Muthén, B. (2011).
Applications of causally defined direct and indirect effects in mediation analysis using SEM in Mplus. Submitted for publication.
Muthén, B., Asparouhov, T., Hunter, A. & Leuchter, A. (2011).
Growth modeling with nonignorable dropout: Alternative analyses of the STAR*D antidepressant trial.
Psychological Methods, 16, 1733.
Muthén, B. & Asparouhov, T. (2012).
Bayesian SEM: A more flexible representation of substantive theory. Psychological Methods, 17, 313335.
Muthén, B. (2010).
Bayesian analysis in Mplus: A brief introduction. Technical Report. Version 3.
Muthén, B., Asparouhov, T., Boye, M.E., Hackshaw, M.D., & Naegeli, A.N. (2009).
Applications of continuoustime survival in latent variable models for the analysis of
oncology randomized clinical trial data using Mplus. Technical Report.
Brown, E.C., Catalano, C.B., Fleming, C.B., Haggerty, K.P. & Abbot, R.D. (2004).
Adolescent substance use outcomes in the Raising
Healthy Children Project: A twopart latent growth curve analysis. Paper under review.
Muthén, B. (2004).
Latent variable analysis: Growth mixture modeling and related
techniques for longitudinal data.
In D. Kaplan (ed.), Handbook of quantitative methodology
for the social sciences (pp. 345368). Newbury Park, CA: Sage Publications.
Prescott, C.A. (2004). Using the Mplus computer program to estimate models for
continuous and categorical data from twins. Behavior Genetics, 34, 17 40.
Muthén, L.K. and Muthén, B.O. (2002).
How to use a Monte Carlo study to decide on sample size and determine power.
Structural Equation Modeling, 4, 599620. (#97).
Dagne, G.A., Howe, G.W., Brown, C.H., & Muthén, B. (2002).
Hierarchical modeling of
sequential behavioral data: An empirical Bayesian approach.
Psychological Methods, 7, 262280.
Jo, B. (2002).
Statistical power in randomized intervention studies with noncompliance.
Psychological Methods, 7, 178193.
Muthén, B. (2001).
Secondgeneration structural equation modeling with a combination of
categorical and continuous latent variables: New opportunities for latent class/latent growth
modeling.
In Collins, L.M. & Sayer, A. (Eds.), New Methods for the Analysis of Change (pp. 291322). Washington, D.C.: APA. (#82)
Muthén, B. & Masyn, K. (2001).
Discretetime survival mixture analysis. (#92)
Muthén, B. (2001).
Latent variable mixture modeling.
In G. A. Marcoulides & R. E. Schumacker (eds.), New Developments and Techniques
in Structural Equation Modeling (pp. 133). Lawrence Erlbaum Associates. (#86)
Muthén, B., Brown, C.H., Masyn, K., Jo, B., Khoo, S.T., Yang, C.C.,
Wang, C.P., Kellam, S., Carlin, J., & Liao, J. (2000).
General growth mixture
modeling for randomized preventive interventions. Accepted for publication
in Biostatistics. (#87)
Muthén, B. & Muthén, L. (2000).
Integrating personcentered
and variablecentered analyses: Growth mixture modeling with latent
trajectory classes.
Alcoholism: Clinical and Experimental Research, 24, 882891. (#85)
Type of Analysis 
Input file 
Data file 
View output 

Muthén, B. (2011).
Applications of causally defined direct and indirect effects in mediation analysis using SEM in Mplus. Submitted for publication.
Download this paper. Click here to view the Technical appendix that goes with this paper and click here for the Mplus input appendix.

