00 2620.00  651.00
Percentage chosen overall          47.02   42.44   10.54
Percentage chosen when available   47.02   42.44   10.54

Summary of class allocation for LC model component :
         Mean prob.
Class_1      0.2500
Class_2      0.2500
Class_3      0.2500
Class_4      0.2500
Class probability for model component "model" averaged across observations of each individual.

Pre-processing likelihood function...
Preparing workers for multithreading...

Testing influence of parameters
Starting main estimation
Initial function value: -7122.441 
Initial gradient value:
                    asc               sigma_asc             beta_area_a            sigma_area_a 
           2.066304e+02            7.710731e+00            8.268517e+02           -1.889842e+00 
            beta_area_b            sigma_area_b             beta_area_c            sigma_area_c 
           8.268517e+02           -1.889842e+00            8.268517e+02           -1.889842e+00 
            beta_area_d            sigma_area_d             beta_fish_a            sigma_fish_a 
           8.268517e+02           -1.889842e+00            9.082778e+02            1.465505e+02 
            beta_fish_b            sigma_fish_b             beta_fish_c            sigma_fish_c 
           9.082778e+02            1.465505e+02            9.082778e+02            1.465505e+02 
            beta_fish_d            sigma_fish_d              beta_CO2_a             sigma_CO2_a 
           9.082778e+02            1.465505e+02           -3.759434e+03            1.583446e+02 
             beta_CO2_b             sigma_CO2_b              beta_CO2_c             sigma_CO2_c 
          -3.759434e+03            1.583446e+02           -3.759434e+03            1.583446e+02 
             beta_CO2_d             sigma_CO2_d          beta_typhoon_a         sigma_typhoon_a 
          -3.759434e+03            1.583446e+02           -4.241461e+01            8.316066e-01 
         beta_typhoon_b         sigma_typhoon_b          beta_typhoon_c         sigma_typhoon_c 
          -4.241461e+01            8.316066e-01           -4.241461e+01            8.316066e-01 
         beta_typhoon_d         sigma_typhoon_d              beta_Aes_a             sigma_Aes_a 
          -4.241461e+01            8.316066e-01           -4.815464e+01            1.414961e+00 
             beta_Aes_b             sigma_Aes_b              beta_Aes_c             sigma_Aes_c 
          -4.815464e+01            1.414961e+00           -4.815464e+01            1.414961e+00 
             beta_Aes_d             sigma_Aes_d         beta_mosquito_a        sigma_mosquito_a 
          -4.815464e+01            1.414961e+00           -1.641941e+02           -2.814759e+00 
        beta_mosquito_b        sigma_mosquito_b         beta_mosquito_c        sigma_mosquito_c 
          -1.641941e+02           -2.814759e+00           -1.641941e+02           -2.814759e+00 
        beta_mosquito_d        sigma_mosquito_d         beta_log_Cost_a        sigma_log_Cost_a 
          -1.641941e+02           -2.814759e+00           -1.776934e+02            6.149588e+02 
        beta_log_Cost_b        sigma_log_Cost_b         beta_log_Cost_c        sigma_log_Cost_c 
          -1.776934e+02            6.149588e+02           -1.776934e+02            6.149588e+02 
        beta_log_Cost_d        sigma_log_Cost_d              delta_a_mu             delta_a_sig 
          -1.776934e+02            6.149588e+02            9.600407e-16            2.850266e-17 
      gamma_residence_a          gamma_income_a gamma_acknowledgement_a       gamma_frequency_a 
           1.020786e-15            6.569797e-15            8.169337e-16            3.231941e-15 
      gamma_education_a                 delta_b       gamma_residence_b gamma_acknowledgement_b 
          -1.122416e-15            9.600407e-16            1.020786e-15            8.169337e-16 
         gamma_income_b       gamma_frequency_b       gamma_education_b                 delta_c 
           6.569797e-15            3.231941e-15           -1.122416e-15            5.322143e-16 
      gamma_residence_c gamma_acknowledgement_c          gamma_income_c       gamma_education_c 
           5.577681e-16            3.139308e-16            4.416787e-15           -1.261111e-15 
