LVM Short Course - Day 1 Examples

Rich Jones, Doug Tommet

July 9, 2022

Longitudinal Data Analysis in R

These slide recreate the examples using:

Setting up the R environment

These are the packages used by R for these examples

library(readr)
library(dplyr)
library(tidyr)
library(ggplot2)
library(RColorBrewer)
library(lme4)
library(lavaan)
library(MplusAutomation)
library(gtsummary)

Getting the EPESE data

address <- "https://lvmworkshop.s3.amazonaws.com/LDA/ex0101.dat"

epese <- read_csv(address, 
                  col_names=c("sad", "blues", "depress", "happy", 
                              "enjoy", "hopeful", "age", "male")) 

epese <- epese %>% 
  mutate(age_high = as.numeric(age > mean(age, na.rm=TRUE)))

Summarizing the data

gtsummary::tbl_summary(epese)
Characteristic N = 2,4421
sad
0 1,606 (66%)
1 656 (27%)
2 87 (3.6%)
3 93 (3.8%)
blues
0 1,906 (78%)
1 355 (15%)
2 75 (3.1%)
3 106 (4.3%)
depress
0 1,573 (64%)
1 635 (26%)
2 92 (3.8%)
3 142 (5.8%)
happy
0 1,638 (67%)
1 247 (10%)
2 380 (16%)
3 177 (7.2%)
enjoy
0 1,855 (76%)
1 184 (7.5%)
2 258 (11%)
3 145 (5.9%)
hopeful
0 1,409 (58%)
1 169 (6.9%)
2 386 (16%)
3 478 (20%)
age
67 696 (29%)
72 702 (29%)
77 466 (19%)
82 373 (15%)
87 205 (8.4%)
male 1,036 (42%)
age_high 1,044 (43%)

1 n (%)

CFA, Example 0101 - lavaan (input)

ex0101mod <- 'f =~ sad + blues + depress + happy + enjoy + hopeful '
ex0101fit <- lavaan::sem(ex0101mod, data = epese, estimator = "ML")

CFA, Example 0101 - lavaan (output)

summary(ex0101fit, fit.measures = TRUE, standardized=TRUE)
## lavaan 0.6-12 ended normally after 26 iterations
## 
##   Estimator                                         ML
##   Optimization method                           NLMINB
##   Number of model parameters                        12
## 
##   Number of observations                          2442
## 
## Model Test User Model:
##                                                       
##   Test statistic                               483.785
##   Degrees of freedom                                 9
##   P-value (Chi-square)                           0.000
## 
## Model Test Baseline Model:
## 
##   Test statistic                              4064.686
##   Degrees of freedom                                15
##   P-value                                        0.000
## 
## User Model versus Baseline Model:
## 
##   Comparative Fit Index (CFI)                    0.883
##   Tucker-Lewis Index (TLI)                       0.805
## 
## Loglikelihood and Information Criteria:
## 
##   Loglikelihood user model (H0)             -17278.438
##   Loglikelihood unrestricted model (H1)     -17036.545
##                                                       
##   Akaike (AIC)                               34580.876
##   Bayesian (BIC)                             34650.483
##   Sample-size adjusted Bayesian (BIC)        34612.356
## 
## Root Mean Square Error of Approximation:
## 
##   RMSEA                                          0.147
##   90 Percent confidence interval - lower         0.136
##   90 Percent confidence interval - upper         0.158
##   P-value RMSEA <= 0.05                          0.000
## 
## Standardized Root Mean Square Residual:
## 
##   SRMR                                           0.065
## 
## Parameter Estimates:
## 
##   Standard errors                             Standard
##   Information                                 Expected
##   Information saturated (h1) model          Structured
## 
## Latent Variables:
##                    Estimate  Std.Err  z-value  P(>|z|)   Std.lv  Std.all
##   f =~                                                                  
##     sad               1.000                               0.510    0.689
##     blues             0.963    0.035   27.318    0.000    0.491    0.665
##     depress           1.193    0.040   29.522    0.000    0.608    0.741
##     happy             1.230    0.047   26.269    0.000    0.627    0.634
##     enjoy             1.075    0.042   25.308    0.000    0.548    0.606
##     hopeful           0.883    0.056   15.913    0.000    0.450    0.366
## 
## Variances:
##                    Estimate  Std.Err  z-value  P(>|z|)   Std.lv  Std.all
##    .sad               0.288    0.010   27.415    0.000    0.288    0.526
##    .blues             0.304    0.011   28.353    0.000    0.304    0.558
##    .depress           0.304    0.012   24.797    0.000    0.304    0.451
##    .happy             0.586    0.020   29.385    0.000    0.586    0.598
##    .enjoy             0.516    0.017   30.144    0.000    0.516    0.632
##    .hopeful           1.315    0.039   33.688    0.000    1.315    0.866
##     f                 0.260    0.015   17.510    0.000    1.000    1.000

CFA, Example 0101 - MplusAutomation (input)

ex0101mod.mplus <-  MplusAutomation::mplusObject(
    MODEL = "f by sad-hopeful; ",
    OUTPUT = "STDYX; tech1",
    usevariables = c("sad", "blues", "depress", "happy", "enjoy", "hopeful"),
    rdata = epese
  )
ex0101fit.mplus <- MplusAutomation::mplusModeler(ex0101mod.mplus,
                          dataout = "ex0101.dat",
                          modelout = "ex0101.inp",
                          run = TRUE) 
## 
## Running model: ex0101.inp 
## System command: cd "/Users/douglastommet/Dropbox/work/ShortCourse/POSTED/SLIDES/LDA/lavaan" && "/Applications/Mplus/mplus" "ex0101.inp" 
## Reading model:  ex0101.out
file.remove("ex0101.inp")
## [1] TRUE

CFA, Example 0101 - MplusAutomation (output)

