** This is a course material for PSY6111-01-00. Any questions or comments regarding the material should be addressed to the course instructor, Jeong Eun Cheon (email: cheonje@yonsei.ac.kr) **
We aim to replicate the results of Study 3 from Czarna et al. (2022). The authors have generously provided access to their datasets and scripts through the Open Science Framework (OSF). These materials can be accessed at the following link: https://osf.io/8j4td/?view_only=dee38744aef04831b98484076616d98d.
We will use their provided code as a foundation to reconstruct and validate their core findings. Although the original study employed SEM, we will use MLM for this replication.
For those interested, the practice replication code for the SEM version of Study 3 is available here: https://rpubs.com/cheonje/moderationreplication.
Reference: Czarna, A. Z., Śmieja, M., Wider, M., Dufner, M., & Sedikides, C. (2022). Narcissism and partner-enhancement at different relationship stages. Journal of Research in Personality, 98, 104212. https://doi.org/10.1016/j.jrp.2022.104212
library(foreign)
dyad_pairwise <-read.spss("narcissism_pair.sav",use.value.label=FALSE, to.data.frame=TRUE)
library(base)
dyad_pairwise$zNPI_A <- as.vector(scale(dyad_pairwise$NPI_A, center = TRUE, scale = TRUE))
dyad_pairwise$zNPI_P <- as.vector(scale(dyad_pairwise$NPI_P, center = TRUE, scale = TRUE))dyad_pairwise <- dyad_pairwise %>%mutate(men = ifelse(partnum_A == 2, 1, 0),
women = ifelse(partnum_A == 1, 1, 0))Interaction approach
library(nlme)##
## Attaching package: 'nlme'## The following object is masked from 'package:usdm':
##
## Variogram## The following object is masked from 'package:dplyr':
##
## collapseAPIM_mlm <- lme(Partner_enhancement__A ~ Sex_A*(zNPI_A + zNPI_P),
data = dyad_pairwise,
random = ~ 1 + Sex_A | dyadno,
weights = varIdent(form=~1|Sex_A),
na.action = na.omit)
summary(APIM_mlm)## Linear mixed-effects model fit by REML
## Data: dyad_pairwise
## AIC BIC logLik
## 434.0013 467.9648 -206.0006
##
## Random effects:
## Formula: ~1 + Sex_A | dyadno
## Structure: General positive-definite, Log-Cholesky parametrization
## StdDev Corr
## (Intercept) 0.7427934 (Intr)
## Sex_A 1.2110764 -0.846
## Residual 0.3782143
##
## Variance function:
## Structure: Different standard deviations per stratum
## Formula: ~1 | Sex_A
## Parameter estimates:
## 0 1
## 1 1
## Fixed effects: Partner_enhancement__A ~ Sex_A * (zNPI_A + zNPI_P)
## Value Std.Error DF t-value p-value
## (Intercept) -0.2669099 0.09111020 83 -2.929529 0.0044
## Sex_A 0.7773964 0.14471275 79 5.371997 0.0000
## zNPI_A -0.2199655 0.09235699 79 -2.381687 0.0196
## zNPI_P 0.3013056 0.09435267 79 3.193397 0.0020
## Sex_A:zNPI_A -0.1425512 0.12498377 79 -1.140558 0.2575
## Sex_A:zNPI_P -0.1405756 0.12510336 79 -1.123675 0.2646
## Correlation:
## (Intr) Sex_A zNPI_A zNPI_P S_A:NPI_A
## Sex_A -0.819
## zNPI_A -0.046 0.038
## zNPI_P 0.047 -0.038 -0.209
## Sex_A:zNPI_A 0.023 -0.001 -0.691 -0.073
## Sex_A:zNPI_P -0.025 0.003 -0.065 -0.708 0.113
##
## Standardized Within-Group Residuals:
## Min Q1 Med Q3 Max
## -1.40003157 -0.30537451 -0.01776638 0.30161695 1.28151501
##
## Number of Observations: 168
## Number of Groups: 84APIM_mlm <- lme(Partner_enhancement__A ~ -1 + men + women +
men:zNPI_A + men:zNPI_P +
women:zNPI_A + women:zNPI_P,
data = dyad_pairwise,
random = ~-1 + women + men | dyadno,
weights = varIdent(form=~1|Sex_A),
na.action = na.omit)
summary(APIM_mlm)## Linear mixed-effects model fit by REML
