Académique Documents
Professionnel Documents
Culture Documents
Overview
Overview of Structural Equation Models (SEM) Introduction to AMOS
User Interface
AMOS Graphics Predictors of Condom Use using latent variables
T-test
ANOVA
Bivariate Correlation
Multiple Regression
Path Analysis
Factor Analysis
Error
Observed Variable
.15 : Loading
Latent Variable
Respondent Sex
SEX1
Impulsive
FRBEHB1
Legend
Observed Variables .15
SXPYRC1
Loadings
SEX1
Impulsive
Independent
FRBEHB1
Legend
Observed Variables .15
Dependent
Latent Variables
SXPYRC1
Loadings
SEX1
Impulsive
efr1
FRBEHB1
ISSUEB1
eiss
Legend
Observed Variables .15 Latent Variables
SXPYRC1
eSXYRC1
Loadings
SEX1
Impulsive
efr1
FRBEHB1
ISSUEB1
eiss
Legend
Observed Variables .15 Latent Variables
SXPYRC1
eSXYRC1
Loadings
.53
.49
.69
.67 -.19
-.06 -.10
Impulsive
-.15
efr1
.03
FRBEHB1 .38 .11
Legend
Observed Variables .15 Latent Variables
SXPYRC1 .15
eSXYRC1
Loadings
SEM Assumptions
A Reasonable Sample Size
a good rule of thumb is 15 cases per predictor in a standard ordinary least squares multiple regression analysis.
[ Applied Multivariate Statistics for the Social Sciences, by James Stevens]
researchers may go as low as five cases per parameter estimate in SEM analyses, but only if the data are perfectly well-behaved [Bentler and Chou (1987)] Usually 5 cases per parameter is equivalent to 15 measured variables.
MAR
MNAR
SEM Software
Several different packages exist
Introduction to
AMOS
AMOS Advantages
Easy to use for visual SEM ( Structural Equation Modeling). Easy to modify, view the model Publication quality graphics
AMOS Components
AMOS Graphics
AMOS Basic
Access
dBase 3 5 Microsft Excel 3, 4, 5, and 97
SPSS *.sav files, versions 7.0.2 through 13.0 (both raw data and matrix formats)
DATASET: AMOS_data_valid_condom.sav
Drawing in AMOS
In Amos Graphics, a model can be specified by drawing a diagram on the 1. To draw an observed variable, click screen
"Diagram" on the top menu, and click "Draw Observed." Move the cursor to the place where you want to place an observed variable and click your mouse. Drag the box in order to adjust the size of the box. You can also use in the tool box to draw observed variables.
2. Unobserved variables can be drawn similarly. Click "Diagram" and "Draw Unobserved." Unobserved variables are shown as circles. You may also use in the toolbox to draw unobserved variables.
Drawing in AMOS
To draw a path, Click Diagram on the top menu and click Draw Path. Instead of using the top menu, you may use the Tool Box buttons to draw arrows ( and ).
Drawing in AMOS
To draw Error Term to the observed and unobserved variables. Use Unique Variable button in the Tool Box. Click and then click a box or a circle to which you want to add errors or a unique variables.(When you use "Unique
Variable" button, the path coefficient will be automatically constrained to 1.)
Drawing in AMOS
Let us draw:
OR
Click on the Text tab and enter the name of the variable in the Variable name field:
FRBEHB1
1
ISSUEB1
1
efr1
eiss
SXPYRC1
1
eSXPYRC1
There is also an Analysis Properties icon you can click on the toolbar. Either way, the Output tab gives you the following options:
Results
When AMOS has completed the calculations, you have two options for viewing the output:
For text output, click the View Text ( or F10) icon on the toolbar.
Here is a portion of the text output for this problem:
SEX1
<-->
IDM
-.02
.01
-2.48
.01
Chose to view either unstandardized or (if you selected this option) standardized estimates by click one or the other in the Parameter Formats panel next to your drawing area:
Standardized
-.08
IDM
-.57 -.38 -.28
SEX1
IDM
-.19 -.10
SEX1
.30
-.11 .02
.12 .06
FRBEHB1
1.94 1
ISSUEB1
1 .49 .16 1.36
FRBEHB1
ISSUEB1
efr1
eiss
efr1
.38
.11
eiss
.15
SXPYRC1
eSXPYRC1
eSXPYRC1
Parameter increase
eiss
<-->
efr1
9.909
.171
Chi-square decrease
IDM
-.38 5.58 0, 1.94 -.57 -.28
SEX1
.30 3.74 ISSUEB1 .16 .17 3.08 SXPYRC1
FRBEHB1 .49
1 efr1
0, 1.36 eiss
0, 2.80
eSXPYRC1
Recalculate the previous example with data AMOS_data.sav with some missing values
IDM
-.18 -.10 .02 -.09
SEX1
.12 .05
FRBEHB1
ISSUEB1
efr1
.37
.08
eiss
.14
SXPYRC1
eSXPYRC1
1
IDME1R
1
IDMJ1R
IDMA1R IDMC1R 1
idm1
0,
e2
.26
e3
.47
e4
.47
Multiple Correlation
IDMA1R
.55
IDMC1R
.51
IDME1R
.69 .69
IDMJ1R
idm1
Factor Loadings
Confirmatory Factor Analysis with Impulsive Decision Making scale: the error variances are the same
Need to give names to the error variances, by double clicking on the error variance. The Object properties will appear, click on the Parameter and type the name for the error variance( e1, e2...) in the Variance box.
