Mplus as a knitr engine in Rmarkdown
MplusAutomation: a brief guide
knitr package in Rmarkdown.Globally we can change the engine interpreters for one/multiple engine(s), we applied for Mplus:
knitr::opts_chunk$set(engine.path = list(
mplus = "C:/Program Files/Mplus/Mplus"
))Next step, we register a Mplus custom language engine:
knitr::knit_engines$set(mplus = function(options) {
code <- paste(options$code, collapse = "\n")
fileConn<-file("formplus.inp")
writeLines(code, fileConn)
close(fileConn)
out <- system2("C:/Program Files/Mplus/Mplus", "formplus.inp")
fileConnOutput <- file("formplus.out")
mplusOutput <- readLines(fileConnOutput)
knitr::engine_output(options, code, mplusOutput)
})For more language engines, we can refer demos from Yihui Xie’s post.
Further reading, we may read a Rich Jones’ post on rpubs
MplusAutomationThe MplusAutomation package for R (Hallquist and Wiley 2018):
Four core routines support these aims:
createModelsrunModelsreadModelscompareModelsThe MplusAutomation package can be installed within R using the following call:
if (!require(MplusAutomation)) install.packages("MplusAutomation")
library(MplusAutomation)MplusAutomationI use Edgar Anderson’s Iris Data with 150 cases (rows) and 5 variables named Sepal.Length, Sepal.Width, Petal.Length, Petal.Width, and Species.
iris data set gives the measurements in cm of the variables sepal length and width and petal length and width, respectively, for 50 flowers from each of 3 species of iris: Iris setosa, versicolor, and virginica.
?irishead(iris) Sepal.Length Sepal.Width Petal.Length Petal.Width Species
1 5.1 3.5 1.4 0.2 setosa
2 4.9 3.0 1.4 0.2 setosa
3 4.7 3.2 1.3 0.2 setosa
4 4.6 3.1 1.5 0.2 setosa
5 5.0 3.6 1.4 0.2 setosa
6 5.4 3.9 1.7 0.4 setosaprepareMPlusData() function prepares a data file in the MPlus’ format, namely, a tab-separated .dat file with no column names.
prepareMplusData(iris[, -5], "iris.dat", inpfile=TRUE)We can directly run in Rmarkdown or apply runModels to run the .inp files.
TITLE: iris LPA
DATA:
File is iris.dat
VARIABLE:
Names are x1, x2, x3, x4;
Classes = c(2) ;
MODEL:
%overall%
x1 x2 x3 x4;
%c#1%
[x1-x4];
%c#2%
[x1-x4];
ANALYSIS:
Type is mixture;
OUTPUT:
Tech11;Mplus VERSION 8.6
MUTHEN & MUTHEN
05/26/2021 10:33 PM
INPUT INSTRUCTIONS
TITLE: iris LPA
DATA:
File is iris.dat
VARIABLE:
Names are x1, x2, x3, x4;
Classes = c(2) ;
MODEL:
%overall%
x1 x2 x3 x4;
%c#1%
[x1-x4];
%c#2%
[x1-x4];
ANALYSIS:
Type is mixture;
OUTPUT:
Tech11;
*** WARNING in DATA command
Statement not terminated by a semicolon:
File is iris.dat
*** WARNING in MODEL command
All variables are uncorrelated with all other variables within class.
Check that this is what is intended.