# readModels("ex0101.out")
MplusAutomation::readModels("ex0101.out", what="summaries")
## Reading model:  ex0101.out
## Estimated using ML 
## Number of obs: 2442, number of (free) parameters: 18 
## 
## Model: Chi2(df = 9) = 483.785, p = 0 
## Baseline model: Chi2(df = 15) = 4064.686, p = 0 
## 
## Fit Indices: 
## 
## CFI = 0.883, TLI = 0.805, SRMR = 0.057 
## RMSEA = 0.147, 90% CI [0.136, 0.158], p < .05 = 0 
## AIC = 34592.876, BIC = 34697.286 
## NULL
MplusAutomation::readModels("ex0101.out")[["parameters"]][["unstandardized"]]
## Reading model:  ex0101.out
##           paramHeader   param   est    se  est_se pval
## 1                F.BY     SAD 1.000 0.000 999.000  999
## 2                F.BY   BLUES 0.963 0.035  27.751    0
## 3                F.BY DEPRESS 1.193 0.040  30.075    0
## 4                F.BY   HAPPY 1.230 0.049  24.975    0
## 5                F.BY   ENJOY 1.075 0.045  23.950    0
## 6                F.BY HOPEFUL 0.883 0.057  15.489    0
## 7          Intercepts     SAD 0.454 0.015  30.325    0
## 8          Intercepts   BLUES 0.337 0.015  22.553    0
## 9          Intercepts DEPRESS 0.510 0.017  30.685    0
## 10         Intercepts   HAPPY 0.630 0.020  31.451    0
## 11         Intercepts   ENJOY 0.465 0.018  25.421    0
## 12         Intercepts HOPEFUL 0.973 0.025  39.018    0
## 13          Variances       F 0.260 0.015  17.461    0
## 14 Residual.Variances     SAD 0.288 0.011  27.263    0
## 15 Residual.Variances   BLUES 0.304 0.011  27.677    0
## 16 Residual.Variances DEPRESS 0.304 0.013  23.883    0
## 17 Residual.Variances   HAPPY 0.586 0.021  27.902    0
## 18 Residual.Variances   ENJOY 0.516 0.018  28.700    0
## 19 Residual.Variances HOPEFUL 1.315 0.039  33.536    0
MplusAutomation::readModels("ex0101.out")[["tech1"]]
## Reading model:  ex0101.out
## $parameterSpecification
## $nu
##   SAD BLUES DEPRESS HAPPY ENJOY HOPEFUL
## 1   1     2       3     4     5       6
## 
## $lambda
##          F
## SAD      0
## BLUES    7
## DEPRESS  8
## HAPPY    9
## ENJOY   10
## HOPEFUL 11
## 
## $theta
##         SAD BLUES DEPRESS HAPPY ENJOY HOPEFUL
## SAD      12    NA      NA    NA    NA      NA
## BLUES     0    13      NA    NA    NA      NA
## DEPRESS   0     0      14    NA    NA      NA
## HAPPY     0     0       0    15    NA      NA
## ENJOY     0     0       0     0    16      NA
## HOPEFUL   0     0       0     0     0      17
## 
## $alpha
##   F
## 1 0
## 
## $beta
##   F
## F 0
## 
## $psi
##    F
## F 18
## 
## attr(,"class")
## [1] "mplus.parameterSpecification" "list"                        
## 
## $startingValues
## $nu
##     SAD BLUES DEPRESS HAPPY ENJOY HOPEFUL
## 1 0.454 0.337    0.51  0.63 0.465   0.973
## 
## $lambda
##             F
## SAD     1.000
## BLUES   0.991
## DEPRESS 1.218
## HAPPY   1.176
## ENJOY   1.031
## HOPEFUL 0.847
## 
## $theta
##           SAD BLUES DEPRESS HAPPY ENJOY HOPEFUL
## SAD     0.274    NA      NA    NA    NA      NA
## BLUES   0.000 0.273      NA    NA    NA      NA
## DEPRESS 0.000 0.000   0.337    NA    NA      NA
## HAPPY   0.000 0.000   0.000  0.49    NA      NA
## ENJOY   0.000 0.000   0.000  0.00 0.408      NA
## HOPEFUL 0.000 0.000   0.000  0.00 0.000   0.759
## 
## $alpha
##   F
## 1 0
## 
## $beta
##   F
## F 0
## 
## $psi
##      F
## F 0.05
## 
## attr(,"class")
## [1] "mplus.startingValues" "list"                
## 
## attr(,"class")
## [1] "mplus.tech1" "list"

CFA & Covariates, Example 0102 - lavaan (input)

ex0102mod <- 'f =~ sad + sad + blues + depress + happy + enjoy + hopeful
              f ~ age + male
              '
ex0102fit <- lavaan::sem(ex0102mod,data=epese, estimator = "ML",  meanstructure = TRUE)

CFA & Covariates, Example 0102 - lavaan (output)

summary(ex0102fit, fit.measures = TRUE, standardized=TRUE)
## lavaan 0.6-12 ended normally after 43 iterations
## 
##   Estimator                                         ML
##   Optimization method                           NLMINB
##   Number of model parameters                        20
## 
##   Number of observations                          2442
## 
## Model Test User Model:
##                                                       
##   Test statistic                               496.985
##   Degrees of freedom                                19
##   P-value (Chi-square)                           0.000
## 
## Model Test Baseline Model:
## 
##   Test statistic                              4124.409
##   Degrees of freedom                                27
##   P-value                                        0.000
## 
## User Model versus Baseline Model:
## 
##   Comparative Fit Index (CFI)                    0.883
##   Tucker-Lewis Index (TLI)                       0.834
## 
## Loglikelihood and Information Criteria:
## 
##   Loglikelihood user model (H0)             -17255.177
##   Loglikelihood unrestricted model (H1)     -17006.684
##                                                       
##   Akaike (AIC)                               34550.354
##   Bayesian (BIC)                             34666.365
##   Sample-size adjusted Bayesian (BIC)        34602.820
## 
## Root Mean Square Error of Approximation:
## 
##   RMSEA                                          0.101
##   90 Percent confidence interval - lower         0.094
##   90 Percent confidence interval - upper         0.109
##   P-value RMSEA <= 0.05                          0.000
## 
## Standardized Root Mean Square Residual:
## 
##   SRMR                                           0.045
## 
## Parameter Estimates:
## 
##   Standard errors                             Standard
##   Information                                 Expected
##   Information saturated (h1) model          Structured
## 
## Latent Variables:
##                    Estimate  Std.Err  z-value  P(>|z|)   Std.lv  Std.all
##   f =~                                                                  
##     sad               1.000                               0.510    0.689
##     blues             0.963    0.035   27.356    0.000    0.491    0.665
##     depress           1.190    0.040   29.547    0.000    0.607    0.739
##     happy             1.231    0.047   26.325    0.000    0.628    0.634
##     enjoy             1.075    0.042   25.359    0.000    0.548    0.607
##     hopeful           0.884    0.055   15.942    0.000    0.451    0.366
## 
## Regressions:
##                    Estimate  Std.Err  z-value  P(>|z|)   Std.lv  Std.all
##   f ~                                                                   
##     age               0.006    0.002    3.233    0.001    0.011    0.072
##     male             -0.134    0.023   -5.784    0.000   -0.263   -0.130
## 
## Intercepts:
##                    Estimate  Std.Err  z-value  P(>|z|)   Std.lv  Std.all
##    .sad               0.082    0.134    0.608    0.543    0.082    0.111
##    .blues            -0.021    0.130   -0.166    0.868   -0.021   -0.029
##    .depress           0.067    0.160    0.417    0.677    0.067    0.081
##    .happy             0.172    0.166    1.035    0.301    0.172    0.173
##    .enjoy             0.064    0.145    0.445    0.656    0.064    0.071
##    .hopeful           0.643    0.122    5.279    0.000    0.643    0.522
##    .f                 0.000                               0.000    0.000
## 
## Variances:
##                    Estimate  Std.Err  z-value  P(>|z|)   Std.lv  Std.all
##    .sad               0.288    0.010   27.441    0.000    0.288    0.525
##    .blues             0.304    0.011   28.390    0.000    0.304    0.558
##    .depress           0.306    0.012   24.928    0.000    0.306    0.453
##    .happy             0.585    0.020   29.396    0.000    0.585    0.598
##    .enjoy             0.516    0.017   30.155    0.000    0.516    0.632
##    .hopeful           1.314    0.039   33.691    0.000    1.314    0.866
##    .f                 0.254    0.015   17.503    0.000    0.977    0.977