      gamma_frequency_c 
           1.323978e-15 
initial  value 7122.440877 
iter   2 value 7106.935795
iter   3 value 7076.713589
iter   4 value 6950.666054
iter   5 value 6680.767105
iter   6 value 6116.311162
iter   7 value 6020.032647
iter   8 value 5983.822518
iter   9 value 5941.313710
iter  10 value 5937.608466
iter  11 value 5739.592568
iter  12 value 5438.059900
iter  13 value 5366.295055
iter  14 value 5328.173248
iter  15 value 5275.438537
iter  16 value 5256.285425
iter  17 value 5248.275035
iter  18 value 5232.980727
iter  19 value 5226.615120
iter  20 value 5224.322760
iter  21 value 5221.086711
iter  22 value 5215.467103
iter  23 value 5209.461951
iter  24 value 5205.891635
iter  25 value 5200.870198
iter  26 value 5154.431023
iter  27 value 5133.956294
iter  28 value 5087.848414
iter  29 value 5078.041745
iter  30 value 5063.787535
iter  31 value 5060.302405
iter  32 value 5044.503168
iter  33 value 5019.341600
iter  34 value 5000.768990
iter  35 value 4982.695607
iter  36 value 4940.215238
iter  37 value 4919.038270
iter  38 value 4886.915374
iter  39 value 4871.654753
iter  40 value 4871.585141
iter  41 value 4867.664140
iter  42 value 4851.295203
iter  43 value 4812.119641
iter  44 value 4734.643192
iter  45 value 4686.065527
iter  46 value 4672.248552
iter  47 value 4650.609257
iter  48 value 4595.096150
iter  49 value 4576.798344
iter  50 value 4547.450106
iter  51 value 4524.365664
iter  52 value 4512.196570
iter  53 value 4505.862664
iter  54 value 4501.654166
iter  55 value 4497.847761
iter  56 value 4489.517255
iter  57 value 4477.795177
iter  58 value 4471.490308
iter  59 value 4467.504148
iter  60 value 4462.607279
iter  61 value 4453.234026
iter  62 value 4449.711402
iter  63 value 4448.566537
iter  64 value 4448.040002
iter  65 value 4445.105278
iter  66 value 4441.207599
iter  67 value 4437.380834
iter  68 value 4431.919690
iter  69 value 4427.854384
iter  70 value 4425.663439
iter  71 value 4422.671344
iter  72 value 4420.502098
iter  73 value 4418.305352
iter  74 value 4414.806071
iter  75 value 4411.523412
iter  76 value 4407.676871
iter  77 value 4406.560814
iter  78 value 4404.102662
iter  79 value 4401.612148
iter  80 value 4399.718171
iter  81 value 4396.623146
iter  82 value 4394.714258
iter  83 value 4391.178742
iter  84 value 4389.038885
iter  85 value 4388.469755
iter  86 value 4385.548038
iter  87 value 4382.065975
iter  88 value 4379.577005
iter  89 value 4377.353393
iter  90 value 4375.549760
iter  91 value 4373.837606
iter  92 value 4373.772929
iter  93 value 4372.177473
iter  94 value 4371.174890
iter  95 value 4366.010903
iter  96 value 4363.670437
iter  97 value 4361.433989
iter  98 value 4360.893068
iter  99 value 4359.580893
iter 100 value 4359.191702
iter 101 value 4358.669140
iter 102 value 4357.062050
iter 103 value 4356.777657
iter 104 value 4355.581560
iter 105 value 4355.332810
iter 106 value 4354.286130
iter 107 value 4353.508846
iter 108 value 4352.052877
iter 109 value 4351.273393
iter 110 value 4350.815890
iter 111 value 4350.575105
iter 112 value 4350.129842
iter 113 value 4349.832376
iter 114 value 4349.610029
iter 115 value 4349.339092
iter 116 value 4349.089084
iter 117 value 4348.741893
iter 118 value 4348.537168
iter 119 value 4348.251230
iter 120 value 4347.940522
iter 121 value 4347.856036
iter 122 value 4347.704650
iter 123 value 4347.543435
iter 124 value 4347.460491
iter 125 value 4347.398460
iter 126 value 4347.338854
iter 127 value 4347.287185
iter 128 value 4347.192990
iter 129 value 4347.095344
iter 130 value 4346.991542
iter 131 value 4346.901107
iter 132 value 4346.806431
iter 133 value 4346.726085
iter 134 value 4346.614974
iter 135 value 4346.501060
iter 136 value 4346.394930
iter 137 value 4346.314916
iter 138 value 4346.236819
iter 139 value 4346.114147
iter 140 value 4345.975456
iter 141 value 4345.831264
iter 142 value 4345.635596
iter 143 value 4345.268287
iter 144 value 4345.130723
iter 145 value 4344.634279
iter 146 value 4344.415680
iter 147 value 4344.202212
iter 148 value 4344.079827
iter 149 value 4343.911790
iter 150 value 4343.761266
iter 151 value 4343.629468
iter 152 value 4343.527654
iter 153 value 4343.462780
iter 154 value 4343.401560
iter 155 value 4343.371789
iter 156 value 4343.339269
iter 157 value 4343.311234