2 WARNING(S) FOUND IN THE INPUT INSTRUCTIONS
iris LPA
SUMMARY OF ANALYSIS
Number of groups 1
Number of observations 150
Number of dependent variables 4
Number of independent variables 0
Number of continuous latent variables 0
Number of categorical latent variables 1
Observed dependent variables
Continuous
X1 X2 X3 X4
Categorical latent variables
C
Estimator MLR
Information matrix OBSERVED
Optimization Specifications for the Quasi-Newton Algorithm for
Continuous Outcomes
Maximum number of iterations 100
Convergence criterion 0.100D-05
Optimization Specifications for the EM Algorithm
Maximum number of iterations 500
Convergence criteria
Loglikelihood change 0.100D-06
Relative loglikelihood change 0.100D-06
Derivative 0.100D-05
Optimization Specifications for the M step of the EM Algorithm for
Categorical Latent variables
Number of M step iterations 1
M step convergence criterion 0.100D-05
Basis for M step termination ITERATION
Optimization Specifications for the M step of the EM Algorithm for
Censored, Binary or Ordered Categorical (Ordinal), Unordered
Categorical (Nominal) and Count Outcomes
Number of M step iterations 1
M step convergence criterion 0.100D-05
Basis for M step termination ITERATION
Maximum value for logit thresholds 15
Minimum value for logit thresholds -15
Minimum expected cell size for chi-square 0.100D-01
Optimization algorithm EMA
Random Starts Specifications
Number of initial stage random starts 20
Number of final stage optimizations 4
Number of initial stage iterations 10
Initial stage convergence criterion 0.100D+01
Random starts scale 0.500D+01
Random seed for generating random starts 0
Input data file(s)
iris.dat
Input data format FREE
UNIVARIATE SAMPLE STATISTICS
UNIVARIATE HIGHER-ORDER MOMENT DESCRIPTIVE STATISTICS
Variable/ Mean/ Skewness/ Minimum/ % with Percentiles
Sample Size Variance Kurtosis Maximum Min/Max 20%/60% 40%/80% Median
X1 5.843 0.312 4.300 0.67% 5.000 5.600 5.800
150.000 0.681 -0.574 7.900 0.67% 6.100 6.500
X2 3.057 0.316 2.000 0.67% 2.700 3.000 3.000
150.000 0.189 0.181 4.400 0.67% 3.100 3.400
X3 3.758 -0.272 1.000 0.67% 1.500 3.900 4.350
150.000 3.096 -1.396 6.900 0.67% 4.600 5.300
X4 1.199 -0.102 0.100 3.33% 0.200 1.100 1.300
150.000 0.577 -1.336 2.500 2.00% 1.500 1.900
RANDOM STARTS RESULTS RANKED FROM THE BEST TO THE WORST LOGLIKELIHOOD VALUES
Final stage loglikelihood values at local maxima, seeds, and initial stage start numbers:
-488.915 253358 2
-488.915 68985 17
-488.915 76974 16
-488.915 573096 20
THE BEST LOGLIKELIHOOD VALUE HAS BEEN REPLICATED. RERUN WITH AT LEAST TWICE THE
RANDOM STARTS TO CHECK THAT THE BEST LOGLIKELIHOOD IS STILL OBTAINED AND REPLICATED.
THE MODEL ESTIMATION TERMINATED NORMALLY
MODEL FIT INFORMATION
Number of Free Parameters 13
Loglikelihood
H0 Value -488.915
H0 Scaling Correction Factor 0.9851
for MLR
Information Criteria
Akaike (AIC) 1003.830
Bayesian (BIC) 1042.968
Sample-Size Adjusted BIC 1001.825
(n* = (n + 2) / 24)
FINAL CLASS COUNTS AND PROPORTIONS FOR THE LATENT CLASSES
BASED ON THE ESTIMATED MODEL
