Mediation with SEM
Getting Started
library(lavaan)
riggsd <- read.csv("riggsd.csv", header=TRUE) Testing the model that Childhood Abuse leads to Anxious Attachment which in turn leads to lower Relationship Satisfaction for men and women. First the model is estimated treating dyad members as indistinguishable:
Distinguishable Dyads
Med_D <- '
Anxiety_M ~ aa1*Abuse_M
Anxiety_W ~ aa2*Abuse_W
Anxiety_M ~ pa1*Abuse_W
Anxiety_W ~ pa2*Abuse_M
Sat_M ~ ab1*Anxiety_M
Sat_W ~ ab2*Anxiety_W
Sat_M ~ pb1*Anxiety_W
Sat_W ~ pb2*Anxiety_M
Sat_M ~ ac1*Abuse_M
Sat_W ~ ac2*Abuse_W
Sat_M ~ pc1*Abuse_W
Sat_W ~ pc2*Abuse_M
Abuse_M ~ m11*1
Abuse_W ~ m12*1
Sat_M ~ m21*1
Sat_W ~ m22*1
Anxiety_M ~ m31*1
Anxiety_W ~ m32*1
Abuse_M ~~ v11*Abuse_M
Abuse_W ~~ v12*Abuse_W
Sat_M ~~ v21*Sat_M
Sat_W ~~ v22*Sat_W
Anxiety_M ~~ v31*Anxiety_M
Anxiety_W ~~ v32*Anxiety_W
Abuse_W ~~ Abuse_M
Sat_W ~~ Sat_M
Anxiety_W ~~ Anxiety_M
ka1 := pa1/aa1
kb1 := pb1/ab1
AA_ie1 := aa1*ab1
AP_ie1 := aa2*pb1
PA_ie1 := pa1*ab1
PP_ie1 := pa2*pb1
total_ie_a1 := aa1*ab1 + pa2*pb1
total_ie_p1 := aa2*pb1 + pa2*ab1
total_a1 := aa1*ab1 + pa1*pb1 + ac1
total_p1 := aa2*pb1 + pa2*ab1 + pc1
ka2 := pa2/aa2
kb2 := pb2/ab2
AA_ie2 := aa2*ab2
AP_ie2 := aa1*pb2
PA_ie2 := pa2*ab2
PP_ie2 := pa1*pb2
total_ie_a2 := aa2*ab2 + pa1*pb2
total_ie_p2 := aa2*pb2 + pa2*ab2
total_a2 := aa2*ab2 + pa2*pb2 + ac2
total_p2 := aa1*pb2 + pa1*ab2 + pc2
'
# Change to 5000 when bootstrapping.
medd <- sem(Med_D,fixed.x=FALSE, data = riggsd,missing="fiml",se = "boot",bootstrap= 50)
summary(medd, fit.measures = TRUE)## lavaan (0.5-23.1097) converged normally after 93 iterations
##
## Number of observations 155
##
## Number of missing patterns 1
##
## Estimator ML
## Minimum Function Test Statistic 0.000
## Degrees of freedom 0
## Minimum Function Value 0.0000000000000
##
## Model test baseline model:
##
## Minimum Function Test Statistic 172.980
## Degrees of freedom 15
## P-value 0.000
##
## User model versus baseline model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -2379.613
## Loglikelihood unrestricted model (H1) -2379.613
##
## Number of free parameters 27
## Akaike (AIC) 4813.226
## Bayesian (BIC) 4895.399
## Sample-size adjusted Bayesian (BIC) 4809.937
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent Confidence Interval 0.000 0.000