iter 158 value 4343.282274
iter 159 value 4343.255765
iter 160 value 4343.231819
iter 161 value 4343.202672
iter 162 value 4343.202605
iter 163 value 4343.172270
iter 164 value 4343.152393
iter 165 value 4343.129527
iter 166 value 4343.096619
iter 167 value 4343.084333
iter 168 value 4343.061116
iter 169 value 4343.060498
iter 170 value 4343.060286
iter 171 value 4343.058885
iter 172 value 4343.056590
iter 173 value 4343.042421
iter 174 value 4343.031912
iter 175 value 4343.026645
iter 176 value 4343.020579
iter 177 value 4343.012079
iter 178 value 4342.998448
iter 179 value 4342.986554
iter 180 value 4342.977175
iter 181 value 4342.963834
iter 182 value 4342.957631
iter 183 value 4342.956584
iter 184 value 4342.954056
iter 185 value 4342.949269
iter 186 value 4342.934681
iter 187 value 4342.919805
iter 188 value 4342.916052
iter 189 value 4342.905828
iter 190 value 4342.904629
iter 191 value 4342.896891
iter 192 value 4342.889512
iter 193 value 4342.880329
iter 194 value 4342.858660
iter 195 value 4342.836226
iter 196 value 4342.835004
iter 197 value 4342.826300
iter 198 value 4342.808204
iter 199 value 4342.794730
iter 200 value 4342.770903
final  value 4342.770903 
stopped after 200 iterations
Estimated parameters:
                           Estimate
asc                      -11.061294
sigma_asc                 -8.222560
beta_area_a               -0.030066
sigma_area_a              -0.081775
beta_area_b               11.506343
sigma_area_b              13.804198
beta_area_c                1.662038
sigma_area_c              -1.335112
beta_area_d               -0.655261
sigma_area_d              13.617864
beta_fish_a                0.003697
sigma_fish_a               0.005112
beta_fish_b                0.315508
sigma_fish_b              -0.661881
beta_fish_c               -0.015327
sigma_fish_c               0.005024
beta_fish_d               -0.525983
sigma_fish_d               0.637828
beta_CO2_a                 0.002085
sigma_CO2_a                0.004362
beta_CO2_b                -0.062888
sigma_CO2_b                0.238467
beta_CO2_c                 0.015945
sigma_CO2_c               -0.005619
beta_CO2_d                 0.031832
sigma_CO2_d                0.230344
beta_typhoon_a             0.159376
sigma_typhoon_a            0.143595
beta_typhoon_b            -3.810390
sigma_typhoon_b            3.416624
beta_typhoon_c             0.603164
sigma_typhoon_c           -0.631694
beta_typhoon_d             9.746217
sigma_typhoon_d           -7.538491
beta_Aes_a                 0.141236
sigma_Aes_a               -0.548785
beta_Aes_b                10.184351
sigma_Aes_b               -0.721753
beta_Aes_c                -0.068672
sigma_Aes_c               -0.007413
beta_Aes_d               -20.613460
sigma_Aes_d               22.508271
beta_mosquito_a           -0.388458
sigma_mosquito_a           0.658468
beta_mosquito_b            4.057403
sigma_mosquito_b           6.253682
beta_mosquito_c           -0.001292
sigma_mosquito_c          -0.084935
beta_mosquito_d           -5.520252
sigma_mosquito_d          -6.277541
beta_log_Cost_a           -4.691008
sigma_log_Cost_a           1.522479
beta_log_Cost_b          -28.236226
sigma_log_Cost_b           0.220997
beta_log_Cost_c          -18.844314
sigma_log_Cost_c           1.736280
beta_log_Cost_d           -3.842124
sigma_log_Cost_d           3.696279
delta_a_mu                 5.927363
delta_a_sig               -5.175481
gamma_residence_a         -2.443949
gamma_income_a             0.066645
gamma_acknowledgement_a   -1.739873
gamma_frequency_a         -1.313066
gamma_education_a          2.792816
delta_b                  -18.569702
gamma_residence_b          0.070208
gamma_acknowledgement_b   -0.306767
gamma_income_b             2.205548
gamma_frequency_b          2.657856
gamma_education_b         -1.864127
delta_c                    3.235958
gamma_residence_c         -1.827196
gamma_acknowledgement_c   -1.089652
gamma_income_c             0.494773
gamma_education_c          1.236508
gamma_frequency_c         -1.017687
delta_d                    0.000000
gamma_residence_d          0.000000
gamma_acknowledgement_d    0.000000
gamma_income_d             0.000000
gamma_education_d          0.000000
gamma_frequency_d          0.000000

