![Page 1: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/1.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
cfa1: Confirmatory Factor Analysiswith a Single Factor
Stas Kolenikov
Department of StatisticsUniversity of Missouri-Columbia
NASUG, Boston, MA, July 24, 2006
![Page 2: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/2.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Outline
1 Factor analysis
2 Implementation
3 Demonstration
4 Extensions
![Page 3: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/3.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Factor analysisIf one has p variables y1, . . . , yp, are there q < p factorsexplaining most of the variability in y ’s?• Exploratory factor analysis: find (simple) covariance
structure in the data; a standard multivariate technique— see [MV] factor
• Confirmatory factor analysis: upon having formulated atheoretical model, see if it fits the data; estimate theparameters and assess goodness of fit. Simplest ofstructural equation models (SEM)
• Principal components analysis is neither of the above,but closer to EFA in spirit
![Page 4: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/4.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Factor analysisIf one has p variables y1, . . . , yp, are there q < p factorsexplaining most of the variability in y ’s?• Exploratory factor analysis: find (simple) covariance
structure in the data; a standard multivariate technique— see [MV] factor
• Confirmatory factor analysis: upon having formulated atheoretical model, see if it fits the data; estimate theparameters and assess goodness of fit. Simplest ofstructural equation models (SEM)
• Principal components analysis is neither of the above,but closer to EFA in spirit
![Page 5: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/5.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Factor analysisIf one has p variables y1, . . . , yp, are there q < p factorsexplaining most of the variability in y ’s?• Exploratory factor analysis: find (simple) covariance
structure in the data; a standard multivariate technique— see [MV] factor
• Confirmatory factor analysis: upon having formulated atheoretical model, see if it fits the data; estimate theparameters and assess goodness of fit. Simplest ofstructural equation models (SEM)
• Principal components analysis is neither of the above,but closer to EFA in spirit
![Page 6: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/6.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Factor analysisIf one has p variables y1, . . . , yp, are there q < p factorsexplaining most of the variability in y ’s?• Exploratory factor analysis: find (simple) covariance
structure in the data; a standard multivariate technique— see [MV] factor
• Confirmatory factor analysis: upon having formulated atheoretical model, see if it fits the data; estimate theparameters and assess goodness of fit. Simplest ofstructural equation models (SEM)
• Principal components analysis is neither of the above,but closer to EFA in spirit
![Page 7: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/7.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Path diagramsA typical CFA model looks like. . .
y1 y2 y3 y4
ξ1
δ1 δ2 δ3 δ4
〈1〉
10.8 0.8
1.2
〈0.4〉 〈0.5〉 〈0.6〉 〈1.5〉
.
1
![Page 8: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/8.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Equation notation. . . which is the same as saying
ξ1 is unobserved, V[ξ1] = 1 = φ
y1 = λ1ξ1 + δ1, V[δ1] = 0.4 = θ1, λ1 = 1,
y2 = λ2ξ1 + δ2, V[δ2] = 0.5 = θ2, λ2 = 0.8,
y3 = λ3ξ1 + δ3, V[δ3] = 0.6 = θ3, λ3 = 0.8,
y4 = λ4ξ1 + δ3, V[δ4] = 1.5 = θ4, λ4 = 1.2
![Page 9: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/9.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Likelihood formulation
y = Λξ1 + δ,
Cov[y ] = ΛφΛ′ + Θ = Σ(θ),
ln L = −np2
ln(2π)− n2
ln |Σ| − n − 12
tr SΣ−1(θ)
where S is the sample covariance matrix
![Page 10: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/10.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Likelihood formulation
y = Λξ1 + δ,
Cov[y ] = ΛφΛ′ + Θ = Σ(θ),
ln L = −np2
ln(2π)− n2
ln |Σ| − n − 12
tr SΣ−1(θ)
where S is the sample covariance matrix
![Page 11: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/11.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Likelihood formulation
y = Λξ1 + δ,
Cov[y ] = ΛφΛ′ + Θ = Σ(θ),
ln L = −np2
ln(2π)− n2
ln |Σ| − n − 12
tr SΣ−1(θ)
where S is the sample covariance matrix