## P-value RMSEA <= 0.05 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Information Observed
## Standard Errors Bootstrap
## Number of requested bootstrap draws 50
## Number of successful bootstrap draws 49
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## Anxiety_M ~
## Abuse_M (aa1) 0.056 0.024 2.298 0.022
## Anxiety_W ~
## Abuse_W (aa2) 0.093 0.020 4.621 0.000
## Anxiety_M ~
## Abuse_W (pa1) 0.022 0.018 1.193 0.233
## Anxiety_W ~
## Abuse_M (pa2) 0.014 0.025 0.576 0.564
## Sat_M ~
## Anxity_M (ab1) -1.634 0.505 -3.237 0.001
## Sat_W ~
## Anxity_W (ab2) -1.525 0.501 -3.043 0.002
## Sat_M ~
## Anxity_W (pb1) -1.168 0.437 -2.673 0.008
## Sat_W ~
## Anxity_M (pb2) -1.210 0.408 -2.963 0.003
## Sat_M ~
## Abuse_M (ac1) -0.072 0.112 -0.643 0.520
## Sat_W ~
## Abuse_W (ac2) -0.249 0.139 -1.791 0.073
## Sat_M ~
## Abuse_W (pc1) -0.030 0.127 -0.236 0.813
## Sat_W ~
## Abuse_M (pc2) -0.136 0.121 -1.121 0.262
##
## Covariances:
## Estimate Std.Err z-value P(>|z|)
## Abuse_M ~~
## Abuse_W 1.532 1.368 1.120 0.263
## .Sat_M ~~
## .Sat_W 27.053 3.311 8.171 0.000
## .Anxiety_M ~~
## .Anxiety_W 0.227 0.113 2.013 0.044
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|)
## Abuse_M (m11) 8.333 0.283 29.430 0.000
## Abuse_W (m12) 9.442 0.394 23.996 0.000
## .Sat_M (m21) 53.461 1.882 28.407 0.000
## .Sat_W (m22) 55.910 2.190 25.534 0.000
## .Anxity_M (m31) 1.963 0.277 7.092 0.000
## .Anxity_W (m32) 1.928 0.255 7.553 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## Abuse_M (v11) 17.514 2.443 7.169 0.000
## Abuse_W (v12) 23.314 3.108 7.501 0.000
## .Sat_M (v21) 43.110 4.380 9.842 0.000
## .Sat_W (v22) 44.147 5.310 8.314 0.000
## .Anxity_M (v31) 1.523 0.099 15.333 0.000
## .Anxity_W (v32) 1.237 0.120 10.287 0.000
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ka1 0.392 0.461 0.850 0.395
## kb1 0.715 0.395 1.809 0.070
## AA_ie1 -0.091 0.055 -1.656 0.098
## AP_ie1 -0.109 0.055 -1.972 0.049
## PA_ie1 -0.036 0.035 -1.020 0.308
## PP_ie1 -0.017 0.034 -0.485 0.628
## total_ie_a1 -0.108 0.072 -1.496 0.135
## total_ie_p1 -0.132 0.068 -1.953 0.051
## total_a1 -0.188 0.122 -1.543 0.123
## total_p1 -0.162 0.129 -1.261 0.207
## ka2 0.154 0.325 0.473 0.636
## kb2 0.793 0.641 1.237 0.216
## AA_ie2 -0.142 0.057 -2.483 0.013
## AP_ie2 -0.067 0.037 -1.814 0.070
## PA_ie2 -0.022 0.042 -0.515 0.607
## PP_ie2 -0.026 0.027 -0.960 0.337
## total_ie_a2 -0.168 0.069 -2.434 0.015
## total_ie_p2 -0.134 0.060 -2.253 0.024
## total_a2 -0.409 0.131 -3.121 0.002
## total_p2 -0.236 