1. Table 25 
run1.inp 
N/A 
run1.out 
2. Table 1, Table 26 
run2.inp 
N/A 
run2.out 
3. Table 27 
run3.inp 
N/A 
run3.out 
4. Table 2, Table 28* 
run4.inp 
N/A 
run4.out 
5. Table 3, Table 29* 
run5.inp 
N/A 
run5.out 
6. Table 30* 
run6.inp 
1stn200.dat 
run6.out 
7. Table 4, Table 3132* 
run7.inp 
N/A 
run7.out 
8. Table 5, Table 33 
run8.inp 
N/A 
run8.out 
9. Table 7, Table 34* 
run9.inp 
4cat m.dat 
run9.out 
10. Table 8, Table 35* 
run10.inp 
4cat m.dat 
run10.out 
11. Table 3637 
run11.inp 
N/A 
run11.out 
12. Table 10, Table 38 
run12.inp 
N/A 
run12.out 
13. Table 3940* 
run13.inp 
N/A 
run13.out 
14. Table 11, Table 41* 
run14.inp 
N/A 
run14.out 
15. Table 12, Table 4243* 
run15.inp 
N/A 
run15.out 
16. Table 14, Table 4445* 
run16.inp 
n200.dat 
run16.out 
17. Table 15, Table 4647 
run17.inp 
N/A 
run17.out 
18. Table 1617, Table 4849 
run18.inp 
N/A 
run18.out 
19. Table 1920, Table 5051 
run19.inp 
nombin.dat 
run19.out 
20. Table 5253 
run20.inp 
N/A 
run20.out 
21. Table 21, Table 54 
run21.inp 
N/A 
run21.out 
22. Table 22, Table 55 
run22.inp 
N/A 
run22.out 
23. Table 23, Table 56 
run23.inp 
N/A 
run23.out 
24. Table 24, Table 57 
run24.inp 
N/A 
run24.out 
*This analysis requires Mplus version 6.12

Back to the top
Type of Analysis 
Input file 
Data file 
View output 

Muthén, B., Asparouhov, T., Hunter, A. & Leuchter, A. (2011). Growth modeling with nonignorable dropout: Alternative analyses of
the STAR*D antidepressant trial. Psychological Methods, 16, 1733.
Download this paper.
Click here for an explanation of the runs.

1. Section 4 MAR 4c 
run1.inp 
N/A 
run1.out 
2. Section 5.1.1 Create yu data 
run2.inp 
N/A 
run2.out 
3. Section 5.1.1 Patternmixture 
run3.inp 
N/A 
run3.out 
4. Section 5.1.1 Patternmixture using V6 
run4.inp 
N/A 
run4.out 
5. Section 5.1.2 Roy dropout 4c 
run5.inp 
N/A 
run5.out 
6. Section 5.1.2 Roy dropout 4c V6 
run6.inp 
N/A 
run6.out 
7. Section 5.2.1 DiggleKenward 
run7.inp 
N/A 
run7.out 
8. Section 5.2.1 DiggleKenward V6 
run8.inp 
N/A 
run8.out 
9. Section 5.2.2 Beunckens 
run9.inp 
N/A 
run9.out 
10. Section 6.1 MuthenRoy 
run10.inp 
N/A 
run10.out 
11. Section 6.2 DiggleKenward 4c V6 
run11.inp 
N/A 
run11.out 
12. Section 7.2 Distal MAR 4c 
run12.inp 
N/A 
run12.out 
13. Section 7.2 Distal DiggleKenward 4c V6 
run13.inp 
N/A 
run13.out 
14. Section 7.2 Distal MuthenRoy, Step 1 V6 
run14.inp 
N/A 
run14.out 
15. Section 7.2 Distal MuthenRoy, Step 2 V6 
run15.inp 
N/A 
run15.out 
Back to the top
Type of Analysis 
Input file 
Data file 
View output 

Muthén, B. & Asparouhov, T. (2011).
Bayesian SEM: A more flexible representation of substantive theory. Psychological Methods, 17, 313335.
Download the latest version dated October 21, 2011.
Download the 2nd version dated April 14, 2011. Click here to view the seven web tables referred to in the paper.
Download the 1st version dated September 29, 2010 containing a MIMIC section and more tables, and the corresponding Mplus inputs, data, and outputs here. The seven web tables correspond to tables 8, 10, 17, 18, 19, 20, and 21 of the first version.