0, e2
e2 1
0, e3
e3 1 IDME1R 0,
0, e4
e4 1 IDMJ1R
IDMA1R IDMC1R 1
idm1
Confirmatory Factor Analysis with Impulsive Decision Making scale: error variances are the same
Click MODEL FIT , then Manage Models In the Manage Models window, click on New. In the Parameter Constraints segment of the window type e1=e2=e3=e4
e1
1 2.18
e2
1 2.44
e3
1 2.24
e4
1 2.28
e1
1 2.18
e2
1 2.44
e3
1 2.24
e4
1 2.28
IDMA1R
IDMC1R
1.15
IDME1R
1.50 0, .19
IDMJ1R
IDMA1R
IDMC1R
1.03
IDME1R
1.48 0, .19
IDMJ1R
1.00
1.36
1.00
1.40
idm1
idm1
Confirmatory Factor Analysis with Impulsive Decision Making scale: error variances are the same
Model2( errors the same) Chi-square = 56.826, df=5, p=0.000
Chi-squaredifference=56.826-11.621=45.205 df=5-3=2
Confirmatory Factor Analysis with Impulsive Decision Making scale: error variances are the same
Nested Model Comparisons
Assuming model Error are free to be correct:
NFI Delta-1
.026
DF
CMIN
3 45.205 .000
For each group, specify the relevant data file name. For this example, choose the data_girls SPSS database for the girls' group;
Structural weights the same regression loadings between the latent var.
Structural intercepts the same intercepts for the latent variables Structural covariates the same variances/covariance for the latent var. Structural residuals the same disturbances Measurement residuals the same errors-THE MOST RESTRICTIVE
MODEL
0, .47 1 2.21
0, .62 1 2.41
0, .44 1 2.36
0, .39 1 2.40
Impulsive
-.62
4.35
Impulsive
-.64
-.28 2.72 4.12 -.38 3.06
FRBEHB1
0, 2.12 1
ISSUEB1
1 .40 .11 0, 1.50
FRBEHB1
0, 1.81 1
ISSUEB1
1 .62 0, 1.13
efr1
eiss
efr1
.26
eiss
3.63
2.16
SXPYRC1
1 0, 2.95
SXPYRC1
1 0, 2.56
eSXPYRC1
eSXPYRC1
Boys
UNCONSTRAINED MODEL
Girls
0, .63 1 2.41
0, .43 1 2.36
0, .40 1 2.40
eidm1
1 2.21
eidm2
eidm3
eidm4
eidm1
1 2.33
eidm2
1 2.60
eidm3
1 2.39
eidm4
1 2.43
IDMA1R
IDMC1R
IDME1R
1.57 1.08
IDMJ1R
1.42
1.00
1.00
Impulsive
0, .18
Impulsive
0, .16
-.45
-.50
-.45
-.50
4.35
2.72
4.12
3.06
FRBEHB1
1
ISSUEB1
FRBEHB1
1 .40 .11 3.62 0, 1.51
ISSUEB1
1 0, 1.12
efr1
0, 2.14
eiss
efr1
0, 1.81
.62
.26
eiss
SXPYRC1
1 0, 2.95
2.16
SXPYRC1
1
eSXPYRC1
Boys
Measurement weights
Girls
0, 2.56
eSXPYRC1
FIT of the Measurement Weights model is not significantly worse than Unconstrained
SEX1
FRBEHB1 ISSUEB1 SXPYRC1
1.000
1.000 1.000 2.000
2.000
6.000 4.000 7.000
.182
-.430 -.431 -.937
2.222
-5.245 -5.259 -11.436
-1.967
-.778 -1.387 -.715
-11.997
-4.748 -8.462 -4.360 -6.149
Multivariate
-3.443
Critical ratio of +/- 2 for skewness and kurtosis statistical significance of NON-NORMALLITY Multivariate kurtosis >10 Severe Non-normality
Stine bootstrap
BOLLEN_STINE BOOTSTRAP performed only for dataset without any missing values
(see handout #6: amos_data_valid_condom.sav)
The model fits better than expected in 496 samples out of 500 samples (500-496)/500=0.010 So, p-value=0.01 < 0.05 - Model does not fit to the data very well
Relationship between
Bootstrap estimates
is 0.487, with S.E.=0.04, Almost the same estimate produced by Bootstrap, 0.488 with S.e=0.042
Hope to see similar results for the estimates NOTE: BOOTSTRAP option works ONLY with COMPLETE data
Thank You!
See you in a week!