0.144 -1.637 0.102parameterEstimates(medd, standardized = TRUE)## lhs op rhs label est se z
## 1 Anxiety_M ~ Abuse_M aa1 0.056 0.024 2.298
## 2 Anxiety_W ~ Abuse_W aa2 0.093 0.020 4.621
## 3 Anxiety_M ~ Abuse_W pa1 0.022 0.018 1.193
## 4 Anxiety_W ~ Abuse_M pa2 0.014 0.025 0.576
## 5 Sat_M ~ Anxiety_M ab1 -1.634 0.505 -3.237
## 6 Sat_W ~ Anxiety_W ab2 -1.525 0.501 -3.043
## 7 Sat_M ~ Anxiety_W pb1 -1.168 0.437 -2.673
## 8 Sat_W ~ Anxiety_M pb2 -1.210 0.408 -2.963
## 9 Sat_M ~ Abuse_M ac1 -0.072 0.112 -0.643
## 10 Sat_W ~ Abuse_W ac2 -0.249 0.139 -1.791
## 11 Sat_M ~ Abuse_W pc1 -0.030 0.127 -0.236
## 12 Sat_W ~ Abuse_M pc2 -0.136 0.121 -1.121
## 13 Abuse_M ~1 m11 8.333 0.283 29.430
## 14 Abuse_W ~1 m12 9.442 0.394 23.996
## 15 Sat_M ~1 m21 53.461 1.882 28.407
## 16 Sat_W ~1 m22 55.910 2.190 25.534
## 17 Anxiety_M ~1 m31 1.963 0.277 7.092
## 18 Anxiety_W ~1 m32 1.928 0.255 7.553
## 19 Abuse_M ~~ Abuse_M v11 17.514 2.443 7.169
## 20 Abuse_W ~~ Abuse_W v12 23.314 3.108 7.501
## 21 Sat_M ~~ Sat_M v21 43.110 4.380 9.842
## 22 Sat_W ~~ Sat_W v22 44.147 5.310 8.314
## 23 Anxiety_M ~~ Anxiety_M v31 1.523 0.099 15.333
## 24 Anxiety_W ~~ Anxiety_W v32 1.237 0.120 10.287
## 25 Abuse_M ~~ Abuse_W 1.532 1.368 1.120
## 26 Sat_M ~~ Sat_W 27.053 3.311 8.171
## 27 Anxiety_M ~~ Anxiety_W 0.227 0.113 2.013
## 28 ka1 := pa1/aa1 ka1 0.392 0.461 0.850
## 29 kb1 := pb1/ab1 kb1 0.715 0.395 1.809
## 30 AA_ie1 := aa1*ab1 AA_ie1 -0.091 0.055 -1.656
## 31 AP_ie1 := aa2*pb1 AP_ie1 -0.109 0.055 -1.972
## 32 PA_ie1 := pa1*ab1 PA_ie1 -0.036 0.035 -1.020
## 33 PP_ie1 := pa2*pb1 PP_ie1 -0.017 0.034 -0.485
## 34 total_ie_a1 := aa1*ab1+pa2*pb1 total_ie_a1 -0.108 0.072 -1.496
## 35 total_ie_p1 := aa2*pb1+pa2*ab1 total_ie_p1 -0.132 0.068 -1.953
## 36 total_a1 := aa1*ab1+pa1*pb1+ac1 total_a1 -0.188 0.122 -1.543
## 37 total_p1 := aa2*pb1+pa2*ab1+pc1 total_p1 -0.162 0.129 -1.261
## 38 ka2 := pa2/aa2 ka2 0.154 0.325 0.473
## 39 kb2 := pb2/ab2 kb2 0.793 0.641 1.237
## 40 AA_ie2 := aa2*ab2 AA_ie2 -0.142 0.057 -2.483
## 41 AP_ie2 := aa1*pb2 AP_ie2 -0.067 0.037 -1.814
## 42 PA_ie2 := pa2*ab2 PA_ie2 -0.022 0.042 -0.515
## 43 PP_ie2 := pa1*pb2 PP_ie2 -0.026 0.027 -0.960
## 44 total_ie_a2 := aa2*ab2+pa1*pb2 total_ie_a2 -0.168 0.069 -2.434
## 45 total_ie_p2 := aa2*pb2+pa2*ab2 total_ie_p2 -0.134 0.060 -2.253
## 46 total_a2 := aa2*ab2+pa2*pb2+ac2 total_a2 -0.409 0.131 -3.121
## 47 total_p2 := aa1*pb2+pa1*ab2+pc2 