#####################################################################################################################
Estimation failed. No covariance matrix to compute.
#####################################################################################################################

Summary of class allocation for LC model component :
         Mean prob.
Class_1     0.77594
Class_2     0.03955
Class_3     0.16864
Class_4     0.01587

Calculating LL(0) for applicable models...
Calculating LL(c) for applicable models...
Calculating LL of each model component...

Results:

Code: Select all

Model name                       : mangrove restoration CE
Model description                : Latent Class method on mangrove restoration CE data
Model run at                     : 2022-03-14 09:21:16
Estimation method                : bfgs
Model diagnosis                  : iteration limit exceeded 
Number of individuals            : 1029
Number of rows in database       : 6174
Number of modelled outcomes      : 6174

Number of cores used             :  6 
Number of inter-individual draws : 500 (halton)

LL(start)                        : -7122.44
LL(0, whole model)               : -6782.83
LL(C, whole model)               : -5900.89
LL(final, whole model)           : -4342.77
Rho-square (0)                   :  0.3597 
Adj.Rho-square (0)               :  0.3484 
Rho-square (C)                   :  0.264 
Adj.Rho-square (C)               :  0.251 
AIC                              :  8839.54 
BIC                              :  9357.61 

LL(0,Class_1)                    : -6782.83
LL(final,Class_1)                : -4716.53
LL(0,Class_2)                    : -6782.83
LL(final,Class_2)                : -18529.36
LL(0,Class_3)                    : -6782.83
LL(final,Class_3)                : -6451.04
LL(0,Class_4)                    : -6782.83
LL(final,Class_4)                : -17485.42

Estimated parameters             :  77
Time taken (hh:mm:ss)            :  01:53:6.08 
     pre-estimation              :  00:13:23.85 
     estimation                  :  01:39:31.21 
     post-estimation             :  00:00:11.02 
Iterations                       :  201 (iteration limit exceeded ) 

Unconstrained optimisation.

