64
Latent Growth Curve Modeling In Latent Growth Curve Modeling In Mplus: Mplus: An Introduction and Practice An Introduction and Practice Examples Examples Part I Part I Edward D. Barker, Ph.D. Social, Genetic, and Developmental Psychiatry Centre Institute of Psychiatry, King’s College London

Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

  • Upload
    varian

  • View
    203

  • Download
    0

Embed Size (px)

DESCRIPTION

Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I. Edward D. Barker, Ph.D. Social, Genetic, and Developmental Psychiatry Centre Institute of Psychiatry, King’s College London. Bength & Linda Muth é n Mplus: http://www.statmodel.com/ Alan A. Acock - PowerPoint PPT Presentation

Citation preview

Page 1: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Latent Growth Curve Modeling In Mplus:Latent Growth Curve Modeling In Mplus:An Introduction and Practice ExamplesAn Introduction and Practice Examples

Part IPart I

Edward D. Barker, Ph.D.

Social, Genetic, and Developmental Psychiatry Centre Institute of Psychiatry, King’s College London

Page 2: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Acknowledgements

Bength & Linda Muthén Mplus: http://www.statmodel.com/

Alan A. Acock Department of HDFS

Oregon State University

Brigitte Wanner GRIP

University of Montréal

Page 3: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Outline

Introduction to Mplus Mplus & prog. language Preparing data Descriptive statistics

Basic growth Curve Model Basic Model and Assumption Mplus code Interpreting Output & Graphs

Quadratic terms Mplus program Interpreting Output & Graphs

Missing values in growth models Introduction Mplus code Output

Multiple group models At the same time As categorical predictors to

show differences in intercept and/or slope

Additional models There are many . . .

Page 4: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Introduction to Mplus

Page 5: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Input and output windows

Page 6: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Mplus Command Language (code, script, etc.)

Different commands divided into a series of sections TITLE

DATA (required)

VARIABLE (required)

DEFINE

ANALYSIS

MODEL

OUTPUT

SAVEDATA

MONTECARLO

Page 7: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Mplus Command Language (code, script, etc.)

TITLE: Everything after “Title:” is the title and the title ends when

“Data:” appears

DATA: Tells Mplus where to find the file containing the data.

“E:\Growth_Curves\ClassData.dat”

Without a specific path, Mplus will look in the same folder where the Mplus code is saved

Page 8: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Mplus Command Language (code, script, etc.)

VARIABLE: Series of subcommands that tell Mplus . . .

Names are names of variables (8 characters max; case sensitive in certain versions)

Missing are all (-99) ; tells Mplus user defined missing values

Use variables are names variables to use in the analysis. Useful if have larger data file for multiple purposes/analysis. IMPORTANT

ANALYSIS: Tells Mplus what type of analysis and estimator will be used

Type = basic ; (default)

Page 9: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Mplus Command Language (code, script, etc.)

MODEL: This contains the basic model statements

Y ON X ; ! regression

F1 BY var1@1 var2 var3 var4 ; ! Latent factors

var1 WITH var2 ; !correlation

OUTPUT: Lists specific statistical and graphical output wanted

Will get to this in the next section

Page 10: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Data and data preparation: SPSS to Mplus

Page 11: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Basic Analysis

Page 12: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Practice 1

Create Mplus data file from SPSS Write the translation file in SPSS

Check to make sure your data is correctly created

Conduct basic Mplus analysis Write the Mplus code

Page 13: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Outline

Introduction to Mplus Mplus & prog. language Preparing data Descriptive statistics

Basic growth Curve Model Basic Model and Assumption Mplus code Interpreting Output & Graphs

Quadratic terms Mplus program Interpreting Output & Graphs

Missing values in growth models Introduction Mplus code Output

Multiple group models At the same time As categorical predictors to

show differences in intercept and/or slope

Additional models There are many . . .

Page 14: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Basic Growth Curve Analysis

General latent variable framework Implemented in Mplus program Muthén and Muthén (1998-

2007)

Latent Growth Curve modeling / Structural Equation Modeling (SEM) is linked to Random Coefficient Growth Modeling / Multilevel modeling

Latent Growth Curve modeling (single population) is a “case“ of Growth Mixture Modeling (we cover this tomorrow)

Page 15: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Basic Growth Curve Analysis

Average growth within a population and its variation

Continuous latent variables (growth factors) capture individual differences in development Intercept (mean starting value)

Slope (rate of growth)

Quadratic term (leveling off, or coming down)

Page 16: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Basic Growth Curve Analysis

observed variables continuous censored binary ordinal count combinations

continuous latent variables measurement models (show an example later today)

Page 17: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Basic Growth Curve Analysis

Estimating a basic growth curve using Mplus is quite easy. In general, start simple, move to more complex

Page 18: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Basic Growth Curve Analysis

Intercept Slope

D12 D13 D14 D15 D16 D17

1.0 1.01.0

1.0 1.0 1.0

1.02.0 3.0 4.0

5.0

0.0

Page 19: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Mplus code for basic growth model

Page 20: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Selected growth curve output