total_p2 -0.236 0.144 -1.637
## pvalue ci.lower ci.upper std.lv std.all std.nox
## 1 0.022 0.013 0.112 0.056 0.185 0.185
## 2 0.000 0.054 0.149 0.093 0.374 0.374
## 3 0.233 -0.011 0.074 0.022 0.083 0.083
## 4 0.564 -0.036 0.069 0.014 0.050 0.050
## 5 0.001 -2.883 -0.714 -1.634 -0.288 -0.288
## 6 0.002 -2.474 -0.366 -1.525 -0.247 -0.247
## 7 0.008 -2.121 -0.219 -1.168 -0.197 -0.197
## 8 0.003 -1.979 -0.019 -1.210 -0.205 -0.205
## 9 0.520 -0.360 0.161 -0.072 -0.042 -0.042
## 10 0.073 -0.589 0.034 -0.249 -0.162 -0.162
## 11 0.813 -0.287 0.283 -0.030 -0.020 -0.020
## 12 0.262 -0.385 0.064 -0.136 -0.076 -0.076
## 13 0.000 7.868 9.116 8.333 1.991 1.991
## 14 0.000 8.651 10.219 9.442 1.956 1.956
## 15 0.000 48.832 57.617 53.461 7.479 7.479
## 16 0.000 50.337 59.302 55.910 7.516 7.516
## 17 0.000 1.383 2.544 1.963 1.556 1.556
## 18 0.000 1.434 2.438 1.928 1.603 1.603
## 19 0.000 13.547 25.217 17.514 1.000 1.000
## 20 0.000 17.466 30.431 23.314 1.000 1.000
## 21 0.000 32.002 52.491 43.110 0.844 0.844
## 22 0.000 33.051 53.945 44.147 0.798 0.798
## 23 0.000 1.285 1.695 1.523 0.957 0.957
## 24 0.000 0.966 1.476 1.237 0.855 0.855
## 25 0.263 -1.623 4.452 1.532 0.076 0.076
## 26 0.000 19.501 31.666 27.053 0.620 0.620
## 27 0.044 0.003 0.442 0.227 0.166 0.166
## 28 0.395 -0.225 2.137 0.392 0.452 0.452
## 29 0.070 0.180 1.987 0.715 0.682 0.682
## 30 0.098 -0.229 -0.014 -0.091 -0.053 -0.053
## 31 0.049 -0.272 -0.019 -0.109 -0.073 -0.073
## 32 0.308 -0.125 0.015 -0.036 -0.024 -0.024
## 33 0.628 -0.110 0.064 -0.017 -0.010 -0.010
## 34 0.135 -0.269 0.028 -0.108 -0.063 -0.063
## 35 0.051 -0.342 -0.014 -0.132 -0.088 -0.088
## 36 0.123 -0.497 0.011 -0.188 -0.112 -0.112
## 37 0.207 -0.474 0.104 -0.162 -0.108 -0.108
## 38 0.636 -0.350 1.146 0.154 0.133 0.133
## 39 0.216 0.031 3.399 0.793 0.832 0.832
## 40 0.013 -0.281 -0.035 -0.142 -0.092 -0.092
## 41 0.070 -0.163 -0.003 -0.067 -0.038 -0.038
## 42 0.607 -0.122 0.066 -0.022 -0.012 -0.012
## 43 0.337 -0.117 0.010 -0.026 -0.017 -0.017
## 44 0.015 -0.349 -0.048 -0.168 -0.109 -0.109
## 45 0.024 -0.300 -0.003 -0.134 -0.089 -0.089
## 46 0.002 -0.702 -0.090 -0.409 -0.264 -0.264
## 47 0.102 -0.531 0.028 -0.236 -0.135 -0.135Estimates the same as with gls. Standard errors, t values, and p values slightly different (gls are “better”).
Note that indirect effect (ie), total indirect effects (total_ie), and total effects (total) are computed.