Latent
Classes
1 50.27148 0.33514
2 99.72852 0.66486
FINAL CLASS COUNTS AND PROPORTIONS FOR THE LATENT CLASSES
BASED ON ESTIMATED POSTERIOR PROBABILITIES
Latent
Classes
1 50.27148 0.33514
2 99.72852 0.66486
FINAL CLASS COUNTS AND PROPORTIONS FOR THE LATENT CLASSES
BASED ON THEIR MOST LIKELY LATENT CLASS MEMBERSHIP
Class Counts and Proportions
Latent
Classes
1 50 0.33333
2 100 0.66667
CLASSIFICATION QUALITY
Entropy 0.991
Average Latent Class Probabilities for Most Likely Latent Class Membership (Row)
by Latent Class (Column)
1 2
1 1.000 0.000
2 0.003 0.997
Classification Probabilities for the Most Likely Latent Class Membership (Column)
by Latent Class (Row)
1 2
1 0.995 0.005
2 0.000 1.000
Logits for the Classification Probabilities for the Most Likely Latent Class Membership (Column)
by Latent Class (Row)
1 2
1 5.216 0.000
2 -13.816 0.000
MODEL RESULTS
Two-Tailed
Estimate S.E. Est./S.E. P-Value
Latent Class 1
Means
X1 5.006 0.049 102.032 0.000
X2 3.423 0.055 61.909 0.000
X3 1.471 0.026 55.788 0.000
X4 0.250 0.016 15.938 0.000
Variances
X1 0.328 0.042 7.853 0.000
X2 0.121 0.017 7.347 0.000
X3 0.459 0.063 7.340 0.000
X4 0.123 0.013 9.126 0.000
Latent Class 2
Means
X1 6.265 0.068 92.358 0.000
X2 2.873 0.034 85.125 0.000
X3 4.911 0.085 57.798 0.000
X4 1.678 0.043 38.643 0.000
Variances
X1 0.328 0.042 7.853 0.000
X2 0.121 0.017 7.347 0.000
X3 0.459 0.063 7.340 0.000
X4 0.123 0.013 9.126 0.000
Categorical Latent Variables
Means
C#1 -0.685 0.175 -3.924 0.000
QUALITY OF NUMERICAL RESULTS
Condition Number for the Information Matrix 0.810E-03
(ratio of smallest to largest eigenvalue)
TECHNICAL 11 OUTPUT
Random Starts Specifications for the k-1 Class Analysis Model
Number of initial stage random starts 20
Number of final stage optimizations 4
VUONG-LO-MENDELL-RUBIN LIKELIHOOD RATIO TEST FOR 1 (H0) VERSUS 2 CLASSES
H0 Loglikelihood Value -741.018
2 Times the Loglikelihood Difference 504.205
Difference in the Number of Parameters 5
Mean 18.069
Standard Deviation 25.180
P-Value 0.0000
LO-MENDELL-RUBIN ADJUSTED LRT TEST
Value 484.852
P-Value 0.0000
Beginning Time: 22:33:15
Ending Time: 22:33:16
Elapsed Time: 00:00:01
MUTHEN & MUTHEN
3463 Stoner Ave.
Los Angeles, CA 90066
Tel: (310) 391-9971
Fax: (310) 391-8971
Web: www.StatModel.com
Support: Support@StatModel.com
Copyright (c) 1998-2021 Muthen & MuthenTITLE: iris LPA
DATA:
File is iris.dat
VARIABLE:
Names are x1, x2, x3, x4;
Classes = c(2) ;
MODEL:
%overall%
x1 x2 x3 x4;
x1 WITH x2-x4;
x2 WITH x3-x4;
x3 WITH x4;
%c#1%
[x1-x4];
%c#2%
[x1-x4];
ANALYSIS:
Type is mixture;
OUTPUT:
Tech11;Mplus VERSION 8.6
MUTHEN & MUTHEN
05/26/2021 10:33 PM
INPUT INSTRUCTIONS
TITLE: iris LPA
DATA:
File is iris.dat
VARIABLE:
Names are x1, x2, x3, x4;
Classes = c(2) ;
MODEL:
%overall%
x1 x2 x3 x4;
x1 WITH x2-x4;
x2 WITH x3-x4;
x3 WITH x4;
%c#1%
[x1-x4];
%c#2%
[x1-x4];
ANALYSIS:
Type is mixture;
OUTPUT:
Tech11;
*** WARNING in DATA command
Statement not terminated by a semicolon:
File is iris.dat
1 WARNING(S) FOUND IN THE INPUT INSTRUCTIONS
iris LPA
SUMMARY OF ANALYSIS