Page 21: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Selected growth curve output

Page 22: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Selected growth curve output

Page 23: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Selected growth curve output

Page 24: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Selected growth curve output

Page 25: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Selected growth curve output

Page 26: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Selected growth curve output

Page 27: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Practice 2

Run basic growth curve model in Mplus Write Mplus code

Go through results and annotate the meaning of different parts of the results

Examine 2 graphs Individual observed values

Sample estimated means based on model

Page 28: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Outline

Introduction to Mplus Mplus & prog. language Preparing data Descriptive statistics

Basic growth Curve Model Basic Model and Assumption Mplus code Interpreting Output & Graphs

Quadratic terms Mplus program Interpreting Output & Graphs

Missing values in growth models Introduction Mplus code Output

Multiple group models At the same time As categorical predictors to

show differences in intercept and/or slope

Additional models There are many . . .

Page 29: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Growth Curve with a Quadratic Term

Intercept Slope

D12 D13 D14 D15 D16 D17

1.01.0 1.0

Quadratic

1.01.0

0.0 1.02.0 3.0 4.0

5.0

1.0

0.0

1.0 4.0 9.0

0.0

16.025.0

Page 30: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Mplus code for basic growth model with Quadratic Term

Page 31: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Selected output for quadratic model

Page 32: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Selected output for quadratic model

Page 33: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Selected output for quadratic model

Page 34: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Selected output for quadratic model

Page 35: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Practice 3

Run growth curve model with quradratic term Write Mplus code

Go through results and annotate the meaning of different parts of the results

Examine 2 graphs Estimated means based on model

Sample individual values

Page 36: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Outline

Introduction to Mplus Mplus & prog. language Preparing data Descriptive statistics

Basic growth Curve Model Basic Model and Assumption Mplus code Interpreting Output & Graphs

Quadratic terms Mplus program Interpreting Output & Graphs

Missing values in growth models Introduction Mplus code Output

Multiple group models At the same time As categorical predictors to

show differences in intercept and/or slope

Additional models There are many . . .

Page 37: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Missing values

Mplus has two ways of working with missing values full information maximum likelihood estimation with

missing values (FIML)

Multiple imputations.

1. Imputing multiple datasets

2. Estimating the model for each of these datasets

3. Then pooling the estimates and standard errors

Page 38: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Mplus code with missing data

Page 39: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Selected output for missing model

Page 40: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Selected output for missing model

Page 41: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Selected output for missing model

Page 42: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Selected output for missing model

Page 43: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Practice 4

Run growth curve model with missing analysis Write Mplus code

Go through results and annotate how the results change when using missing data analysis

Page 44: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Outline

Introduction to Mplus Mplus & prog. language Preparing data Descriptive statistics

Basic growth Curve Model Basic Model and Assumption Mplus code Interpreting Output & Graphs

Quadratic terms Mplus program Interpreting Output & Graphs

Missing values in growth models Introduction Mplus code Output

Multiple group models At the same time As categorical predictors to

show differences in intercept and/or slope

Additional models There are many . . .

Page 45: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Multiple group models

Gender Boys higher in delinquency

Several ways Compare models

Step 1: fit multiple model group and allow estimated parameters to vary

Step 2: constrain, at least intercept and slope

Page 46: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Multiple group models

Page 47: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Selected output: Multiple group models

Page 48: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Selected output: Multiple group models

Page 49: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Selected output: Multiple group models

Page 50: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Selected output: Multiple group models

Page 51: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Selected output: Multiple group models

Page 52: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Multiple group models: Constraints

Page 53: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Multiple group models: Constraints

Page 54: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Multiple group models: group as predictor

Page 55: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Group as predictor: Selected output

Page 56: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Practice 4

Practice A Run multiple groups with no restraints

Annotate output

Run multiple groups with restraints (intercept, slope) Annotate output

Practice B Add gender as predictor of intercept, slope, and

quadratic Annotate output

Page 57: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Other models

Here I am going to go through different models some of which you may end up using

Page 58: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Curran and Hussong (2003)

Conditional Linear Growth Curve: Covariate effectsConditional Linear Growth Curve: Covariate effects

Page 59: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Curran and Hussong (2003)

Parallel Conditional Linear Growth CurvesParallel Conditional Linear Growth Curves

Page 60: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Hancock, Kuo, and Lawrence (2001)

Second-order factors

First-order factors

Second-Order LGC ModelsSecond-Order LGC Models

Page 61: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Time-varying covariates

Combination of autoregressive cross-lagged model and LGCM

Difference scores (e.g., McArdle, 2001)

Two stage models (0-1; 1+) (see Mplus user’s guides)

ExtensionsExtensions

Page 62: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

Maximum likelihood with robust standard errrors (MLR ) violate normal distribution

Satorra-Benter scaled chi-square difference test See Mplus for scaling correction factor http://www.statmodel.com/chidiff.shtml

Other estimatorsOther estimators

Page 63: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

End Day 1

Page 64: Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part I

http://www2.chass.ncsu.edu/garson/pa765/statnote.htm

Change measured through random effects