Estimates:
                           Estimate        s.e.   t.rat.(0)  p(1-sided)    Rob.s.e. Rob.t.rat.(0)  p(1-sided)
asc                      -11.061294          NA          NA          NA          NA            NA          NA
sigma_asc                 -8.222560          NA          NA          NA          NA            NA          NA
beta_area_a               -0.030066          NA          NA          NA          NA            NA          NA
sigma_area_a              -0.081775          NA          NA          NA          NA            NA          NA
beta_area_b               11.506343          NA          NA          NA          NA            NA          NA
sigma_area_b              13.804198          NA          NA          NA          NA            NA          NA
beta_area_c                1.662038          NA          NA          NA          NA            NA          NA
sigma_area_c              -1.335112          NA          NA          NA          NA            NA          NA
beta_area_d               -0.655261          NA          NA          NA          NA            NA          NA
sigma_area_d              13.617864          NA          NA          NA          NA            NA          NA
beta_fish_a                0.003697          NA          NA          NA          NA            NA          NA
sigma_fish_a               0.005112          NA          NA          NA          NA            NA          NA
beta_fish_b                0.315508          NA          NA          NA          NA            NA          NA
sigma_fish_b              -0.661881          NA          NA          NA          NA            NA          NA
beta_fish_c               -0.015327          NA          NA          NA          NA            NA          NA
sigma_fish_c               0.005024          NA          NA          NA          NA            NA          NA
beta_fish_d               -0.525983          NA          NA          NA          NA            NA          NA
sigma_fish_d               0.637828          NA          NA          NA          NA            NA          NA
beta_CO2_a                 0.002085          NA          NA          NA          NA            NA          NA
sigma_CO2_a                0.004362          NA          NA          NA          NA            NA          NA
beta_CO2_b                -0.062888          NA          NA          NA          NA            NA          NA
sigma_CO2_b                0.238467          NA          NA          NA          NA            NA          NA
beta_CO2_c                 0.015945          NA          NA          NA          NA            NA          NA
sigma_CO2_c               -0.005619          NA          NA          NA          NA            NA          NA
beta_CO2_d                 0.031832          NA          NA          NA          NA            NA          NA
sigma_CO2_d                0.230344          NA          NA          NA          NA            NA          NA
beta_typhoon_a             0.159376          NA          NA          NA          NA            NA          NA
sigma_typhoon_a            0.143595          NA          NA          NA          NA            NA          NA
beta_typhoon_b            -3.810390          NA          NA          NA          NA            NA          NA
sigma_typhoon_b            3.416624          NA          NA          NA          NA            NA          NA
beta_typhoon_c             0.603164          NA          NA          NA          NA            NA          NA
sigma_typhoon_c           -0.631694          NA          NA          NA          NA            NA          NA
beta_typhoon_d             9.746217          NA          NA          NA          NA            NA          NA
sigma_typhoon_d           -7.538491          NA          NA          NA          NA            NA          NA
beta_Aes_a                 0.141236          NA          NA          NA          NA            NA          NA
sigma_Aes_a               -0.548785          NA          NA          NA          NA            NA          NA
beta_Aes_b                10.184351          NA          NA          NA          NA            NA          NA
sigma_Aes_b               -0.721753          NA          NA          NA          NA            NA          NA
beta_Aes_c                -0.068672          NA          NA          NA          NA            NA          NA
sigma_Aes_c               -0.007413          NA          NA          NA          NA            NA          NA
beta_Aes_d               -20.613460          NA          NA          NA          NA            NA          NA
sigma_Aes_d               22.508271          NA          NA          NA          NA            NA          NA
beta_mosquito_a           -0.388458          NA          NA          NA          NA            NA          NA
sigma_mosquito_a           0.658468          NA          NA          NA          NA            NA          NA
beta_mosquito_b            4.057403          NA          NA          NA          NA            NA          NA
sigma_mosquito_b           6.253682          NA          NA          NA          NA            NA          NA