CFA & Covariates, Example 0102 - MplusAutomation (input)

ex0102mod.mplus <-  MplusAutomation::mplusObject(
    MODEL = "f by sad-hopeful; 
            f on age male ;",
    OUTPUT = "STDYX; tech1;",
    usevariables = c("sad", "blues", "depress", "happy", 
                     "enjoy", "hopeful", "age", "male"),
    rdata = epese
  )
ex0102fit.mplus <- MplusAutomation::mplusModeler(ex0102mod.mplus,
                          dataout = "ex0102.dat",
                          modelout = "ex0102.inp",
                          run = TRUE) 
## 
## Running model: ex0102.inp 
## System command: cd "/Users/douglastommet/Dropbox/work/ShortCourse/POSTED/SLIDES/LDA/lavaan" && "/Applications/Mplus/mplus" "ex0102.inp" 
## Reading model:  ex0102.out
file.remove("ex0102.inp")
## [1] TRUE

CFA & Covariates, Example 0102 - MplusAutomation (output)

# readModels("ex0102.out")
MplusAutomation::readModels("ex0102.out", what="summaries")
## Reading model:  ex0102.out
## Estimated using ML 
## Number of obs: 2442, number of (free) parameters: 20 
## 
## Model: Chi2(df = 19) = 496.985, p = 0 
## Baseline model: Chi2(df = 27) = 4124.409, p = 0 
## 
## Fit Indices: 
## 
## CFI = 0.883, TLI = 0.834, SRMR = 0.048 
## RMSEA = 0.101, 90% CI [0.094, 0.109], p < .05 = 0 
## AIC = 34550.354, BIC = 34666.365 
## NULL
MplusAutomation::readModels("ex0102.out")[["parameters"]][["unstandardized"]]
## Reading model:  ex0102.out
##           paramHeader   param    est    se  est_se    pval
## 1                F.BY     SAD  1.000 0.000 999.000 999.000
## 2                F.BY   BLUES  0.963 0.035  27.784   0.000
## 3                F.BY DEPRESS  1.190 0.040  30.104   0.000
## 4                F.BY   HAPPY  1.231 0.049  25.035   0.000
## 5                F.BY   ENJOY  1.075 0.045  24.007   0.000
## 6                F.BY HOPEFUL  0.884 0.057  15.517   0.000
## 7                F.ON     AGE  0.006 0.002   3.234   0.001
## 8                F.ON    MALE -0.134 0.023  -5.778   0.000
## 9          Intercepts     SAD  0.082 0.134   0.608   0.543
## 10         Intercepts   BLUES -0.021 0.130  -0.165   0.869
## 11         Intercepts DEPRESS  0.067 0.160   0.417   0.677
## 12         Intercepts   HAPPY  0.172 0.166   1.034   0.301
## 13         Intercepts   ENJOY  0.065 0.145   0.445   0.657
## 14         Intercepts HOPEFUL  0.643 0.122   5.265   0.000
## 15 Residual.Variances     SAD  0.288 0.011  27.278   0.000
## 16 Residual.Variances   BLUES  0.304 0.011  27.713   0.000
## 17 Residual.Variances DEPRESS  0.306 0.013  24.034   0.000
## 18 Residual.Variances   HAPPY  0.585 0.021  27.942   0.000
## 19 Residual.Variances   ENJOY  0.516 0.018  28.740   0.000
## 20 Residual.Variances HOPEFUL  1.314 0.039  33.541   0.000
## 21 Residual.Variances       F  0.254 0.015  17.456   0.000
MplusAutomation::readModels("ex0102.out")[["tech1"]]
## Reading model:  ex0102.out
## $parameterSpecification
## $nu
##   SAD BLUES DEPRESS HAPPY ENJOY HOPEFUL AGE MALE
## 1   1     2       3     4     5       6   0    0
## 
## $lambda
##          F AGE MALE
## SAD      0   0    0
## BLUES    7   0    0
## DEPRESS  8   0    0
## HAPPY    9   0    0
## ENJOY   10   0    0
## HOPEFUL 11   0    0
## AGE      0   0    0
## MALE     0   0    0
## 
## $theta
##         SAD BLUES DEPRESS HAPPY ENJOY HOPEFUL AGE MALE
## SAD      12    NA      NA    NA    NA      NA  NA   NA
## BLUES     0    13      NA    NA    NA      NA  NA   NA
## DEPRESS   0     0      14    NA    NA      NA  NA   NA
## HAPPY     0     0       0    15    NA      NA  NA   NA
## ENJOY     0     0       0     0    16      NA  NA   NA
## HOPEFUL   0     0       0     0     0      17  NA   NA
## AGE       0     0       0     0     0       0   0   NA
## MALE      0     0       0     0     0       0   0    0
## 
## $alpha
##   F AGE MALE
## 1 0   0    0
## 
## $beta
##      F AGE MALE
## F    0  18   19
## AGE  0   0    0
## MALE 0   0    0
## 
## $psi
##       F AGE MALE
## F    20  NA   NA
## AGE   0   0   NA
## MALE  0   0    0
## 
## attr(,"class")
## [1] "mplus.parameterSpecification" "list"                        
## 
## $startingValues
## $nu
##     SAD BLUES DEPRESS HAPPY ENJOY HOPEFUL AGE MALE
## 1 0.454 0.337    0.51  0.63 0.465   0.973   0    0
## 
## $lambda
##             F AGE MALE
## SAD     1.000   0    0
## BLUES   0.991   0    0
## DEPRESS 1.218   0    0
## HAPPY   1.176   0    0
## ENJOY   1.031   0    0
## HOPEFUL 0.847   0    0
## AGE     0.000   1    0
## MALE    0.000   0    1
## 
## $theta
##           SAD BLUES DEPRESS HAPPY ENJOY HOPEFUL AGE MALE
## SAD     0.274    NA      NA    NA    NA      NA  NA   NA
## BLUES   0.000 0.273      NA    NA    NA      NA  NA   NA
## DEPRESS 0.000 0.000   0.337    NA    NA      NA  NA   NA
## HAPPY   0.000 0.000   0.000  0.49    NA      NA  NA   NA
## ENJOY   0.000 0.000   0.000  0.00 0.408      NA  NA   NA
## HOPEFUL 0.000 0.000   0.000  0.00 0.000   0.759  NA   NA
## AGE     0.000 0.000   0.000  0.00 0.000   0.000   0   NA
## MALE    0.000 0.000   0.000  0.00 0.000   0.000   0    0
## 
## $alpha
##   F    AGE  MALE
## 1 0 74.316 0.424
## 
## $beta
##      F AGE MALE
## F    0   0    0
## AGE  0   0    0
## MALE 0   0    0
## 
## $psi
##         F    AGE  MALE
## F    0.05     NA    NA
## AGE  0.00 40.696    NA
## MALE 0.00 -0.190 0.244
## 
## attr(,"class")
## [1] "mplus.startingValues" "list"                
## 
## attr(,"class")
## [1] "mplus.tech1" "list"