Number of groups 1
Number of observations 150
Number of dependent variables 4
Number of independent variables 0
Number of continuous latent variables 0
Number of categorical latent variables 1
Observed dependent variables
Continuous
X1 X2 X3 X4
Categorical latent variables
C
Estimator MLR
Information matrix OBSERVED
Optimization Specifications for the Quasi-Newton Algorithm for
Continuous Outcomes
Maximum number of iterations 100
Convergence criterion 0.100D-05
Optimization Specifications for the EM Algorithm
Maximum number of iterations 500
Convergence criteria
Loglikelihood change 0.100D-06
Relative loglikelihood change 0.100D-06
Derivative 0.100D-05
Optimization Specifications for the M step of the EM Algorithm for
Categorical Latent variables
Number of M step iterations 1
M step convergence criterion 0.100D-05
Basis for M step termination ITERATION
Optimization Specifications for the M step of the EM Algorithm for
Censored, Binary or Ordered Categorical (Ordinal), Unordered
Categorical (Nominal) and Count Outcomes
Number of M step iterations 1
M step convergence criterion 0.100D-05
Basis for M step termination ITERATION
Maximum value for logit thresholds 15
Minimum value for logit thresholds -15
Minimum expected cell size for chi-square 0.100D-01
Optimization algorithm EMA
Random Starts Specifications
Number of initial stage random starts 20
Number of final stage optimizations 4
Number of initial stage iterations 10
Initial stage convergence criterion 0.100D+01
Random starts scale 0.500D+01
Random seed for generating random starts 0
Input data file(s)
iris.dat
Input data format FREE
UNIVARIATE SAMPLE STATISTICS
UNIVARIATE HIGHER-ORDER MOMENT DESCRIPTIVE STATISTICS
Variable/ Mean/ Skewness/ Minimum/ % with Percentiles
Sample Size Variance Kurtosis Maximum Min/Max 20%/60% 40%/80% Median
X1 5.843 0.312 4.300 0.67% 5.000 5.600 5.800
150.000 0.681 -0.574 7.900 0.67% 6.100 6.500
X2 3.057 0.316 2.000 0.67% 2.700 3.000 3.000
150.000 0.189 0.181 4.400 0.67% 3.100 3.400
X3 3.758 -0.272 1.000 0.67% 1.500 3.900 4.350
150.000 3.096 -1.396 6.900 0.67% 4.600 5.300
X4 1.199 -0.102 0.100 3.33% 0.200 1.100 1.300
150.000 0.577 -1.336 2.500 2.00% 1.500 1.900
RANDOM STARTS RESULTS RANKED FROM THE BEST TO THE WORST LOGLIKELIHOOD VALUES
Final stage loglikelihood values at local maxima, seeds, and initial stage start numbers:
-296.448 533738 11
-296.448 68985 17
-296.448 unperturbed 0
-296.448 27071 15
THE BEST LOGLIKELIHOOD VALUE HAS BEEN REPLICATED. RERUN WITH AT LEAST TWICE THE
RANDOM STARTS TO CHECK THAT THE BEST LOGLIKELIHOOD IS STILL OBTAINED AND REPLICATED.
THE MODEL ESTIMATION TERMINATED NORMALLY
MODEL FIT INFORMATION
Number of Free Parameters 19
Loglikelihood
H0 Value -296.448
H0 Scaling Correction Factor 1.0304
for MLR
Information Criteria
Akaike (AIC) 630.895
Bayesian (BIC) 688.097
Sample-Size Adjusted BIC 627.966
(n* = (n + 2) / 24)
FINAL CLASS COUNTS AND PROPORTIONS FOR THE LATENT CLASSES
BASED ON THE ESTIMATED MODEL
Latent
Classes
1 50.00004 0.33333
2 99.99996 0.66667