Table 3, GrantWhite ML CFA 
run1.inp 
HS Combined.txt 
run1.out 
Table 3, GrantWhite ML EFA 
run2.inp 
HS Combined.txt 
run2.out 
Table 3, Pasteur ML CFA 
run3.inp 
HS Combined.txt 
run3.out 
Table 3, Pasteur ML EFA 
run4.inp 
HS Combined.txt 
run4.out 
Table 4, GrantWhite ML EFA 
run5.inp 
HS Combined.txt 
run5.out 
Table 4, Pasteur ML EFA 
run6.inp 
HS Combined.txt 
run6.out 
Table 5, GrantWhite Bayes 
run7.inp 
HS Combined.txt 
run7.out 
Table 56, GrantWhite Bayes xload 
run8.inp 
HS Combined.txt 
run8.out 
Table 5, Pasteur Bayes 
run9.inp 
HS Combined.txt 
run9.out 
Table 56, Pasteur Bayes xload 
run10.inp 
HS Combined.txt 
run10.out 
Table 9, ML 0.1 
run12.inp 
N/A 
run12.out 
Table 10 
run13.inp 
N/A 
run13.out 
Table 1314, females, ML EFA 
run14.inp 
BHPS OINDRESPX1.DAT 
run14.out 
Table 15, females, BSEM 
run15.inp 
BHPS OINDRESPX1.DAT 
run15.out 
Back to the top
Back to the top
Type of Analysis 
Input file 
Data file 
View output 

Muthén, B., Asparouhov, T., Boye, M.E., Hackshaw, M.D., & Naegeli, A.N. (2009).
Applications of continuoustime survival in latent variable models for the analysis of
oncology randomized clinical trial data using Mplus. Technical Report.
Download this paper.

Section 3.1, Cox regression 
run1.inp 
N/A 
run1.out 
Table 6, proportional model 
run2.inp 
N/A 
run2.out 
Table 6, unrestricted model 
run3.inp 
N/A 
run3.out 
Table 6, linear model 
run4.inp 
N/A 
run4.out 
Table 7, nonprop on qol 
run5.inp 
N/A 
run5.out 
Table 10, XuZeger model 
run6.inp 
N/A 
run6.out 
Table 10, observed model 
run7.inp 
N/A 
run7.out 
Table 10, random effects model 
run8.inp 
N/A 
run8.out 
Table 10, growth mixture model 
run9.inp 
N/A 
run9.out 
Table 11, i and s 3 covs qol 
run10.inp 
N/A 
run10.out 
Table 14, efa 5+3 mlr 
run11.inp 
N/A 
run11.out 
Table 14, cfa 5+3 1g 1s 
run12.inp 
N/A 
run12.out 
Table 14, lca 5+3 2c 
run13.inp 
N/A 
run13.out 
Table 14, fma 5+3 fma 2c 1f 
run14.inp 
N/A 
run14.out 
Table 14, mimic with xs 
run15.inp 
N/A 
run15.out 
Figure 16 model 
run16.inp 
N/A 
run16.out 
Figure 22 model 
run17.inp 
N/A 
run17.out 
Figure 23 model 
run18.inp 
N/A 
run18.out 
Table 20, M1 
run19.inp 
N/A 
run19.out 
Table 20, M2 
run20.inp 
N/A 
run20.out 
Table 20, M3 
run21.inp 
N/A 
run21.out 
Table 20, M4 
run22.inp 
N/A 
run22.out 
Table 20, M5 
run23.inp 
N/A 
run23.out 
Table 20, M6 
run24.inp 
N/A 
run24.out 
Back to the top
Type of Analysis 
Input file 
Data file 
View output 

Brown, E.C., Catalano, C.B., Fleming, C.B., Haggerty, K.P. & Abbot, R.D. (2004). Adolescent substance use outcomes in the Raising
Healthy Children Project: A twopart latent growth curve analysis. Paper under review.
Download the corresponding set of examples. The data files for these
examples are not available for download.