From APIMeM app:
https://davidakenny.shinyapps.io/APIMeM/
Indistinguishable Dyads
Medi <- '
Anxiety_M ~ aa*Abuse_M
Anxiety_W ~ aa*Abuse_W
Anxiety_M ~ pa*Abuse_W
Anxiety_W ~ pa*Abuse_M
Sat_M ~ ab*Anxiety_M
Sat_W ~ ab*Anxiety_W
Sat_M ~ pb*Anxiety_W
Sat_W ~ pb*Anxiety_M
Sat_M ~ ac*Abuse_M
Sat_W ~ ac*Abuse_W
Sat_M ~ pc*Abuse_W
Sat_W ~ pc*Abuse_M
Abuse_M ~ m1*1
Abuse_W ~ m1*1
Sat_M ~ m2*1
Sat_W ~ m2*1
Anxiety_M ~ m3*1
Anxiety_W ~ m3*1
Abuse_M ~~ v1*Abuse_M
Abuse_W ~~ v1*Abuse_W
Sat_M ~~ v2*Sat_M
Sat_W ~~ v2*Sat_W
Anxiety_M ~~ v3*Anxiety_M
Anxiety_W ~~ v3*Anxiety_W
Abuse_W ~~ Abuse_M
Sat_W ~~ Sat_M
Anxiety_W ~~ Anxiety_M
ka := pa/aa
kb := pb/ab
AA_ie := aa*ab
AP_ie := aa*pb
PA_ie := pa*ab
PP_ie := pa*pb
total_ie_a := aa*ab + pa*pb
total_ie_p := aa*pb + pa*ab
total_a := aa*ab + pa*pb + ac
total_p := aa*pb + pa*ab + pc
'
# Change to "bootstrap = 5000" to get reliable values for the confidence interval.
Med_i <- sem(Medi,fixed.x=FALSE, data = riggsd,missing="fiml",se = "boot",bootstrap= 50)
summary(Med_i, fit.measures = TRUE)## lavaan (0.5-23.1097) converged normally after 59 iterations
##
## Number of observations 155
##
## Number of missing patterns 1
##
## Estimator ML
## Minimum Function Test Statistic 18.784
## Degrees of freedom 12
## P-value (Chi-square) 0.094
##
## Model test baseline model:
##
## Minimum Function Test Statistic 172.980
## Degrees of freedom 15
## P-value 0.000
##
## User model versus baseline model:
##
## Comparative Fit Index (CFI) 0.957
## Tucker-Lewis Index (TLI) 0.946
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -2389.005
## Loglikelihood unrestricted model (H1) -2379.613
##
## Number of free parameters 15
## Akaike (AIC) 4808.010
## Bayesian (BIC) 4853.661
## Sample-size adjusted Bayesian (BIC) 4806.183
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.060
## 90 Percent Confidence Interval 0.000 0.110
## P-value RMSEA <= 0.05 0.331
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.077
##
## Parameter Estimates:
##
## Information Observed
## Standard Errors Bootstrap
## Number of requested bootstrap draws 50
## Number of successful bootstrap draws 50
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## Anxiety_M ~