![Page 12: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/12.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Identification conditionsNot all parameters are necessarily estimable. . .• Number of parameters ≤ p(p + 1)/2• E ξ1 is not identified, assumed zero• Only λkφ1/2, or ratios λk/λj , are identified
• Set φ = 1• Set one of λk = 1
![Page 13: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/13.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Identification conditionsNot all parameters are necessarily estimable. . .• Number of parameters ≤ p(p + 1)/2• E ξ1 is not identified, assumed zero• Only λkφ1/2, or ratios λk/λj , are identified
• Set φ = 1• Set one of λk = 1
![Page 14: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/14.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Identification conditionsNot all parameters are necessarily estimable. . .• Number of parameters ≤ p(p + 1)/2• E ξ1 is not identified, assumed zero• Only λkφ1/2, or ratios λk/λj , are identified
• Set φ = 1• Set one of λk = 1
![Page 15: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/15.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Stata implementation• Stata’s ml model lf structure• Identification: by the first indicator, or by φ = 1;
implemented as constraints supported by ml
• Improper solutions workarounds: what if θk ≤ 0?• Goodness of fit tests• Corrections for multivariate kurtosis traditional for SEM
literature (Satorra-Bentler standard errors and χ2)
![Page 16: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/16.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Stata implementation• Stata’s ml model lf structure• Identification: by the first indicator, or by φ = 1;
implemented as constraints supported by ml
• Improper solutions workarounds: what if θk ≤ 0?• Goodness of fit tests• Corrections for multivariate kurtosis traditional for SEM
literature (Satorra-Bentler standard errors and χ2)
![Page 17: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/17.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Stata implementation• Stata’s ml model lf structure• Identification: by the first indicator, or by φ = 1;
implemented as constraints supported by ml
• Improper solutions workarounds: what if θk ≤ 0?• Goodness of fit tests• Corrections for multivariate kurtosis traditional for SEM
literature (Satorra-Bentler standard errors and χ2)
![Page 18: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/18.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Stata implementation• Stata’s ml model lf structure• Identification: by the first indicator, or by φ = 1;
implemented as constraints supported by ml
• Improper solutions workarounds: what if θk ≤ 0?• Goodness of fit tests• Corrections for multivariate kurtosis traditional for SEM
literature (Satorra-Bentler standard errors and χ2)
![Page 19: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/19.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Stata implementation• Stata’s ml model lf structure• Identification: by the first indicator, or by φ = 1;
implemented as constraints supported by ml
• Improper solutions workarounds: what if θk ≤ 0?• Goodness of fit tests• Corrections for multivariate kurtosis traditional for SEM
literature (Satorra-Bentler standard errors and χ2)
![Page 20: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/20.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Mata usage• Normal likelihood, observation by observation; a lot ofst view’s and Cholesky decompositions. Earlier versionsused mkmat. . . that was a disaster!
• Satorra-Bentler corrections:
acov(θ) = (n − 1)−1(∆′Vn∆)−1
∆′VnΓnVn∆(∆′Vn∆
)−1
∆ =∂σ
∂θ
∣∣∣bθ, Vn = 1/2 D′(A−1n ⊗ A−1
n )D,
Anp−→ Σ, vec Σ = D vech Σ
Γn =1
n − 1
∑i
(bi − b)(bi − b)′
bi = (yi − y)(yi − y)′
• Mata functions for D (vec, invvech), ∆ (analyticderivatives, but with lots of matrix operations), b (st view)
![Page 21: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/21.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Mata usage• Normal likelihood, observation by observation; a lot ofst view’s and Cholesky decompositions. Earlier versionsused mkmat. . . that was a disaster!
• Satorra-Bentler corrections:
acov(θ) = (n − 1)−1(∆′Vn∆)−1
∆′VnΓnVn∆(∆′Vn∆
)−1
∆ =∂σ
∂θ
∣∣∣bθ, Vn = 1/2 D′(A−1n ⊗ A−1
n )D,
Anp−→ Σ, vec Σ = D vech Σ
Γn =1
n − 1
∑i
(bi − b)(bi − b)′
bi = (yi − y)(yi − y)′
• Mata functions for D (vec, invvech), ∆ (analyticderivatives, but with lots of matrix operations), b (st view)
![Page 22: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/22.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Mata usage• Normal likelihood, observation by observation; a lot ofst view’s and Cholesky decompositions. Earlier versionsused mkmat. . . that was a disaster!