CFA, Covariates, & Direct Effects, Example 0103 - lavaan (input)

ex0103mod <- 'f =~ sad + blues + depress + happy + enjoy + hopeful
              f ~ age + male
              sad ~ 0 * age + 0 * male
              blues ~ 0 * age + 0 * male
              depress ~ 0 * age + 0 * male
              happy ~ 0 * age + 0 * male
              enjoy ~ 0 * age + 0 * male
              hopeful ~ age + 0 * male
              '
ex0103fit <- lavaan::sem(ex0103mod,data=epese, estimator = "ML",  meanstructure = TRUE)

CFA, Covariates, & Direct Effects, Example 0103 - lavaan (output)

summary(ex0103fit, fit.measures=TRUE, standardized=TRUE )
## lavaan 0.6-12 ended normally after 53 iterations
## 
##   Estimator                                         ML
##   Optimization method                           NLMINB
##   Number of model parameters                        21
## 
##   Number of observations                          2442
## 
## Model Test User Model:
##                                                       
##   Test statistic                               490.382
##   Degrees of freedom                                18
##   P-value (Chi-square)                           0.000
## 
## Model Test Baseline Model:
## 
##   Test statistic                              4124.409
##   Degrees of freedom                                27
##   P-value                                        0.000
## 
## User Model versus Baseline Model:
## 
##   Comparative Fit Index (CFI)                    0.885
##   Tucker-Lewis Index (TLI)                       0.827
## 
## Loglikelihood and Information Criteria:
## 
##   Loglikelihood user model (H0)             -17251.875
##   Loglikelihood unrestricted model (H1)     -17006.684
##                                                       
##   Akaike (AIC)                               34545.751
##   Bayesian (BIC)                             34667.563
##   Sample-size adjusted Bayesian (BIC)        34600.841
## 
## Root Mean Square Error of Approximation:
## 
##   RMSEA                                          0.104
##   90 Percent confidence interval - lower         0.096
##   90 Percent confidence interval - upper         0.112
##   P-value RMSEA <= 0.05                          0.000
## 
## Standardized Root Mean Square Residual:
## 
##   SRMR                                           0.045
## 
## Parameter Estimates:
## 
##   Standard errors                             Standard
##   Information                                 Expected
##   Information saturated (h1) model          Structured
## 
## Latent Variables:
##                    Estimate  Std.Err  z-value  P(>|z|)   Std.lv  Std.all
##   f =~                                                                  
##     sad               1.000                               0.510    0.689
##     blues             0.963    0.035   27.367    0.000    0.491    0.665
##     depress           1.191    0.040   29.563    0.000    0.607    0.740
##     happy             1.230    0.047   26.324    0.000    0.627    0.634
##     enjoy             1.074    0.042   25.351    0.000    0.548    0.606
##     hopeful           0.872    0.055   15.733    0.000    0.445    0.361
## 
## Regressions:
##                    Estimate  Std.Err  z-value  P(>|z|)   Std.lv  Std.all
##   f ~                                                                   
##     age               0.005    0.002    3.007    0.003    0.011    0.067
##     male             -0.134    0.023   -5.785    0.000   -0.263   -0.130
##   sad ~                                                                 
##     age               0.000                               0.000    0.000
##     male              0.000                               0.000    0.000
##   blues ~                                                               
##     age               0.000                               0.000    0.000
##     male              0.000                               0.000    0.000
##   depress ~                                                             
##     age               0.000                               0.000    0.000
##     male              0.000                               0.000    0.000
##   happy ~                                                               
##     age               0.000                               0.000    0.000
##     male              0.000                               0.000    0.000
##   enjoy ~                                                               
##     age               0.000                               0.000    0.000
##     male              0.000                               0.000    0.000
##   hopeful ~                                                             
##     age               0.010    0.004    2.572    0.010    0.010    0.049
##     male              0.000                               0.000    0.000
## 
## Intercepts:
##                    Estimate  Std.Err  z-value  P(>|z|)   Std.lv  Std.all
##    .sad               0.110    0.135    0.818    0.413    0.110    0.149
##    .blues             0.006    0.130    0.047    0.963    0.006    0.008
##    .depress           0.101    0.160    0.627    0.531    0.101    0.122
##    .happy             0.207    0.166    1.245    0.213    0.207    0.209
##    .enjoy             0.096    0.145    0.658    0.511    0.096    0.106
##    .hopeful          -0.037    0.291   -0.126    0.900   -0.037   -0.030
##    .f                 0.000                               0.000    0.000
## 
## Variances:
##                    Estimate  Std.Err  z-value  P(>|z|)   Std.lv  Std.all
##    .sad               0.287    0.010   27.426    0.000    0.287    0.525
##    .blues             0.304    0.011   28.381    0.000    0.304    0.558
##    .depress           0.305    0.012   24.900    0.000    0.305    0.453
##    .happy             0.586    0.020   29.400    0.000    0.586    0.598
##    .enjoy             0.516    0.017   30.162    0.000    0.516    0.632
##    .hopeful           1.312    0.039   33.719    0.000    1.312    0.864
##    .f                 0.254    0.015   17.511    0.000    0.977    0.977

CFA, Covariates, & Direct Effects, Example 0103 - MplusAutomation (input)

ex0103mod.mplus <-  MplusAutomation::mplusObject(
    MODEL = "f by sad-hopeful; 
            f on age male ;
            sad-hopeful ON age-male@0 ; 
            hopeful ON age ;",
    OUTPUT = "STDYX; tech1;",
    usevariables = c("sad", "blues", "depress", "happy", "enjoy", 
                     "hopeful", "age", "male"),
    rdata = epese
  )
ex0103fit.mplus <- MplusAutomation::mplusModeler(ex0103mod.mplus,
                          dataout = "ex0103.dat",
                          modelout = "ex0103.inp",
                          run = TRUE) 
## 
## Running model: ex0103.inp 
## System command: cd "/Users/douglastommet/Dropbox/work/ShortCourse/POSTED/SLIDES/LDA/lavaan" && "/Applications/Mplus/mplus" "ex0103.inp" 
## Reading model:  ex0103.out
file.remove("ex0103.inp")
## [1] TRUE

CFA, Covariates, & Direct Effects, Example 0103 - MplusAutomation (output)