FINAL CLASS COUNTS AND PROPORTIONS FOR THE LATENT CLASSES
BASED ON ESTIMATED POSTERIOR PROBABILITIES
Latent
Classes
1 50.00004 0.33333
2 99.99996 0.66667
FINAL CLASS COUNTS AND PROPORTIONS FOR THE LATENT CLASSES
BASED ON THEIR MOST LIKELY LATENT CLASS MEMBERSHIP
Class Counts and Proportions
Latent
Classes
1 50 0.33333
2 100 0.66667
CLASSIFICATION QUALITY
Entropy 1.000
Average Latent Class Probabilities for Most Likely Latent Class Membership (Row)
by Latent Class (Column)
1 2
1 1.000 0.000
2 0.000 1.000
Classification Probabilities for the Most Likely Latent Class Membership (Column)
by Latent Class (Row)
1 2
1 1.000 0.000
2 0.000 1.000
Logits for the Classification Probabilities for the Most Likely Latent Class Membership (Column)
by Latent Class (Row)
1 2
1 11.903 0.000
2 -12.706 0.000
MODEL RESULTS
Two-Tailed
Estimate S.E. Est./S.E. P-Value
Latent Class 1
X1 WITH
X2 0.113 0.019 5.805 0.000
X3 0.305 0.050 6.104 0.000
X4 0.114 0.019 6.112 0.000
X2 WITH
X3 0.098 0.022 4.359 0.000
X4 0.056 0.010 5.330 0.000
X3 WITH
X4 0.193 0.024 8.175 0.000
Means
X1 5.006 0.049 101.442 0.000
X2 3.428 0.053 64.589 0.000
X3 1.462 0.024 60.137 0.000
X4 0.246 0.015 16.674 0.000
Variances
X1 0.331 0.042 7.870 0.000
X2 0.120 0.016 7.574 0.000
X3 0.460 0.063 7.333 0.000
X4 0.123 0.013 9.137 0.000
Latent Class 2
X1 WITH
X2 0.113 0.019 5.805 0.000
X3 0.305 0.050 6.104 0.000
X4 0.114 0.019 6.112 0.000
X2 WITH
X3 0.098 0.022 4.359 0.000
X4 0.056 0.010 5.330 0.000
X3 WITH
X4 0.193 0.024 8.175 0.000
Means
X1 6.262 0.066 94.947 0.000
X2 2.872 0.033 86.743 0.000
X3 4.906 0.082 59.719 0.000
X4 1.676 0.042 39.652 0.000
Variances
X1 0.331 0.042 7.870 0.000
X2 0.120 0.016 7.574 0.000
X3 0.460 0.063 7.333 0.000
X4 0.123 0.013 9.137 0.000
Categorical Latent Variables
Means
C#1 -0.693 0.173 -4.002 0.000
QUALITY OF NUMERICAL RESULTS
Condition Number for the Information Matrix 0.149E-04
(ratio of smallest to largest eigenvalue)
TECHNICAL 11 OUTPUT
Random Starts Specifications for the k-1 Class Analysis Model
Number of initial stage random starts 20
Number of final stage optimizations 4
VUONG-LO-MENDELL-RUBIN LIKELIHOOD RATIO TEST FOR 1 (H0) VERSUS 2 CLASSES
H0 Loglikelihood Value -379.915
2 Times the Loglikelihood Difference 166.934
Difference in the Number of Parameters 5
Mean 11.054
Standard Deviation 9.531
P-Value 0.0000
LO-MENDELL-RUBIN ADJUSTED LRT TEST
Value 160.527
P-Value 0.0000
Beginning Time: 22:33:16
Ending Time: 22:33:17
Elapsed Time: 00:00:01
MUTHEN & MUTHEN
3463 Stoner Ave.
Los Angeles, CA 90066
Tel: (310) 391-9971
Fax: (310) 391-8971
Web: www.StatModel.com
Support: Support@StatModel.com
Copyright (c) 1998-2021 Muthen & MuthenTITLE: iris LPA
DATA:
File is iris.dat
VARIABLE:
Names are x1, x2, x3, x4;
Classes = c(2) ;
MODEL:
%c#1%
x1 x2 x3 x4;
x1 WITH x2-x4;
x2 WITH x3-x4;
x3 WITH x4;
[x1-x4];
%c#2%
x1 x2 x3 x4;
x1 WITH x2-x4;
x2 WITH x3-x4;
x3 WITH x4;
[x1-x4];
ANALYSIS:
Type is mixture;
OUTPUT:
Tech11;The disadvantage is that Rmarkdown shows a lengthy output, making “eye strain” to track the necessary information.