Twopart growth for alcohol 
N/A 
N/A 
twopartlgm_alc.out 
Twopart growth for cigarettes 
N/A 
N/A 
twopartlgm_cig.out 
Twopart growth for pot 
N/A 
N/A 
twopartlgm_pot.out 
Back to the top
Type of Analysis 
Input file 
Data file 
View output 

Muthén, B. (2004). Latent variable analysis: Growth mixture modeling and related
techniques for longitudinal data. In D. Kaplan (ed.), Handbook of quantitative methodology
for the social sciences (pp. 345368). Newbury Park, CA: Sage Publications.
Download the corresponding set of examples.

Example 6: LCGA, pp. 361362 
example6.inp 
N/A 
example6.std 
Example 7: Growth Analysis 
example7.inp 
N/A 
example7.std 
Example 8: GMM, pp. 362363 
example8.inp 
N/A 
example8.std 
Back to the top
Type of Analysis 
Input file 
Data file 
View output 

Prescott, C.A. (2004). Using the Mplus computer program to estimate models for
continuous and categorical data from twins. Behavior Genetics, 34, 17 40.
Download this paper, the
technical appendix for the paper, or
the corresponding set of examples. The data file onset99.dat is not
available for download.

Example 1: 2group univariate twin model for a continuous variable 
example1.inp 
example1.dat 
example1.out 
Example 2 step 1: Estimating thresholds for a 2group univariate twin model for a binary variable 
example2_step1.inp 
example1.dat 
example2_step1.out 
Example 2: 2group univariate twin model for a binary variable (DELTA parameterization) 
example2_delta.inp 
example1.dat 
example2_delta.out 
Example 2: 2group univariate twin model for a binary variable with THETA parameterization 
example2_theta.inp 
example1.dat 
example2_theta.out 
Example 3: 5group model for transformed age at drinking onset, MF proportional 
example3.inp 
onset99.dat 
example3.out 
Example 4: 5group model for 3categ. diagnosis with age regressions & free R 
example4.inp 
onset99.dat 
example4.out 
Example 5: 2group bivariate model for age at drinking onset and diagnosis 
example5.inp 
onset99.dat 
example5.out 
Example 6: 2group bivariate mediation model for diagnosis and drinking onset with fixed unreliability for onset among female drinking pairs 
example6.inp 
onset99.dat 
example6.out 
Example 7 step 1: Estimating thresholds for input into THETA parameterization model 
example7_step1.inp 
onset99.dat 
example7_step1.out 
Example 7 step 2: 2group bivariate model for diagnosis and categorized onset age using threshold values estimated in prior run 
example7_step2.inp 
onset99.dat 
example7_step2.out 
5group model for age at drinking onset A & C loadings parameterized as square roots to keep nonnegative 
MF_sqroot.inp 
onset99.dat 
MF_sqroot.out 
Back to the top
Type of Analysis 
Input file 
Data file 
View output 

Muthén, L.K. and Muthén, B.O. (2002).
How to use a Monte Carlo study to decide on sample size and determine power.
Structural Equation Modeling, 4, 599620. (#97)
Download this paper or the corresponding
set of examples. 
CFA model with normally distributed continuous factor indicators without missing data.

cfa1.inp 
N/A 
cfa1.std 
CFA model with normally distributed continuous factor indicators with missing data.

cfa2.inp 
N/A 
cfa2.std 
CFA model with nonnormal continuous factor indicators without missing data.

cfa3.inp 
N/A 
cfa3.std 
CFA model with nonnormal continuous factor indicators with missing data.

cfa4.inp 
N/A 
cfa4.std 
Growth model with normally distributed continuous outcomes without missing data without
a covariate.

growth1.inp 
N/A 
growth1.std 
Growth model with normally distributed continuous outcomes without missing data with a
covariate that has a regression coefficient of 0.2 for the slope growth factor.

growth2.inp 
N/A 
growth2.std 
Growth model with normally distributed continuous outcomes with missing data with a covariate
that has a regression coefficient of 0.2 for the slope growth factor.

growth3.inp 
N/A 
growth3.std 
Growth model with normally distributed continuous outcomes without missing data with a
covariate that has a regression coefficient of 0.1 for the slope growth factor.