# readModels("ex0103.out")
MplusAutomation::readModels("ex0103.out", what="summaries")
## Reading model:  ex0103.out
## Estimated using ML 
## Number of obs: 2442, number of (free) parameters: 21 
## 
## Model: Chi2(df = 18) = 490.382, p = 0 
## Baseline model: Chi2(df = 27) = 4124.409, p = 0 
## 
## Fit Indices: 
## 
## CFI = 0.885, TLI = 0.827, SRMR = 0.048 
## RMSEA = 0.104, 90% CI [0.096, 0.112], p < .05 = 0 
## AIC = 34545.751, BIC = 34667.563 
## NULL
MplusAutomation::readModels("ex0103.out")[["parameters"]][["unstandardized"]]
## Reading model:  ex0103.out
##           paramHeader   param    est    se  est_se    pval
## 1                F.BY     SAD  1.000 0.000 999.000 999.000
## 2                F.BY   BLUES  0.963 0.035  27.792   0.000
## 3                F.BY DEPRESS  1.191 0.040  30.113   0.000
## 4                F.BY   HAPPY  1.230 0.049  25.034   0.000
## 5                F.BY   ENJOY  1.074 0.045  24.002   0.000
## 6                F.BY HOPEFUL  0.872 0.057  15.319   0.000
## 7                F.ON     AGE  0.005 0.002   3.007   0.003
## 8                F.ON    MALE -0.134 0.023  -5.779   0.000
## 9              SAD.ON     AGE  0.000 0.000 999.000 999.000
## 10             SAD.ON    MALE  0.000 0.000 999.000 999.000
## 11           BLUES.ON     AGE  0.000 0.000 999.000 999.000
## 12           BLUES.ON    MALE  0.000 0.000 999.000 999.000
## 13         DEPRESS.ON     AGE  0.000 0.000 999.000 999.000
## 14         DEPRESS.ON    MALE  0.000 0.000 999.000 999.000
## 15           HAPPY.ON     AGE  0.000 0.000 999.000 999.000
## 16           HAPPY.ON    MALE  0.000 0.000 999.000 999.000
## 17           ENJOY.ON     AGE  0.000 0.000 999.000 999.000
## 18           ENJOY.ON    MALE  0.000 0.000 999.000 999.000
## 19         HOPEFUL.ON     AGE  0.010 0.004   2.572   0.010
## 20         HOPEFUL.ON    MALE  0.000 0.000 999.000 999.000
## 21         Intercepts     SAD  0.110 0.135   0.818   0.413
## 22         Intercepts   BLUES  0.006 0.130   0.047   0.963
## 23         Intercepts DEPRESS  0.101 0.160   0.627   0.531
## 24         Intercepts   HAPPY  0.207 0.166   1.245   0.213
## 25         Intercepts   ENJOY  0.096 0.145   0.657   0.511
## 26         Intercepts HOPEFUL -0.037 0.291  -0.126   0.900
## 27 Residual.Variances     SAD  0.287 0.011  27.267   0.000
## 28 Residual.Variances   BLUES  0.304 0.011  27.708   0.000
## 29 Residual.Variances DEPRESS  0.305 0.013  24.009   0.000
## 30 Residual.Variances   HAPPY  0.586 0.021  27.941   0.000
## 31 Residual.Variances   ENJOY  0.516 0.018  28.747   0.000
## 32 Residual.Variances HOPEFUL  1.312 0.039  33.574   0.000
## 33 Residual.Variances       F  0.254 0.015  17.467   0.000
MplusAutomation::readModels("ex0103.out")[["tech1"]]
## Reading model:  ex0103.out
## $parameterSpecification
## $nu
##   SAD BLUES DEPRESS HAPPY ENJOY HOPEFUL AGE MALE
## 1   0     0       0     0     0       0   0    0
## 
## $lambda
##         F SAD BLUES DEPRESS HAPPY ENJOY HOPEFUL AGE MALE
## SAD     0   0     0       0     0     0       0   0    0
## BLUES   0   0     0       0     0     0       0   0    0
## DEPRESS 0   0     0       0     0     0       0   0    0
## HAPPY   0   0     0       0     0     0       0   0    0
## ENJOY   0   0     0       0     0     0       0   0    0
## HOPEFUL 0   0     0       0     0     0       0   0    0
## AGE     0   0     0       0     0     0       0   0    0
## MALE    0   0     0       0     0     0       0   0    0
## 
## $theta
##         SAD BLUES DEPRESS HAPPY ENJOY HOPEFUL AGE MALE
## SAD       0    NA      NA    NA    NA      NA  NA   NA
## BLUES     0     0      NA    NA    NA      NA  NA   NA
## DEPRESS   0     0       0    NA    NA      NA  NA   NA
## HAPPY     0     0       0     0    NA      NA  NA   NA
## ENJOY     0     0       0     0     0      NA  NA   NA
## HOPEFUL   0     0       0     0     0       0  NA   NA
## AGE       0     0       0     0     0       0   0   NA
## MALE      0     0       0     0     0       0   0    0
## 
## $alpha
##   F SAD BLUES DEPRESS HAPPY ENJOY HOPEFUL AGE MALE
## 1 0   1     2       3     4     5       6   0    0
## 
## $beta
##          F SAD BLUES DEPRESS HAPPY ENJOY HOPEFUL AGE MALE
## F        0   0     0       0     0     0       0   7    8
## SAD      0   0     0       0     0     0       0   0    0
## BLUES    9   0     0       0     0     0       0   0    0
## DEPRESS 10   0     0       0     0     0       0   0    0
## HAPPY   11   0     0       0     0     0       0   0    0
## ENJOY   12   0     0       0     0     0       0   0    0
## HOPEFUL 13   0     0       0     0     0       0  14    0
## AGE      0   0     0       0     0     0       0   0    0
## MALE     0   0     0       0     0     0       0   0    0
## 
## $psi
##          F SAD BLUES DEPRESS HAPPY ENJOY HOPEFUL AGE MALE
## F       15  NA    NA      NA    NA    NA      NA  NA   NA
## SAD      0  16    NA      NA    NA    NA      NA  NA   NA
## BLUES    0   0    17      NA    NA    NA      NA  NA   NA
## DEPRESS  0   0     0      18    NA    NA      NA  NA   NA
## HAPPY    0   0     0       0    19    NA      NA  NA   NA
## ENJOY    0   0     0       0     0    20      NA  NA   NA
## HOPEFUL  0   0     0       0     0     0      21  NA   NA
## AGE      0   0     0       0     0     0       0   0   NA
## MALE     0   0     0       0     0     0       0   0    0
## 
## attr(,"class")
## [1] "mplus.parameterSpecification" "list"                        
## 
## $startingValues
## $nu
##   SAD BLUES DEPRESS HAPPY ENJOY HOPEFUL AGE MALE
## 1   0     0       0     0     0       0   0    0
## 
## $lambda
##         F SAD BLUES DEPRESS HAPPY ENJOY HOPEFUL AGE MALE
## SAD     0   1     0       0     0     0       0   0    0
## BLUES   0   0     1       0     0     0       0   0    0
## DEPRESS 0   0     0       1     0     0       0   0    0
## HAPPY   0   0     0       0     1     0       0   0    0
## ENJOY   0   0     0       0     0     1       0   0    0
## HOPEFUL 0   0     0       0     0     0       1   0    0
## AGE     0   0     0       0     0     0       0   1    0
## MALE    0   0     0       0     0     0       0   0    1
## 
## $theta
##         SAD BLUES DEPRESS HAPPY ENJOY HOPEFUL AGE MALE
## SAD       0    NA      NA    NA    NA      NA  NA   NA
## BLUES     0     0      NA    NA    NA      NA  NA   NA
## DEPRESS   0     0       0    NA    NA      NA  NA   NA
## HAPPY     0     0       0     0    NA      NA  NA   NA
## ENJOY     0     0       0     0     0      NA  NA   NA
## HOPEFUL   0     0       0     0     0       0  NA   NA
## AGE       0     0       0     0     0       0   0   NA
## MALE      0     0       0     0     0       0   0    0
## 
## $alpha
##   F   SAD BLUES DEPRESS HAPPY ENJOY HOPEFUL    AGE  MALE
## 1 0 0.454 0.337    0.51  0.63 0.465   0.973 74.316 0.424
## 
## $beta
##             F SAD BLUES DEPRESS HAPPY ENJOY HOPEFUL AGE MALE
## F       0.000   0     0       0     0     0       0   0    0
## SAD     1.000   0     0       0     0     0       0   0    0
## BLUES   0.991   0     0       0     0     0       0   0    0
## DEPRESS 1.218   0     0       0     0     0       0   0    0
## HAPPY   1.176   0     0       0     0     0       0   0    0
## ENJOY   1.031   0     0       0     0     0       0   0    0
## HOPEFUL 0.847   0     0       0     0     0       0   0    0
## AGE     0.000   0     0       0     0     0       0   0    0
## MALE    0.000   0     0       0     0     0       0   0    0
## 
## $psi
##            F   SAD BLUES DEPRESS HAPPY ENJOY HOPEFUL    AGE  MALE
## F       0.05    NA    NA      NA    NA    NA      NA     NA    NA
## SAD     0.00 0.274    NA      NA    NA    NA      NA     NA    NA
## BLUES   0.00 0.000 0.273      NA    NA    NA      NA     NA    NA
## DEPRESS 0.00 0.000 0.000   0.337    NA    NA      NA     NA    NA
## HAPPY   0.00 0.000 0.000   0.000  0.49    NA      NA     NA    NA
## ENJOY   0.00 0.000 0.000   0.000  0.00 0.408      NA     NA    NA
## HOPEFUL 0.00 0.000 0.000   0.000  0.00 0.000   0.759     NA    NA
## AGE     0.00 0.000 0.000   0.000  0.00 0.000   0.000 40.696    NA
## MALE    0.00 0.000 0.000   0.000  0.00 0.000   0.000 -0.190 0.244
## 
## attr(,"class")
## [1] "mplus.startingValues" "list"                
## 
## attr(,"class")
## [1] "mplus.tech1" "list"

