Download presentation
Presentation is loading. Please wait.
1
Modelos para datos longitudinales
2
Data example “We have four measures of hability, for a sample of 204 children, at ages 6,7,9 and 11 years (Osbourne and Suddick, 1972)” (see Dunn et al. p. 100) The Mean, Standard deviation, Correlation matrix: /STANDARD DEVIATIONS /MEANS /MATRIX 1 .809 1 /LMtest /END
3
Single-factor model
4
Single-factor Model * * * * V1 V2 V3 V4 * * * * F1
5
Autoregressive model
6
Autoregressive Model * * * * V1 V2 * V4 V3 * *
7
EQS code: /TITLE longitudinal model (Dunn et al. p. 108)
/SPECIFICATIONS CAS=204 ; VAR=4; ME=ML; ANAL = COV; /LABELS V1 = ABIL6; V2 = ABIL7; V3 = ABIL9; V4 = ABIL11; /EQUATIONS V2 = 1.0*V1+ E2; V3 = 1.0*V2 + E3 ; V4 = 1.0*V3 + E4; /VARIANCES V1 = 36*; E2 TO E4 = 1.0*; /PRINT EFFECT = YES; /STANDARD DEVIATIONS /MEANS /MATRIX 1 .809 1 /LMtest /END
8
Estimates
9
Simplex model
10
Simplex Model * * * * V4 V1 V2 V3 * * F4 F3 F1 * F2 * * * *
11
EQS imput for simplex model
12
Estimates, s.e., and chi2 g.o.f test
13
Restricting equality of effects across time
14
Exercise: using the cov. Matrix below, fit a simplex model
15
Dynamic factor model (Dunn et al. P. 140)
Judd and Milburn (1980) used a latent variable analysis to examine attitudes in a nation-wide sample of individuals who were surveyed on three occasions, in 1972, 1974 and 1976. (Dunn et al. P. 140)
16
Part of the data involved recording attitudes on three topics: busing- a policy designed to achieve school integration; criminals - the protection for the legal rights of those accused of crimes; jobs- whether government should guarantee jobs and standard of living. The sample consisted of 143 individuals each with four years of college education, and 203 individuals who had no college education .
17
college education n = 143. 1972. 1974. 1976. B. C. J. B. C. J. B. C
college education n = B C J B C J B C J B 1 C J B C J B C J SD B Busing C Criminals J Jobs
18
Path diagram for effects across time
* * * T1 * T3 T2 * V1 V2 V3 V4 V5 V6 V7 V8 V9
19
EQS code /TITLE liberalism-conservatism exmple
factor loadings and latent variable regression coefficients constrained to be equal across groups group 1 - four years of college education /SPECIFICATIONS GROUPS = 1; CAS=143; VAR=9; MATRIX = CORR; ANALYSIS = COV; /EQUATIONS V1 = 1*F1 + E1; ! F1 is liberalism in 1972 V2 = 1*F E2; V3 = 1*F E3; V4 = F2 + E4; !F2 is liberalism in 1974 !scale of F2 set to that of V4 !scale can not be set in /VARIANCE ! since F2 appears later as a depend. var V5 = 1*F2 + E5; V6 = 1*F2 + E6; V7 = F3 + E7; !F3 is liberalism in 1976, again scale .. V8 = 1*F3 + E8; V9 = 1*F3 + E9; F2 = 1*F1 + D1; !Regression of 1974 kuberakusn ib 1972 F3 = 1*F2 + D2; !Regression of 1976 liberalism on 1974 /VARIANCES F1 = 1; E1 TO E9 = 1*; D1 TO D2 = .2*; /COVARIANCES E1,E4 = .5*; E1,E7 = .5*; E2,E5 = .5*; E2,E8 = .5*; E3,E6 = .5*; E3,E9 = .5*; E4,E7 = .5*; E5,E8 =.5*; E6,E9 = .5*; /STANDARD DEVIATIONS /MATRIX 1 .43 1 /END
20
Estimated Time effects
F2 =F2 = *F D1 .102 9.106 F3 =F3 = *F D2 .085 11.800 CHI-SQUARE = BASED ON DEGREES OF FREEDOM PROBABILITY VALUE FOR THE CHI-SQUARE STATISTIC IS
21
V1 =V1 = *F E1 .113 9.897 V2 =V2 = *F E2 .120 6.999 V3 =V3 = *F E3 .115 8.730 V4 =V4 = F E4 V5 =V5 = *F E5 .131 5.922 V6 =V6 = *F E6 .147 6.174 V7 =V7 = F E7 V8 =V8 = *F E8 .123 4.496 V9 =V9 = *F E9 .142 5.890
22
Random walk model
23
Random Walk Model * * * * V4 V1 V2 V3 1 1 1 1 F4 F3 F1 F2 * * * *
24
EQS code for random walk model
25
Estimates I F1 - F1 .806*I RESIDUAL COVARIANCE MATRIX (S-SIGMA) :