## Abuse_M (aa) 0.080 0.015 5.249 0.000
## Anxiety_W ~
## Abuse_W (aa) 0.080 0.015 5.249 0.000
## Anxiety_M ~
## Abuse_W (pa) 0.015 0.014 1.072 0.284
## Anxiety_W ~
## Abuse_M (pa) 0.015 0.014 1.072 0.284
## Sat_M ~
## Anxiety_M (ab) -1.601 0.376 -4.262 0.000
## Sat_W ~
## Anxiety_W (ab) -1.601 0.376 -4.262 0.000
## Sat_M ~
## Anxiety_W (pb) -1.182 0.332 -3.559 0.000
## Sat_W ~
## Anxiety_M (pb) -1.182 0.332 -3.559 0.000
## Sat_M ~
## Abuse_M (ac) -0.169 0.087 -1.937 0.053
## Sat_W ~
## Abuse_W (ac) -0.169 0.087 -1.937 0.053
## Sat_M ~
## Abuse_W (pc) -0.076 0.071 -1.080 0.280
## Sat_W ~
## Abuse_M (pc) -0.076 0.071 -1.080 0.280
##
## Covariances:
## Estimate Std.Err z-value P(>|z|)
## Abuse_M ~~
## Abuse_W 1.225 1.443 0.849 0.396
## .Sat_M ~~
## .Sat_W 26.853 3.515 7.639 0.000
## .Anxiety_M ~~
## .Anxiety_W 0.217 0.116 1.874 0.061
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|)
## Abuse_M (m1) 8.888 0.265 33.600 0.000
## Abuse_W (m1) 8.888 0.265 33.600 0.000
## .Sat_M (m2) 54.732 1.714 31.936 0.000
## .Sat_W (m2) 54.732 1.714 31.936 0.000
## .Anxiety_M (m3) 1.932 0.214 9.013 0.000
## .Anxiety_W (m3) 1.932 0.214 9.013 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## Abuse_M (v1) 20.722 1.807 11.465 0.000
## Abuse_W (v1) 20.722 1.807 11.465 0.000
## .Sat_M (v2) 43.853 3.674 11.937 0.000
## .Sat_W (v2) 43.853 3.674 11.937 0.000
## .Anxiety_M (v3) 1.400 0.085 16.503 0.000
## .Anxiety_W (v3) 1.400 0.085 16.503 0.000
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ka 0.189 0.182 1.033 0.301
## kb 0.738 0.217 3.404 0.001
## AA_ie -0.129 0.049 -2.630 0.009
## AP_ie -0.095 0.034 -2.767 0.006
## PA_ie -0.024 0.026 -0.926 0.355
## PP_ie -0.018 0.020 -0.875 0.381
## total_ie_a -0.146 0.059 -2.498 0.012
## total_ie_p -0.119 0.053 -2.242 0.025
## total_a -0.315 0.097 -3.244 0.001
## total_p -0.196 0.088 -2.211 0.027parameterEstimates(Med_i, standardized = TRUE)## lhs op rhs label est se z pvalue
## 1 Anxiety_M ~ Abuse_M aa 0.080 0.015 5.249 0.000
## 2 Anxiety_W ~ Abuse_W aa 0.080 0.015 5.249 0.000
## 3 Anxiety_M ~ Abuse_W pa 0.015 0.014 1.072 0.284
## 4 Anxiety_W ~ Abuse_M pa 0.015 0.014 1.072 0.284
## 5 Sat_M ~ Anxiety_M ab -1.601 0.376 -4.262 0.000
## 6 Sat_W ~ Anxiety_W ab -1.601 0.376 -4.262 0.000
## 7 Sat_M ~ Anxiety_W pb -1.182 0.332 -3.559 0.000
## 8 Sat_W ~ Anxiety_M pb -1.182 0.332 -3.559 0.000
## 9 Sat_M ~ Abuse_M ac -0.169 0.087 -1.937 0.053
## 10 Sat_W ~ Abuse_W ac -0.169 0.087 -1.937 0.053
## 11 Sat_M ~ Abuse_W pc -0.076 0.071 -1.080 0.280
## 12 Sat_W ~ Abuse_M pc -0.076 0.071 -1.080 0.280
## 13 Abuse_M ~1 m1 8.888 0.265 33.600 0.000
## 14 Abuse_W ~1 m1 8.888 0.265 33.600 0.000
## 15 Sat_M ~1 m2 54.732 1.714 31.936 0.000
## 16 Sat_W ~1 m2 54.732 1.714 31.936 0.000
## 17 Anxiety_M ~1 m3 1.932 0.214 9.013 0.000
## 18 Anxiety_W ~1 m3 1.932 0.214 9.013 0.000
## 19 Abuse_M ~~ Abuse_M v1 20.722 1.807 11.465 0.000
## 20 Abuse_W ~~ Abuse_W v1 20.722 1.807 11.465 0.000
## 21 Sat_M ~~ Sat_M v2 