Growth Modeling - Alcohol Use from Singer and Willet (2003)

address <- "https://stats.oarc.ucla.edu/stat/r/examples/alda/data/alcohol1_pp.txt"
alcohol1 <- read_csv(address, col_names=TRUE) 

alcohol1 <- alcohol1 %>%
  rename(age14 = age_14) %>%
  mutate(id = factor(id))

Summarizing the data

alcohol1 %>%
  select(-id) %>%
  gtsummary::tbl_summary(type = list(c(peer, cpeer) ~ "continuous",
                                     c(male, coa, ccoa) ~ "categorical"))
Characteristic N = 2461
age
14 82 (33%)
15 82 (33%)
16 82 (33%)
coa
0 135 (55%)
1 111 (45%)
male
0 120 (49%)
1 126 (51%)
age14
0 82 (33%)
1 82 (33%)
2 82 (33%)
alcuse 1.00 (0.00, 1.73)
peer 0.89 (0.00, 1.55)
cpeer -0.12 (-1.02, 0.53)
ccoa
-0.451 135 (55%)
0.549 111 (45%)

1 n (%); Median (IQR)

Spaghetti Plot

ggplot(alcohol1, aes(x = age, y = alcuse, group = id, color = id)) +
  geom_line(position =  position_jitter(width = .5)) +
  labs(title = "Alcohol use by age", x = "Age", y = "Alcohol Use") +
  guides(color = "none")

LGM - Intercept Only, Example 0104 - lme

ex0104fit.lme <- lme4::lmer(alcuse ~ (1 | id), data = alcohol1, REML = FALSE)
summary(ex0104fit.lme)
## Linear mixed model fit by maximum likelihood  ['lmerMod']
## Formula: alcuse ~ (1 | id)
##    Data: alcohol1
## 
##      AIC      BIC   logLik deviance df.resid 
##    676.2    686.7   -335.1    670.2      243 
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -1.8865 -0.3076 -0.3067  0.6137  2.8567 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev.
##  id       (Intercept) 0.5639   0.7509  
##  Residual             0.5617   0.7495  
## Number of obs: 246, groups:  id, 82
## 
## Fixed effects:
##             Estimate Std. Error t value
## (Intercept)  0.92195    0.09571   9.633

LGM - Intercept Only, Example 0104 - lavaan (input)

alc.wide <- alcohol1 %>% 
  select(id, age, alcuse) %>% 
  pivot_wider(id_cols = id, 
              names_from = age, 
              names_pre = "alc", 
              values_from = alcuse)

ex0104mod <- 'i =~ 1*alc14 + 1*alc15 + 1*alc16 
          alc14~~v1*alc14 
          alc15~~v1*alc15
          alc16~~v1*alc16
          i ~ 1
          i~~i'
ex0104fit.lavaan <- lavaan(ex0104mod, data=alc.wide, estimator = "MLR")

LGM - Intercept Only, Example 0104 - lavaan (output)

summary(ex0104fit.lavaan, fit.measures = TRUE, standardized=TRUE)
## lavaan 0.6-12 ended normally after 13 iterations
## 
##   Estimator                                         ML
##   Optimization method                           NLMINB
##   Number of model parameters                         5
##   Number of equality constraints                     2
## 
##   Number of observations                            82
## 
## Model Test User Model:
##                                               Standard      Robust
##   Test Statistic                                37.783      30.060
##   Degrees of freedom                                 6           6
##   P-value (Chi-square)                           0.000       0.000
##   Scaling correction factor                                  1.257
##     Yuan-Bentler correction (Mplus variant)                       
## 
## Model Test Baseline Model:
## 
##   Test statistic                                80.798      44.816
##   Degrees of freedom                                 3           3
##   P-value                                        0.000       0.000
##   Scaling correction factor                                  1.803
## 
## User Model versus Baseline Model:
## 
##   Comparative Fit Index (CFI)                    0.591       0.425
##   Tucker-Lewis Index (TLI)                       0.796       0.712
##                                                                   
##   Robust Comparative Fit Index (CFI)                         0.599
##   Robust Tucker-Lewis Index (TLI)                            0.799
## 
## Loglikelihood and Information Criteria:
## 
##   Loglikelihood user model (H0)               -335.078    -335.078
##   Scaling correction factor                                  0.700
##       for the MLR correction                                      
##   Loglikelihood unrestricted model (H1)       -316.186    -316.186
##   Scaling correction factor                                  1.227
##       for the MLR correction                                      
##                                                                   
##   Akaike (AIC)                                 676.156     676.156
##   Bayesian (BIC)                               683.376     683.376
##   Sample-size adjusted Bayesian (BIC)          673.914     673.914
## 
## Root Mean Square Error of Approximation:
## 
##   RMSEA                                          0.254       0.221
##   90 Percent confidence interval - lower         0.180       0.154
##   90 Percent confidence interval - upper         0.335       0.294
##   P-value RMSEA <= 0.05                          0.000       0.000
##                                                                   
##   Robust RMSEA                                               0.248
##   90 Percent confidence interval - lower                     0.164
##   90 Percent confidence interval - upper                     0.339
## 
## Standardized Root Mean Square Residual:
## 
##   SRMR                                           0.178       0.178
## 
## Parameter Estimates:
## 
##   Standard errors                             Sandwich
##   Information bread                           Observed
##   Observed information based on                Hessian
## 
## Latent Variables:
##                    Estimate  Std.Err  z-value  P(>|z|)   Std.lv  Std.all
##   i =~                                                                  
##     alc14             1.000                               0.751    0.708
##     alc15             1.000                               0.751    0.708
##     alc16             1.000                               0.751    0.708
## 
## Intercepts:
##                    Estimate  Std.Err  z-value  P(>|z|)   Std.lv  Std.all
##     i                 0.922    0.096    9.633    0.000    1.228    1.228
##    .alc14             0.000                               0.000    0.000
##    .alc15             0.000                               0.000    0.000
##    .alc16             0.000                               0.000    0.000
## 
## Variances:
##                    Estimate  Std.Err  z-value  P(>|z|)   Std.lv  Std.all
##    .alc14     (v1)    0.562    0.083    6.788    0.000    0.562    0.499
##    .alc15     (v1)    0.562    0.083    6.788    0.000    0.562    0.499
##    .alc16     (v1)    0.562    0.083    6.788    0.000    0.562    0.499
##     i                 0.564    0.106    5.314    0.000    1.000    1.000