ABIL ABIL ABIL ABIL11 V V V V 4 ABIL6 V ABIL7 V ABIL9 V ABIL11 V CHI-SQUARE = BASED ON DEGREES OF FREEDOM PROBABILITY VALUE FOR THE CHI-SQUARE STATISTIC IS I F F *I I I I I I I I F F *I I I I I I F F *I I I I I I F F *I I I I I
26
Estimates of meas. Error
E1 -ABIL *I I .014 I I 9.376 I I I I E2 -ABIL *I I E3 -ABIL *I I E4 -ABIL *I I
27
Growth curve model
28
Growth curve model * * * * V1 V2 V3 V4 * 1 * 1 * D1 1 * D2 1 Slope F2
Intercept F1 * 1 *
29
growth curve model /TITLE
Dependence between ability scores at 6,7,9 and 11 Growth curve model of latent ability /SPECIFICATIONS CAS=204 ; VAR=4; ANALYSIS=MOMENT; MATRIX = CORR; ANAL = COV; /LABELS V1 = ABIL6; V2 = ABIL7; V3 = ABIL9; V4 = ABIL11; F1 = intercept; F2 = slope; /EQUATIONS V1 = F1 + E1; V2 = F1 + F E2; V3 = F1 + 3*F E3; V4 = F1 + 5*F2 + E4; F1 = 18*V999 + D1; F2 = 7*V999 + D2; /VARIANCES D1 = 25*; D2 = 1*; E1 TO E4 = 1.0*; /CONSTRAINTS (E1,E1 ) = (E2,E2) = (E3,E3) = (E4,E4); !/PRINT !EFFECT = YES; /STANDARD DEVIATIONS /MEANS /MATRIX 1 .809 1 /END
30
Moment Matrix RESIDUAL COVARIANCE/MEAN MATRIX (S-SIGMA) :
4 VARIABLES (SELECTED FROM 4 VARIABLES), BASED ON CASES. ABIL ABIL ABIL ABIL V999 V V V V V999 ABIL6 V ABIL7 V ABIL9 V ABIL11 V V999 V RESIDUAL COVARIANCE/MEAN MATRIX (S-SIGMA) : ABIL6 V ABIL7 V ABIL9 V ABIL11 V V999 V CHI-SQUARE = BASED ON DEGREES OF FREEDOM PROBABILITY VALUE FOR THE CHI-SQUARE STATISTIC IS LESS THAN 0.001
31
Estimates ABIL6 =V1 = F E1 ABIL7 =V2 = F F E2 ABIL9 =V3 = F *F E3 .069 31.739 ABIL11 =V4 = F *F E4 .119 30.755 INTERCEP=F1 = *V D1 .470 38.417 SLOPE =F2 = *V D2 .305 25.612
32
Estimates of variances
E D E1 -ABIL *I D1 -INTERCEP *I .625 I I I I I I E2 -ABIL *I D2 -SLOPE *I .625 I I I I E3 -ABIL *I I .625 I I I I E4 -ABIL *I I
33
Model with cov. Betw. F1 and F2
CHI-SQUARE = BASED ON DEGREES OF FREEDOM PROBABILITY VALUE FOR THE CHI-SQUARE STATISTIC IS COVARIANCES AMONG INDEPENDENT VARIABLES E D I D2 -SLOPE *I I D1 -INTERCEP I I I CORRELATIONS AMONG INDEPENDENT VARIABLES I D2 -SLOPE *I I D1 -INTERCEP I
34
/TITLE Dependence between ability scores at 6,7,9 and 11 Growth curve model of latent ability /SPECIFICATIONS CAS=204 ; VAR=4; ANALYSIS=MOMENT; MATRIX = CORR; ANAL = COV; /LABELS V1 = ABIL6; V2 = ABIL7; V3 = ABIL9; V4 = ABIL11; F1 = intercept; F2 = slope; /EQUATIONS V1 = F1 + E1; V2 = F1 + F E2; V3 = F1 + 3*F E3; V4 = F1 + 5*F2 + E4; F1 = 18*V999 + D1; F2 = 7*V999 + D2; /VARIANCES D1 = 25*; D2 = 1*; E1 TO E4 = 1.0*; /COVARIANCES D1,D2 = .4*; /CONSTRAINTS (E1,E1 ) = (E2,E2) = (E3,E3) = (E4,E4); !/PRINT !EFFECT = YES; /STANDARD DEVIATIONS /MEANS /MATRIX 1 .809 1 /END
36
Exercice: One reason why the ability data might not show uniform linear growth is that there are practice effects in the testing; in particular, the initial test might give relatively low scores in comparison to the later tests because it was new to the children. The addition of a direct link from V999 to V1 would allow for such an effect. Does the linear growth model fit better when allowing for such a practice effect ?.
37
CHI-SQUARE = 14.266 BASED ON 5 DEGREES OF FREEDOM
/EQUATIONS V1 = *V999 + F1 + E1; V2 = F1 + F E2; V3 = F1 + 3*F E3; V4 = F1 + 5*F2 + E4; F1 = 18*V999 + D1; F2 = 7*V999 + D2; MEASUREMENT EQUATIONS WITH STANDARD ERRORS AND TEST STATISTICS ABIL6 =V1 = F *V E1 1.852 -1.626 ABIL7 =V2 = F F E2 ABIL9 =V3 = F *F E3 .730 4.000 ABIL11 =V4 = F *F E4 1.624 3.262 CHI-SQUARE = BASED ON DEGREES OF FREEDOM PROBABILITY VALUE FOR THE CHI-SQUARE STATISTIC IS
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.