growth4.inp 
N/A 
growth4.std 
Growth model with normally distributed continuous outcomes with missing data with a
covariate that has a regression coefficient of 0.1 for the slope growth factor.

growth5.inp 
N/A 
growth5.std 
Back to the top
Type of Analysis 
Input file 
Data file 
View output 

Dagne, G.A., Howe, G.W., Brown, C.H., & Muthén, B. (2002). Hierarchical modeling of
sequential behavioral data: An empirical Bayesian approach. Psychological Methods, 7, 262280.
Download this paper or the corresponding
set of examples. Refer to
Web Note 3 for technical background for the Mplus inputs.

Model 1. Full model. 5 parameters.

model1.inp 
stationary_oddratio.dat 
model1.std 
Model 2. Equal intercepts and zero residual variances. 2 parameters.

model2.inp 
stationary_oddratio.dat 
model2.std 
Model 3. Equal intercepts. 4 parameters.

model3.inp 
stationary_oddratio.dat 
model3.std 
Model 4. Zero residual variances. 3 parameters.

model4.inp 
stationary_oddratio.dat 
model4.std 
Model 5. Zero residual variances, zero factor variance. 2 parameters.

model5.inp 
stationary_oddratio.dat 
model5.std 
Model 6. Zero factor variance. 4 parameters.

model6.inp 
stationary_oddratio.dat 
model6.std 
Back to the top
Type of Analysis 
Input file 
Data file 
View output 

Jo, B (2002). Statistical power in randomized intervention studies with
noncompliance. Psychological Methods, 7, 178193.
Download this paper or the corresponding
set of examples. View
a description of the Mplus inputs used in this paper.

Internal Mplus Monte Carlo simulation of CACE power.

cacepow.inp 
N/A 
cacepow.std 
Back to the top
Type of Analysis 
Input file 
Data file 
View output 

Muthén, B. (2001). Secondgeneration structural equation modeling with a combination of
categorical and continuous latent variables: New opportunities for latent class/latent growth
modeling. In Collins, L.M. & Sayer, A. (Eds.), New Methods for the Analysis of Change (pp. 291322). Washington, D.C.: APA. (#82)
Download this paper.
The data file lsay.dat is not available for download.

EXAMPLE 1: LSAY example, page 22 unconditional analysis, 1class model

penn1.inp 
lsay.dat 
penn1.std 
EXAMPLE 1: LSAY example, page 22 unconditional analysis, 2class model,
classinvariant factor covariance matrix (Psi) and residual covariance matrix (Theta)

penn2.inp 
lsay.dat 
penn2.std 
EXAMPLE 1: LSAY example, same model as penn2, but illustration of E step iterations
getting stuck with poor starting values

penn3.inp 
lsay.dat 
penn3.std 
EXAMPLE 1: LSAY example, page 23 unconditional analysis, 2class model,
classinvariant factor covariance matrix, classvarying residual covariance matrix

penn4.inp 
lsay.dat 
penn4.std 
EXAMPLE 1: LSAY example, page 23 unconditional analysis, 2class model,
classvarying factor covariance matrix, classvarying residual covariance matrix

penn5.inp 
lsay.dat 
penn5.std 
EXAMPLE 1: LSAY example, page 24 conditional analysis, 2class model,
classvarying slopes for mothed and homeres, classvarying factor covariance matrix,
classvarying residual covariance matrix

penn6.inp 
lsay.dat 
penn6.std 
EXAMPLE 1: LSAY example, page 25 conditional analysis, 2class model,
classvarying slopes for mothed and homeres, classvarying factor covariance matrix,
classvarying residual covariance matrix, c on mothed and homeres

penn7.inp 
lsay.dat 
penn7.std 
EXAMPLE 2 and 5: NLSY Heavy Drinking example, pages 2527 and 3032.

penn8.inp 
nlsy64.dat 
penn8.std 
EXAMPLE 3: Analysis of reading skills development: confirmatory
analysis of growth curve shapes.