LGM - Intercept Only, Example 0104 - MplusAutomation (input)

ex0104mod.mplus <-  MplusAutomation::mplusObject(
    ANALYSIS = "ESTIMATOR = MLR; ",
    MODEL = "i by alc14 - alc16@1 ; 
            [alc14 - alc16@0] ;
            [i*]  ; 
            alc14 - alc16 (1) ;",
    OUTPUT = "STDYX; tech1;",
    usevariables = c("alc14", "alc15", "alc16"),
    rdata = alc.wide
  )
ex0104fit.mplus <- MplusAutomation::mplusModeler(ex0104mod.mplus,
                          dataout = "ex0104.dat",
                          modelout = "ex0104.inp",
                          run = TRUE) 
## 
## Running model: ex0104.inp 
## System command: cd "/Users/douglastommet/Dropbox/work/ShortCourse/POSTED/SLIDES/LDA/lavaan" && "/Applications/Mplus/mplus" "ex0104.inp" 
## Reading model:  ex0104.out
file.remove("ex0104.inp")
## [1] TRUE

LGM - Intercept Only, Example 0104 - MplusAutomation (output)

# readModels("ex0104.out")
MplusAutomation::readModels("ex0104.out", what="summaries")
## Reading model:  ex0104.out
## Estimated using MLR 
## Number of obs: 82, number of (free) parameters: 3 
## 
## Model: Chi2(df = 6) = 30.06, p = 0 
## Baseline model: Chi2(df = 3) = 44.816, p = 0 
## 
## Fit Indices: 
## 
## CFI = 0.425, TLI = 0.712, SRMR = 0.152 
## RMSEA = 0.221, 90% CI [0.146, 0.303], p < .05 = 0 
## AIC = 676.156, BIC = 683.376 
## NULL
MplusAutomation::readModels("ex0104.out")[["parameters"]][["unstandardized"]]
## Reading model:  ex0104.out
##           paramHeader param   est    se  est_se pval
## 1                I.BY ALC14 1.000 0.000 999.000  999
## 2                I.BY ALC15 1.000 0.000 999.000  999
## 3                I.BY ALC16 1.000 0.000 999.000  999
## 4               Means     I 0.922 0.096   9.633    0
## 5          Intercepts ALC14 0.000 0.000 999.000  999
## 6          Intercepts ALC15 0.000 0.000 999.000  999
## 7          Intercepts ALC16 0.000 0.000 999.000  999
## 8           Variances     I 0.564 0.106   5.314    0
## 9  Residual.Variances ALC14 0.562 0.083   6.788    0
## 10 Residual.Variances ALC15 0.562 0.083   6.788    0
## 11 Residual.Variances ALC16 0.562 0.083   6.788    0
MplusAutomation::readModels("ex0104.out")[["tech1"]]
## Reading model:  ex0104.out
## $parameterSpecification
## $nu
##   ALC14 ALC15 ALC16
## 1     0     0     0
## 
## $lambda
##       I
## ALC14 0
## ALC15 0
## ALC16 0
## 
## $theta
##       ALC14 ALC15 ALC16
## ALC14     1    NA    NA
## ALC15     0     1    NA
## ALC16     0     0     1
## 
## $alpha
##   I
## 1 2
## 
## $beta
##   I
## I 0
## 
## $psi
##   I
## I 3
## 
## attr(,"class")
## [1] "mplus.parameterSpecification" "list"                        
## 
## $startingValues
## $nu
##   ALC14 ALC15 ALC16
## 1     0     0     0
## 
## $lambda
##       I
## ALC14 1
## ALC15 1
## ALC16 1
## 
## $theta
##       ALC14 ALC15 ALC16
## ALC14 0.435    NA    NA
## ALC15 0.000 0.542    NA
## ALC16 0.000 0.000 0.637
## 
## $alpha
##   I
## 1 0
## 
## $beta
##   I
## I 0
## 
## $psi
##      I
## I 0.05
## 
## attr(,"class")
## [1] "mplus.startingValues" "list"                
## 
## attr(,"class")
## [1] "mplus.tech1" "list"

LGM - Intercept and Slope, Example 0105 - lme

ex0105fit.lme <- lme4::lmer(alcuse ~ age14 + (1 + age14 | id ), data = alcohol1, REML = FALSE)
summary(ex0105fit.lme)
## Linear mixed model fit by maximum likelihood  ['lmerMod']
## Formula: alcuse ~ age14 + (1 + age14 | id)
##    Data: alcohol1
## 
##      AIC      BIC   logLik deviance df.resid 
##    648.6    669.6   -318.3    636.6      240 
## 
## Scaled residuals: 
##      Min       1Q   Median       3Q      Max 
## -2.47999 -0.38401 -0.07553  0.39001  2.50685 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  id       (Intercept) 0.6244   0.7902        
##           age14       0.1512   0.3888   -0.22
##  Residual             0.3373   0.5808        
## Number of obs: 246, groups:  id, 82
## 
## Fixed effects:
##             Estimate Std. Error t value
## (Intercept)  0.65130    0.10508   6.198
## age14        0.27065    0.06245   4.334
## 
## Correlation of Fixed Effects:
##       (Intr)
## age14 -0.441

