Day 2: Common Fate Model

Back to schedule

---

Common Fate Model

library(tidyr)
library(dplyr)
#install.packages("lavaan")
library(lavaan)

acitelli_ind <- read.csv(file.choose(), header=TRUE)

Individual to Dyad struture

acitelli_dyd <- acitelli_ind %>% 
  mutate(gender = ifelse(gender == 1, "H", "W")) %>%
  gather(variable, value, self_pos:simhob) %>%
  unite(var_gender, variable, gender) %>%
  spread(var_gender, value)

Learn more about structural equation modeling with `lavaan’ here.

cfm.model <- '
      # measurement model
        satisfaction  =~ satisfaction_H + 1*satisfaction_W 
        tension =~ tension_H + 1*tension_W

      # structural model
        satisfaction ~ tension

      # residual correlations
        satisfaction_H ~~ tension_H
        satisfaction_W ~~ tension_W
'

cfm <- sem(cfm.model, data = acitelli_dyd)

summary(cfm, fit.measures = TRUE)

## lavaan (0.5-22) converged normally after  27 iterations
## 
##   Number of observations                           148
## 
##   Estimator                                         ML
##   Minimum Function Test Statistic                0.181
##   Degrees of freedom                                 1
##   P-value (Chi-square)                           0.671
## 
## Model test baseline model:
## 
##   Minimum Function Test Statistic              207.095
##   Degrees of freedom                                 6
##   P-value                                        0.000
## 
## User model versus baseline model:
## 
##   Comparative Fit Index (CFI)                    1.000
##   Tucker-Lewis Index (TLI)                       1.024
## 
## Loglikelihood and Information Criteria:
## 
##   Loglikelihood user model (H0)               -412.710
##   Loglikelihood unrestricted model (H1)       -412.620
## 
##   Number of free parameters                          9
##   Akaike (AIC)                                 843.421
##   Bayesian (BIC)                               870.396
##   Sample-size adjusted Bayesian (BIC)          841.914
## 
## Root Mean Square Error of Approximation:
## 
##   RMSEA                                          0.000
##   90 Percent Confidence Interval          0.000  0.164
##   P-value RMSEA <= 0.05                          0.723
## 
## Standardized Root Mean Square Residual:
## 
##   SRMR                                           0.011
## 
## Parameter Estimates:
## 
##   Information                                 Expected
##   Standard Errors                             Standard
## 
## Latent Variables:
##                    Estimate  Std.Err  z-value  P(>|z|)
##   satisfaction =~                                     
##     satisfaction_H    1.000                           
##     satisfaction_W    1.000                           
##   tension =~                                          
##     tension_H         1.000                           
##     tension_W         1.000                           
## 
## Regressions:
##                    Estimate  Std.Err  z-value  P(>|z|)
##   satisfaction ~                                      
##     tension          -0.894    0.150   -5.974    0.000
## 
## Covariances:
##                     Estimate  Std.Err  z-value  P(>|z|)
##  .satisfaction_H ~~                                    
##    .tension_H         -0.032    0.021   -1.499    0.134
##  .satisfaction_W ~~                                    
##    .tension_W         -0.089    0.025   -3.527    0.000
## 
## Variances:
##                    Estimate  Std.Err  z-value  P(>|z|)
##    .satisfaction_H    0.060    0.017    3.501    0.000
##    .satisfaction_W    0.128    0.022    5.969    0.000
##    .tension_H         0.274    0.046    5.914    0.000
##    .tension_W         0.335    0.050    6.744    0.000
##    .satisfaction      0.025    0.021    1.200    0.230
##     tension           0.158    0.040    3.956    0.000

---

Back to schedule

---