• Satorra-Bentler corrections:
acov(θ) = (n − 1)−1(∆′Vn∆)−1
∆′VnΓnVn∆(∆′Vn∆
)−1
∆ =∂σ
∂θ
∣∣∣bθ, Vn = 1/2 D′(A−1n ⊗ A−1
n )D,
Anp−→ Σ, vec Σ = D vech Σ
Γn =1
n − 1
∑i
(bi − b)(bi − b)′
bi = (yi − y)(yi − y)′
• Mata functions for D (vec, invvech), ∆ (analyticderivatives, but with lots of matrix operations), b (st view)
![Page 23: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/23.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Syntaxcfa1 varlist [if ...] [in ...]
[[pweight=weight]],unitvar free posvarconstraint(numlist)cluster(varname) svyrobust vce(oim|opg|robust|sbentler)from(starting values) level(#)ml options
![Page 24: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/24.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
DemonstrationDo something!
![Page 25: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/25.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Broader CFA models?
y1 y2 y3
ξ1
y4 y5 y6
ξ2
δ1 δ2 δ3 δ4 δ5 δ6
〈φ11〉 〈φ22〉φ12
1λ2
λ3 1λ5
λ6
〈θ1〉 〈θ2〉 〈θ3〉 〈θ4〉 〈θ5〉 〈θ6〉
.
1
cfa (xi1: y1 y2 y3) (xi2: y4 y5 y6)
![Page 26: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/26.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
General structural equationmodels?
x1 x2 x3
ξ1
δ1 δ2 δ3
η1
ζ1
y1 ε1 〈θ4〉
y2 ε2 〈θ5〉
y3 ε3 〈θ6〉
z1〈φ11〉〈φ22〉φ12
1λ2
λ3
β11
β12
〈θ1〉 〈θ2〉 〈θ3〉 〈σ1〉
〈θ4〉
.
1
sem (xi1: x1 x2 x3) (eta1 = .xi1 z1: y1 y2 y3)
Parsing structural equation models is generally a nightmare. . .
![Page 27: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/27.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
GLLAMMThe minimal syntax for a CFA example for gllamm package
g long id = nreshape long y, i(id) j(k)g byte one = 1tab k, gen(d)eq main: d1 d2 d3 d4gllamm y d*, eq(main) i(id) nocons s(main)
![Page 28: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/28.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
MplusThe minimal syntax for Mplus SEM package (text file inputand output)
Title: Simple CFA exampleData: File = cfa-example.txt;
Type = individual;Variable:
Names = y1 y2 y3 y4;Analysis:
Type = general;Model:
xi by y1 y2 y3 y4;
![Page 29: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/29.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
SAS PROC CALISThe minimal syntax for SAS PROC CALIS
proc calis data = cfa-example;lineqs
y1 = f1 + e1,y2 = l2 f1 + e2,y3 = l3 f1 + e3,y4 = l4 f1 + e4;
stde1 = theta1,e2 = theta2,e3 = theta3,e4 = theta4,f1 = phi;
run;
Rigid variable names (F for factors/latent variables, E and Dfor errors and disturbances).
![Page 30: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/30.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
LISRELTI PRELIS processing of CFA exampleDA NI = 4 NO = 200 MI = -999LA
y1 y2 y3 y4RA = cfa-example.txtOU RA = cfa-example.psf
TI Estimation of CFA exampleDA MA = CM NI = 4 NO = 200RA = cfa-example.psfLK xiMO NK = 1 NX = 4
LX = FU, FRTD = DI, FRFI LX(1,1) VA 1 LX(1,1)
PDOU ME = ML EF
![Page 31: cfa1: Confirmatory Factor Analysis with a Single Factor Simple CFA Models Stas Kolenikov U of Missouri Factor analysis Implementation Demonstration Extensions cfa1: Confirmatory Factor](https://reader031.vdocument.in/reader031/viewer/2022030506/5ab55ceb7f8b9a1a048cbf98/html5/thumbnails/31.jpg)
cfa1: SimpleCFA Models
StasKolenikov
U of Missouri
Factoranalysis
Implementation
Demonstration
Extensions
Download infonet from ///http://www.missouri.edu/˜kolenikovs/statanet install cfa1
findit cfa1