LGM - Intercept and Slope, Example 0105 - lavaan (input)

ex0105mod <- 'i =~ 1*alc14 + 1*alc15 + 1*alc16
          s =~ 0*alc14 + 1*alc15 + 2*alc16
          alc14~~v1*alc14 
          alc15~~v1*alc15
          alc16~~v1*alc16
          i ~ 1
          i~~i
          s ~ 1
          s~~s
          i~~s'
ex0105fit.lavaan <- lavaan(ex0105mod, data=alc.wide, estimator = "MLR")

LGM - Intercept and Slope, Example 0105 - lavaan (output)

summary(ex0105fit.lavaan)
## lavaan 0.6-12 ended normally after 21 iterations
## 
##   Estimator                                         ML
##   Optimization method                           NLMINB
##   Number of model parameters                         8
##   Number of equality constraints                     2
## 
##   Number of observations                            82
## 
## Model Test User Model:
##                                               Standard      Robust
##   Test Statistic                                 4.238       2.939
##   Degrees of freedom                                 3           3
##   P-value (Chi-square)                           0.237       0.401
##   Scaling correction factor                                  1.442
##     Yuan-Bentler correction (Mplus variant)                       
## 
## Parameter Estimates:
## 
##   Standard errors                             Sandwich
##   Information bread                           Observed
##   Observed information based on                Hessian
## 
## Latent Variables:
##                    Estimate  Std.Err  z-value  P(>|z|)
##   i =~                                                
##     alc14             1.000                           
##     alc15             1.000                           
##     alc16             1.000                           
##   s =~                                                
##     alc14             0.000                           
##     alc15             1.000                           
##     alc16             2.000                           
## 
## Covariances:
##                    Estimate  Std.Err  z-value  P(>|z|)
##   i ~~                                                
##     s                -0.068    0.074   -0.920    0.357
## 
## Intercepts:
##                    Estimate  Std.Err  z-value  P(>|z|)
##     i                 0.651    0.105    6.198    0.000
##     s                 0.271    0.062    4.334    0.000
##    .alc14             0.000                           
##    .alc15             0.000                           
##    .alc16             0.000                           
## 
## Variances:
##                    Estimate  Std.Err  z-value  P(>|z|)
##    .alc14     (v1)    0.337    0.066    5.105    0.000
##    .alc15     (v1)    0.337    0.066    5.105    0.000
##    .alc16     (v1)    0.337    0.066    5.105    0.000
##     i                 0.624    0.162    3.861    0.000
##     s                 0.151    0.056    2.721    0.007

LGM - Intercept Only, Example 0105 - MplusAutomation (input)

ex0105mod.mplus <-  MplusAutomation::mplusObject(
    ANALYSIS = "ESTIMATOR = MLR; ",
    MODEL = "i by alc14 - alc16@1 ;
            s by alc14@0 alc15@1 alc16@2 ;
            [alc14 - alc16@0] ;
            [i* s*]  ; 
            alc14 - alc16 (1) ;",
    OUTPUT = "STDYX; tech1;",
    usevariables = c("alc14", "alc15", "alc16"),
    rdata = alc.wide
  )
ex0105fit.mplus <- MplusAutomation::mplusModeler(ex0105mod.mplus,
                          dataout = "ex0105.dat",
                          modelout = "ex0105.inp",
                          run = TRUE) 
## 
## Running model: ex0105.inp 
## System command: cd "/Users/douglastommet/Dropbox/work/ShortCourse/POSTED/SLIDES/LDA/lavaan" && "/Applications/Mplus/mplus" "ex0105.inp" 
## Reading model:  ex0105.out
file.remove("ex0105.inp")
## [1] TRUE

LGM - Intercept Only, Example 0105 - MplusAutomation (output)

# readModels("ex0105.out")
MplusAutomation::readModels("ex0105.out", what="summaries")
## Reading model:  ex0105.out
## Estimated using MLR 
## Number of obs: 82, number of (free) parameters: 6 
## 
## Model: Chi2(df = 3) = 2.939, p = 0.4011 
## Baseline model: Chi2(df = 3) = 44.816, p = 0 
## 
## Fit Indices: 
## 
## CFI = 1, TLI = 1, SRMR = 0.055 
## RMSEA = 0, 90% CI [0, 0.185], p < .05 = 0.49 
## AIC = 648.611, BIC = 663.051 
## NULL
MplusAutomation::readModels("ex0105.out")[["parameters"]][["unstandardized"]]
## Reading model:  ex0105.out
##           paramHeader param    est    se  est_se    pval
## 1                I.BY ALC14  1.000 0.000 999.000 999.000
## 2                I.BY ALC15  1.000 0.000 999.000 999.000
## 3                I.BY ALC16  1.000 0.000 999.000 999.000
## 4                S.BY ALC14  0.000 0.000 999.000 999.000
## 5                S.BY ALC15  1.000 0.000 999.000 999.000
## 6                S.BY ALC16  2.000 0.000 999.000 999.000
## 7              S.WITH     I -0.068 0.074  -0.920   0.357
## 8               Means     I  0.651 0.105   6.198   0.000
## 9               Means     S  0.271 0.062   4.334   0.000
## 10         Intercepts ALC14  0.000 0.000 999.000 999.000
## 11         Intercepts ALC15  0.000 0.000 999.000 999.000
## 12         Intercepts ALC16  0.000 0.000 999.000 999.000
## 13          Variances     I  0.624 0.162   3.861   0.000
## 14          Variances     S  0.151 0.056   2.721   0.007
## 15 Residual.Variances ALC14  0.337 0.066   5.105   0.000
## 16 Residual.Variances ALC15  0.337 0.066   5.105   0.000
## 17 Residual.Variances ALC16  0.337 0.066   5.105   0.000
MplusAutomation::readModels("ex0105.out")[["tech1"]]
## Reading model:  ex0105.out
## $parameterSpecification
## $nu
##   ALC14 ALC15 ALC16
## 1     0     0     0
## 
## $lambda
##       I S
## ALC14 0 0
## ALC15 0 0
## ALC16 0 0
## 
## $theta
##       ALC14 ALC15 ALC16
## ALC14     1    NA    NA
## ALC15     0     1    NA
## ALC16     0     0     1
## 
## $alpha
##   I S
## 1 2 3
## 
## $beta
##   I S
## I 0 0
## S 0 0
## 
## $psi
##   I  S
## I 4 NA
## S 5  6
## 
## attr(,"class")
## [1] "mplus.parameterSpecification" "list"                        
## 
## $startingValues
## $nu
##   ALC14 ALC15 ALC16
## 1     0     0     0
## 
## $lambda
##       I S
## ALC14 1 0
## ALC15 1 1
## ALC16 1 2
## 
## $theta
##       ALC14 ALC15 ALC16
## ALC14 0.435    NA    NA
## ALC15 0.000 0.542    NA
## ALC16 0.000 0.000 0.637
## 
## $alpha
##   I S
## 1 0 0
## 
## $beta
##   I S
## I 0 0
## S 0 0
## 
## $psi
##      I    S
## I 0.05   NA
## S 0.00 0.05
## 
## attr(,"class")
## [1] "mplus.startingValues" "list"                
## 
## attr(,"class")
## [1] "mplus.tech1" "list"