43.853 3.674 11.937 0.000
## 22 Sat_W ~~ Sat_W v2 43.853 3.674 11.937 0.000
## 23 Anxiety_M ~~ Anxiety_M v3 1.400 0.085 16.503 0.000
## 24 Anxiety_W ~~ Anxiety_W v3 1.400 0.085 16.503 0.000
## 25 Abuse_M ~~ Abuse_W 1.225 1.443 0.849 0.396
## 26 Sat_M ~~ Sat_W 26.853 3.515 7.639 0.000
## 27 Anxiety_M ~~ Anxiety_W 0.217 0.116 1.874 0.061
## 28 ka := pa/aa ka 0.189 0.182 1.033 0.301
## 29 kb := pb/ab kb 0.738 0.217 3.404 0.001
## 30 AA_ie := aa*ab AA_ie -0.129 0.049 -2.630 0.009
## 31 AP_ie := aa*pb AP_ie -0.095 0.034 -2.767 0.006
## 32 PA_ie := pa*ab PA_ie -0.024 0.026 -0.926 0.355
## 33 PP_ie := pa*pb PP_ie -0.018 0.020 -0.875 0.381
## 34 total_ie_a := aa*ab+pa*pb total_ie_a -0.146 0.059 -2.498 0.012
## 35 total_ie_p := aa*pb+pa*ab total_ie_p -0.119 0.053 -2.242 0.025
## 36 total_a := aa*ab+pa*pb+ac total_a -0.315 0.097 -3.244 0.001
## 37 total_p := aa*pb+pa*ab+pc total_p -0.196 0.088 -2.211 0.027
## ci.lower ci.upper std.lv std.all std.nox
## 1 0.047 0.114 0.080 0.294 0.294
## 2 0.047 0.114 0.080 0.294 0.294
## 3 -0.007 0.051 0.015 0.056 0.056
## 4 -0.007 0.051 0.015 0.056 0.056
## 5 -2.411 -0.930 -1.601 -0.272 -0.272
## 6 -2.411 -0.930 -1.601 -0.272 -0.272
## 7 -1.913 -0.371 -1.182 -0.201 -0.201
## 8 -1.913 -0.371 -1.182 -0.201 -0.201
## 9 -0.356 0.016 -0.169 -0.105 -0.105
## 10 -0.356 0.016 -0.169 -0.105 -0.105
## 11 -0.263 0.041 -0.076 -0.048 -0.048
## 12 -0.263 0.041 -0.076 -0.048 -0.048
## 13 8.378 9.628 8.888 1.952 1.952
## 14 8.378 9.628 8.888 1.952 1.952
## 15 51.553 58.427 54.732 7.502 7.502
## 16 51.553 58.427 54.732 7.502 7.502
## 17 1.444 2.331 1.932 1.556 1.556
## 18 1.444 2.331 1.932 1.556 1.556
## 19 17.134 24.807 20.722 1.000 1.000
## 20 17.134 24.807 20.722 1.000 1.000
## 21 35.411 50.050 43.853 0.824 0.824
## 22 35.411 50.050 43.853 0.824 0.824
## 23 1.135 1.548 1.400 0.908 0.908
## 24 1.135 1.548 1.400 0.908 0.908
## 25 -1.787 4.307 1.225 0.059 0.059
## 26 20.134 34.668 26.853 0.612 0.612
## 27 -0.033 0.418 0.217 0.155 0.155
## 28 -0.100 0.731 0.189 0.189 0.189
## 29 0.277 1.264 0.738 0.738 0.738
## 30 -0.276 -0.061 -0.129 -0.080 -0.080
## 31 -0.182 -0.035 -0.095 -0.059 -0.059
## 32 -0.101 0.014 -0.024 -0.015 -0.015
## 33 -0.081 0.011 -0.018 -0.011 -0.011
## 34 -0.325 -0.074 -0.146 -0.091 -0.091
## 35 -0.250 -0.035 -0.119 -0.074 -0.074
## 36 -0.552 -0.132 -0.315 -0.197 -0.197
## 37 -0.397 -0.072 -0.196 -0.122 -0.122As this model is just-identified, the chi square is for the I-SAT model. As it is not statistically significant, it indicates that it is sensible to treat dyad members as if they were indistinguishable.