runModelsSave each chunk of the following models (either in a .txt file or in MPlus style using a .inp file type), then run with runModels
# Model 1
runModels("2-iris-LPA_means.inp")
Running model: 2-iris-LPA_means.inp
System command: C:\WINDOWS\system32\cmd.exe /c cd "C:\Users\minhh\Box Sync\Dissertation\hai-mn.github.io\_posts\2021-05-26-Mplus-as-a-knitr-engine" && "Mplus" "2-iris-LPA_means.inp" # Model 2
runModels("2-iris-LPA_means_correlated.inp")
Running model: 2-iris-LPA_means_correlated.inp
System command: C:\WINDOWS\system32\cmd.exe /c cd "C:\Users\minhh\Box Sync\Dissertation\hai-mn.github.io\_posts\2021-05-26-Mplus-as-a-knitr-engine" && "Mplus" "2-iris-LPA_means_correlated.inp" # Model 3
runModels("2-iris-LPA_means_correlated_free_variances.inp")
Running model: 2-iris-LPA_means_correlated_free_variances.inp
System command: C:\WINDOWS\system32\cmd.exe /c cd "C:\Users\minhh\Box Sync\Dissertation\hai-mn.github.io\_posts\2021-05-26-Mplus-as-a-knitr-engine" && "Mplus" "2-iris-LPA_means_correlated_free_variances.inp" m1 <- readModels("2-iris-LPA_means.out")Reading model: 2-iris-LPA_means.out m2 <- readModels("2-iris-LPA_means_correlated.out")Reading model: 2-iris-LPA_means_correlated.out m3 <- readModels("2-iris-LPA_means_correlated_free_variances.out")Reading model: 2-iris-LPA_means_correlated_free_variances.out Now, we inspect the fit statistics and other summary information for the three models:
m1$summaries$BIC[1] 1042.968m2$summaries$BIC[1] 688.097m3$summaries$BIC[1] 574.018And examine parameters:
m1$parameters[[1]][-nrow(m1$parameters[[1]]), ] paramHeader param est se est_se pval LatentClass
1 Means X1 5.006 0.049 102.032 0 1
2 Means X2 3.423 0.055 61.909 0 1
3 Means X3 1.471 0.026 55.788 0 1
4 Means X4 0.250 0.016 15.938 0 1
5 Variances X1 0.328 0.042 7.853 0 1
6 Variances X2 0.121 0.017 7.347 0 1
7 Variances X3 0.459 0.063 7.340 0 1
8 Variances X4 0.123 0.013 9.126 0 1
9 Means X1 6.265 0.068 92.358 0 2
10 Means X2 2.873 0.034 85.125 0 2
11 Means X3 4.911 0.085 57.798 0 2
12 Means X4 1.678 0.043 38.643 0 2
13 Variances X1 0.328 0.042 7.853 0 2
14 Variances X2 0.121 0.017 7.347 0 2
15 Variances X3 0.459 0.063 7.340 0 2
16 Variances X4 0.123 0.013 9.126 0 2m2$parameters[[1]][-nrow(m2$parameters[[1]]), ] paramHeader param est se est_se pval LatentClass
1 X1.WITH X2 0.113 0.019 5.805 0 1
2 X1.WITH X3 0.305 0.050 6.104 0 1
3 X1.WITH X4 0.114 0.019 6.112 0 1
4 X2.WITH X3 0.098 0.022 4.359 0 1
5 X2.WITH X4 0.056 0.010 5.330 0 1
6 X3.WITH X4 0.193 0.024 8.175 0 1
7 Means X1 5.006 0.049 101.442 0 1
8 Means X2 3.428 0.053 64.589 0 1
9 Means X3 1.462 0.024 60.137 0 1
10 Means X4 0.246 0.015 16.674 0 1
11 Variances X1 0.331 0.042 7.870 0 1
12 Variances X2 0.120 0.016 7.574 0 1
13 Variances X3 0.460 0.063 7.333 0 1
14 Variances X4 0.123 0.013 9.137 0 1
15 X1.WITH X2 0.113 0.019 5.805 0 2
16 X1.WITH X3 0.305 0.050 6.104 0 2
17 X1.WITH X4 0.114 0.019 6.112 0 2
18 X2.WITH X3 0.098 0.022 4.359 0 2
19 X2.WITH X4 0.056 0.010 5.330 0 2
20 X3.WITH X4 0.193 0.024 8.175 0 2
21 Means X1 6.262 0.066 94.947 0 2
22 Means X2 2.872 0.033 86.743 0 2
23 Means X3 4.906 0.082 59.719 0 2
24 Means X4 1.676 0.042 39.652 0 2