beta_mosquito_c           -0.001292          NA          NA          NA          NA            NA          NA
sigma_mosquito_c          -0.084935          NA          NA          NA          NA            NA          NA
beta_mosquito_d           -5.520252          NA          NA          NA          NA            NA          NA
sigma_mosquito_d          -6.277541          NA          NA          NA          NA            NA          NA
beta_log_Cost_a           -4.691008          NA          NA          NA          NA            NA          NA
sigma_log_Cost_a           1.522479          NA          NA          NA          NA            NA          NA
beta_log_Cost_b          -28.236226          NA          NA          NA          NA            NA          NA
sigma_log_Cost_b           0.220997          NA          NA          NA          NA            NA          NA
beta_log_Cost_c          -18.844314          NA          NA          NA          NA            NA          NA
sigma_log_Cost_c           1.736280          NA          NA          NA          NA            NA          NA
beta_log_Cost_d           -3.842124          NA          NA          NA          NA            NA          NA
sigma_log_Cost_d           3.696279          NA          NA          NA          NA            NA          NA
delta_a_mu                 5.927363          NA          NA          NA          NA            NA          NA
delta_a_sig               -5.175481          NA          NA          NA          NA            NA          NA
gamma_residence_a         -2.443949          NA          NA          NA          NA            NA          NA
gamma_income_a             0.066645          NA          NA          NA          NA            NA          NA
gamma_acknowledgement_a   -1.739873          NA          NA          NA          NA            NA          NA
gamma_frequency_a         -1.313066          NA          NA          NA          NA            NA          NA
gamma_education_a          2.792816          NA          NA          NA          NA            NA          NA
delta_b                  -18.569702          NA          NA          NA          NA            NA          NA
gamma_residence_b          0.070208          NA          NA          NA          NA            NA          NA
gamma_acknowledgement_b   -0.306767          NA          NA          NA          NA            NA          NA
gamma_income_b             2.205548          NA          NA          NA          NA            NA          NA
gamma_frequency_b          2.657856          NA          NA          NA          NA            NA          NA
gamma_education_b         -1.864127          NA          NA          NA          NA            NA          NA
delta_c                    3.235958          NA          NA          NA          NA            NA          NA
gamma_residence_c         -1.827196          NA          NA          NA          NA            NA          NA
gamma_acknowledgement_c   -1.089652          NA          NA          NA          NA            NA          NA
gamma_income_c             0.494773          NA          NA          NA          NA            NA          NA
gamma_education_c          1.236508          NA          NA          NA          NA            NA          NA
gamma_frequency_c         -1.017687          NA          NA          NA          NA            NA          NA
delta_d                    0.000000          NA          NA          NA          NA            NA          NA
gamma_residence_d          0.000000          NA          NA          NA          NA            NA          NA
gamma_acknowledgement_d    0.000000          NA          NA          NA          NA            NA          NA
gamma_income_d             0.000000          NA          NA          NA          NA            NA          NA
gamma_education_d          0.000000          NA          NA          NA          NA            NA          NA
gamma_frequency_d          0.000000          NA          NA          NA          NA            NA          NA


Summary of class allocation for LC model component :
         Mean prob.
Class_1     0.77594
Class_2     0.03955
Class_3     0.16864
Class_4     0.01587
stephanehess
Site Admin
Posts: 974
Joined: 24 Apr 2020, 16:29

Re: Latent class fail with "No covariance matrix to compute"

Post by stephanehess »

Hi

please see the output. Your model has not converged - iteration limit exceeded

Also, you should not use Halton draws with that many random parameters.

Please also consider updating to a recent version of Apollo in case yours is not 0.2.7

Stephane
--------------------------------
Stephane Hess
www.stephanehess.me.uk
JoeSu
Posts: 4
Joined: 10 Mar 2022, 00:18

Re: Latent class fail with "No covariance matrix to compute"

Post by JoeSu »

Dear Stephane,

Thank you a lot for your prompt reply and for pointing out the issues.

I am sure that I am using the 0.2.7 version of Apollo. I have changed the type of draws and extent the iteration to 300. Hope they could work.

Many thanks again,
Joe
Post Reply