R: Моделирование скрытого структурного уравнения, добавление переменной размерной группы - PullRequest
0 голосов
/ 25 февраля 2019

Я строю модель скрытого структурного уравнения в лаване с одной скрытой переменной (Cognition), измеренной в два раза.Теперь я хочу добавить размерную групповую переменную, которая в основном является переменной от шкалы Ликерта (1 = отрицательный к 7 = положительный).Предполагается, что переменная просто влияет на показатель скрытого изменения (dextra1).Если бы переменная была категориальной, как пол, я бы просто построил модель для нескольких групп, но в этом случае я не знаю, что делать.Где бы я добавил размерную переменную, чтобы повлиять на показатель скрытого изменения (dextra1)?

Ниже приведен пример из OSF, где сначала моделируются, а затем подгоняются первые данные.

#####  Simulate data for a multiple indicator Univariate Latent Change Score model #### 
Fix sample size samplesize<-500 Simulate data for a Univariate Latent Change Score model. 
MILCS_simulate<-'

####    The following two lines specify the measurement model for multiple indicators (X1-X3) 
####    measured on two occasions (T1-T2)
COG_T1=~.8*T1X1+.9*T1X2+.7*T1X3   # This specifies the measurement model for COG_T1 
COG_T2=~.8*T2X1+.9*T2X2+.7*T2X3   # This specifies the measurement model for COG_T2 

#####     The following lines specify the core assumptions of the LCS 
#####     and should not generally be modified

COG_T2 ~ 1*COG_T1           # Fixed regression of COG_T2 on COG_T1
dCOG1 =~ 1*COG_T2           # Fixed regression of dCOG1 on COG_T2
COG_T2 ~ 0*1                # This line constrains the intercept of COG_T2 to 0
COG_T2 ~~ 0*COG_T2          # This fixes the variance of the COG_T2 to 0  

T1X1~0*1                  # This fixes the intercept of X1 to 0
T1X2~1*1                  # This fixes the intercept of X2 to 1
T1X3~.5*1                 # This fixes the intercept of X3 to 0.5 
T2X1~0*1                  # This fixes the intercept of X1 to 0
T2X2~1*1                  # This fixes the intercept of X2 to 1
T2X3~.5*1                 # This fixes the intercept of X3 to 0.5

###### The following five parameters will be estimated in the model. 
###### Values can be modified manually to examine the effect on the model

dCOG1 ~ 10*1            # This fixes the intercept of the change score to 10 
COG_T1 ~ 50*1           # This fixes the intercept of COG_T1 to 50. 
dCOG1 ~~ 5*dCOG1        # This fixes the variance of the change scores to 5. 
COG_T1 ~~ 8*COG_T1      # This fixes the variance of the COG_T1 to 8. 
dCOG1~-0.1*COG_T1       # This fixes the self-feedback parameter to -0.1. 
'



#Simulate data
set.seed(1234)
simdatMILCS<-simulateData(MILCS_simulate,sample.nobs =    samplesize,meanstructure = T) #Simulate data
colMeans(simdatMILCS) #sanity check the means
write.csv(simdatMILCS,'2_simdatMILCS.csv')

#Fit the multiple indicator Univariate Latent Change Score model to     simulated data MILCS<-'
COG_T1=~1*T1X1+T1X2+T1X3                           # This specifies the   measurement model for COG_T1 
COG_T2=~1*T2X1+equal("COG_T1=~T1X2")*T2X2+equal("COG_T1=~T1X3")*T2X3   #  This specifies the measurement model for COG_T2 with the equality constrained factor loadings

COG_T2 ~ 1*COG_T1     # Fixed regression of COG_T2 on COG_T1
dCOG1 =~ 1*COG_T2     # Fixed regression of dCOG1 on COG_T2
COG_T2 ~ 0*1          # This line constrains the intercept of COG_T2 to 0
COG_T2 ~~ 0*COG_T2    # This fixes the variance of the COG_T2 to 0 

dCOG1 ~ 1             # This estimates the intercept of the change score 
COG_T1 ~  1           # This estimates the intercept of COG_T1 
dCOG1 ~~  dCOG1       # This estimates the variance of the change scores 
COG_T1 ~~   COG_T1    # This estimates the variance of the COG_T1 
dCOG1~COG_T1          # This estimates the self-feedback parameter


T1X1~~T2X1   # This allows residual covariance on indicator X1 across T1 and T2
T1X2~~T2X2   # This allows residual covariance on indicator X2 across T1 and T2
T1X3~~T2X3   # This allows residual covariance on indicator X3 across T1 and T2

T1X1~~T1X1   # This allows residual variance on indicator X1 
T1X2~~T1X2   # This allows residual variance on indicator X2
T1X3~~T1X3   # This allows residual variance on indicator X3

T2X1~~equal("T1X1~~T1X1")*T2X1  # This allows residual variance on indicator X1 at T2
T2X2~~equal("T1X2~~T1X2")*T2X2  # This allows residual variance on indicator X2 at T2
T2X3~~equal("T1X3~~T1X3")*T2X3  # This allows residual variance on indicator X3 at T2

T1X1~0*1                 # This constrains the intercept of X1 to 0 at T1
T1X2~1                   # This estimates the intercept of X2 at T1
T1X3~1                   # This estimates the intercept of X3 at T1
T2X1~0*1                 # This constrains the intercept of X1 to 0 at T2
T2X2~equal("T1X2~1")*1   # This estimates the intercept of X2 at T2
T2X3~equal("T1X3~1")*1   # This estimates the intercept of X3 at T2
'
...