25 Variances X1 0.331 0.042 7.870 0 2
26 Variances X2 0.120 0.016 7.574 0 2
27 Variances X3 0.460 0.063 7.333 0 2
28 Variances X4 0.123 0.013 9.137 0 2m3$parameters[[1]][-nrow(m3$parameters[[1]]), ] paramHeader param est se est_se pval LatentClass
1 X1.WITH X2 0.097 0.022 4.469 0.000 1
2 X1.WITH X3 0.016 0.010 1.655 0.098 1
3 X1.WITH X4 0.010 0.004 2.486 0.013 1
4 X2.WITH X3 0.011 0.008 1.418 0.156 1
5 X2.WITH X4 0.009 0.005 1.763 0.078 1
6 X3.WITH X4 0.006 0.003 2.316 0.021 1
7 Means X1 5.006 0.049 101.439 0.000 1
8 Means X2 3.428 0.053 64.591 0.000 1
9 Means X3 1.462 0.024 60.132 0.000 1
10 Means X4 0.246 0.015 16.673 0.000 1
11 Variances X1 0.122 0.022 5.498 0.000 1
12 Variances X2 0.141 0.033 4.267 0.000 1
13 Variances X3 0.030 0.007 4.222 0.000 1
14 Variances X4 0.011 0.003 3.816 0.000 1
15 X1.WITH X2 0.121 0.027 4.467 0.000 2
16 X1.WITH X3 0.449 0.070 6.377 0.000 2
17 X1.WITH X4 0.166 0.026 6.282 0.000 2
18 X2.WITH X3 0.141 0.033 4.330 0.000 2
19 X2.WITH X4 0.079 0.015 5.295 0.000 2
20 X3.WITH X4 0.286 0.031 9.107 0.000 2
21 Means X1 6.262 0.066 94.948 0.000 2
22 Means X2 2.872 0.033 86.743 0.000 2
23 Means X3 4.906 0.082 59.719 0.000 2
24 Means X4 1.676 0.042 39.652 0.000 2
25 Variances X1 0.435 0.059 7.332 0.000 2
26 Variances X2 0.110 0.017 6.442 0.000 2
27 Variances X3 0.675 0.086 7.822 0.000 2
28 Variances X4 0.179 0.018 10.148 0.000 2One last thing, I want to mention about the createModels() which can creates a set of models using a template. We can save file as mplus_iris_lpa_template.txt
[[init]]
iterators = classes;
classes = 1:9;
filename = "[[classes]]-iris-LPA.inp";
outputDirectory = the_dir;
[[/init]]
TITLE: iris LPA
DATA:
File is iris.dat
VARIABLE:
Names are x1 x2 x3 x4;
Classes = c([[classes]]) ;
MODEL:
%overall%
x1 x2 x3 x4;
[x1-x4];
ANALYSIS:
Type is mixture;
OUTPUT:
Tech11;Here is an example that would create models with different numbers of profiles, from 1 to 9.
#Set the folder containing mplus.txt as working
createModels("mplus_iris_lpa_template.txt")
#Set the folder containing input files as working directory
runModels()
#Set the folder containing output files as working directory
models_list <- readModels()
outputs<-extractModelParameters()Further reading, we can look at a Josh Rosenberg’s post and the Mplus website
More information about the MplusAutomation package in GitHub.
If you see mistakes or want to suggest changes, please create an issue on the source repository.
Text and figures are licensed under Creative Commons Attribution CC BY 4.0. Source code is available at https://github.com/hai-mn/hai-mn.github.io, unless otherwise noted. The figures that have been reused from other sources don't fall under this license and can be recognized by a note in their caption: "Figure from ...".
For attribution, please cite this work as
Nguyen (2021, May 26). HaiBiostat: Set up to run Mplus inside Rmarkdown. Retrieved from https://hai-mn.github.io/posts/2021-05-26-Mplus-as-a-knitr-engine/
BibTeX citation
@misc{nguyen2021set,
author = {Nguyen, Hai},
title = {HaiBiostat: Set up to run Mplus inside Rmarkdown},
url = {https://hai-mn.github.io/posts/2021-05-26-Mplus-as-a-knitr-engine/},
year = {2021}
}