Not ready yet. 
EXAMPLE 4: Piecewise growth modeling with individuallyvarying transition points,
simulated data, second replication.

penn9.inp 
wise102.dat 
penn9.std 
Back to the top
Type of Analysis 
Input file 
Data file 
View output 

Muthén, B. (2001). Latent variable mixture modeling.
In G. A. Marcoulides & R. E. Schumacker (eds.), New Developments and Techniques
in Structural Equation Modeling (pp. 133). Lawrence Erlbaum Associates. (#86)
Download the corresponding set of examples.
The data files newran.dat and toca.dat are not available for download.

Section 4: Confirmatory latent class analysis of NLSY ASB items with
several latent class variables

app5.inp 
asb.dat 
app5.std 
Latent class growth analysis of college drinking data
with 3 trend classes for AUD combined with 3 classes for TD.

app6.inp 
raw5ww12.dat 
app6.std 
Growth mixture modeling of reading data.

app7.inp 
newran.dat 
app7.std 
Growth mixture modeling for reading with a covariate predicting
class membership.

app8.inp 
newran.dat 
app8.std 
Growth mixture modeling of aggression data.

app9.inp 
toca.dat 
app9.std 
Growth mixture modeling for aggression with a distal outcome predicted
by class membership.

app10.inp 
toca.dat 
app10.std 
Back to the top
Type of Analysis 
Input file 
Data file 
View output 

Muthén, B. & Masyn, K. (2001). Discretetime survival mixture analysis. (#92)
Download the corresponding set of examples.
The data file ggmmfull.dat is not available for download.

Recidivism analysis: Singleclass model using nonproportionality

app12.inp 
recid.dat 
app12.std 
Recidivism analysis: Singleclass model using proportionality

app13.inp 
recid.dat 
app13.std 
Recidivism analysis: Singleclass model using all covariates and proportionality

app14.inp 
recid.dat 
app14.std 
Recidivism analysis: Singleclass model using all covariates, proportionality, and
constant hazard

app15.inp 
recid.dat 
app15.std 
Recidivism analysis: Twoclass model using longterm survivors

app16.inp 
recid.dat 
app16.std 
School removal analysis: 3class growth mixture model combined with survival

app17.inp 
ggmmfull.dat 
app17.std 
School removal analysis: 3class growth mixture model combined with 2class
survival (5 classes)

app18.inp 
ggmmfull.dat 
app18.std 
Back to the top
Type of Analysis 
Input file 
Data file 
View output 

Muthén, B., Brown, C.H., Masyn, K., Jo, B., Khoo, S.T., Yang, C.C.,
Wang, C.P., Kellam, S., Carlin, J., & Liao, J. (2000). General growth mixture
modeling for randomized preventive interventions. Accepted for publication in
Biostatistics. (#87)
Download the corresponding set of examples.
The data file toca.dat is not available for download.

Growth mixture modeling for aggression allowing treatment effects to vary
across latent trajectory classes.

app11.inp 
toca.dat 
app11.std 
Back to the top
Type of Analysis 
Input file 
Data file 
View output 

Muthén, B. & Muthén, L. (2000). Integrating personcentered
and variablecentered analyses: Growth mixture modeling with latent
trajectory classes. Alcoholism: Clinical and Experimental Research, 24,
882891. (#85)
Download the corresponding set of examples.

EXAMPLE 1: Latent class analysis of the 17 NLSY ASB items,
no covariates (4 classes)

app1.inp 
asb.dat 
app1.std 
EXAMPLE 1: Latent class analysis of 9 selected NLSY ASB items,
3 covariates (4 classes)

app2.inp 
asb.dat 
app2.std 
EXAMPLE 2 and 3: Growth mixture modeling of NLSY
cohort 64 with covariates centered at 25: fourclass
model of heavy drinking with classes predicting alcohol dependence

app3.inp 
big.dat 
app3.std 
EXAMPLE 4: GGMM of NLSY relating 4 heavy drinking classes to
4 antisocial classes (16class run)

app4.inp 
asbhd.dat 
app4.std 
Back to the top
Back to index of Examples