## Data: dyad_pairwise
## AIC BIC logLik
## 434.0013 467.9648 -206.0006
##
## Random effects:
## Formula: ~-1 + women + men | dyadno
## Structure: General positive-definite, Log-Cholesky parametrization
## StdDev Corr
## women 0.7841700 women
## men 0.7477667 -0.357
## Residual 0.2826048
##
## Variance function:
## Structure: Different standard deviations per stratum
## Formula: ~1 | Sex_A
## Parameter estimates:
## 0 1
## 1 1
## Fixed effects: Partner_enhancement__A ~ -1 + men + women + men:zNPI_A + men:zNPI_P + women:zNPI_A + women:zNPI_P
## Value Std.Error DF t-value p-value
## men 0.5104865 0.08737722 79 5.842329 0.0000
## women -0.2669099 0.09111020 79 -2.929529 0.0044
## men:zNPI_A -0.3625167 0.09048684 79 -4.006292 0.0001
## men:zNPI_P 0.1607300 0.08857292 79 1.814663 0.0734
## women:zNPI_A -0.2199655 0.09235699 79 -2.381687 0.0196
## women:zNPI_P 0.3013056 0.09435267 79 3.193397 0.0020
## Correlation:
## men women m:NPI_A m:NPI_P w:NPI_A
## women -0.314
## men:zNPI_A 0.047 -0.015
## men:zNPI_P -0.046 0.015 -0.209
## women:zNPI_A 0.015 -0.046 0.066 -0.314
## women:zNPI_P -0.015 0.047 -0.314 0.066 -0.209
##
## Standardized Within-Group Residuals:
## Min Q1 Med Q3 Max
## -1.04611501 -0.22817833 -0.01327518 0.22537065 0.95755848
##
## Number of Observations: 168
## Number of Groups: 84APIM_mlm <- lme(Partner_enhancement__A ~ Sex_A*(zNPI_A + zNPI_P + zMonths_A) +
Sex_A*zNPI_A*zMonths_A + Sex_A*zNPI_P*zMonths_A,
data = dyad_pairwise,
random = ~ 1 + Sex_A | dyadno,
weights = varIdent(form=~1|Sex_A),
method = "ML",
na.action = na.omit)
summary(APIM_mlm)## Linear mixed-effects model fit by maximum likelihood
## Data: dyad_pairwise
## AIC BIC logLik
## 397.269 450.3764 -181.6345
##
## Random effects:
## Formula: ~1 + Sex_A | dyadno
## Structure: General positive-definite, Log-Cholesky parametrization
## StdDev Corr
## (Intercept) 0.6996869 (Intr)
## Sex_A 1.1035106 -0.872
## Residual 0.3464446
##
## Variance function:
## Structure: Different standard deviations per stratum
## Formula: ~1 | Sex_A
## Parameter estimates:
## 0 1
## 1 1
## Fixed effects: Partner_enhancement__A ~ Sex_A * (zNPI_A + zNPI_P + zMonths_A) + Sex_A * zNPI_A * zMonths_A + Sex_A * zNPI_P * zMonths_A
## Value Std.Error DF t-value p-value
## (Intercept) -0.2598133 0.08989419 82 -2.890213 0.0049
## Sex_A 0.8035747 0.13901471 74 5.780501 0.0000
## zNPI_A -0.2222362 0.09059028 74 -2.453202 0.0165
## zNPI_P 0.3216194 0.09229237 74 3.484789 0.0008
## zMonths_A 0.0393021 0.09093645 82 0.432193 0.6667
## Sex_A:zNPI_A -0.1558648 0.11802293 74 -1.320632 0.1907
## Sex_A:zNPI_P -0.1849462 0.11830228 74 -1.563336 0.1222
## Sex_A:zMonths_A -0.3809630 0.14062649 74 -2.709041 0.0084
## zNPI_A:zMonths_A 0.1770073 0.10600670 74 1.669774 0.0992
## zNPI_P:zMonths_A -0.1950412 0.08114474 74 -2.403621 0.0187
## Sex_A:zNPI_A:zMonths_A -0.0401407 0.12567451 74 -0.319402 0.7503
## Sex_A:zNPI_P:zMonths_A 0.3457144 0.12168513 74 2.841057 0.0058
## Correlation:
## (Intr) Sex_A zNPI_A zNPI_P zMnt_A Sx_A:NPI_A Sx_A:NPI_P
## Sex_A -0.842
## zNPI_A -0.036 0.030
## zNPI_P 0.056 -0.047 -0.196
## zMonths_A -0.021 0.018 0.108 0.067
## Sex_A:zNPI_A 0.014 0.008 -0.721 -0.086 -0.099
## Sex_A:zNPI_P -0.036 0.018 -0.078 -0.735 -0.077 0.152
## Sex_A:zMonths_A 0.018 -0.021 -0.091 -0.056 -0.842 0.107 0.102
## zNPI_A:zMonths_A 0.152 -0.128 0.038 0.084 -0.044 -0.049 -0.074
## zNPI_P:zMonths_A 0.060 -0.050 0.043 -0.041 -0.153 -0.023 0.022
## Sex_A:zNPI_A:zMonths_A -0.140 0.135 -0.040 -0.063 0.067 0.031 0.073
## Sex_A:zNPI_P:zMonths_A -0.080 0.127 -0.039 0.005 0.113 0.068 0.022
## S_A:M_ zNPI_A: zNPI_P: S_A:NPI_A:
## Sex_A
## zNPI_A
## zNPI_P
## zMonths_A
## Sex_A:zNPI_A
## Sex_A:zNPI_P
## Sex_A:zMonths_A
## zNPI_A:zMonths_A 0.037
## zNPI_P:zMonths_A 0.129 -0.122
## Sex_A:zNPI_A:zMonths_A -0.101 -0.820 -0.092
## Sex_A:zNPI_P:zMonths_A -0.113 -0.182 -0.635 0.229
##
## Standardized Within-Group Residuals:
## Min Q1 Med Q3 Max
## -1.276726968 -0.376488867 0.009209769 0.327350547 1.375329338
##
## Number of Observations: 168
## Number of Groups: 84APIM_mlm1 <- lme(Partner_enhancement__A ~ men + zNPI_A + zNPI_P + zMonths_A +
zNPI_A:zMonths_A + zNPI_P:zMonths_A +
zNPI_P:men + zMonths_A:men +
zNPI_P:zMonths_A:men,
data = dyad_pairwise,
random = ~ 1 + men | dyadno,
weights = varIdent(form=~1|men),
method = "ML",
na.action = na.omit) #women coeffient
summary(APIM_mlm1)## Linear mixed-effects model fit by maximum likelihood
## Data: dyad_pairwise
## AIC BIC logLik
## 395.2186 442.0781 -182.6093
##
## Random effects:
## Formula: ~1 + men | dyadno
## Structure: General positive-definite, Log-Cholesky parametrization
## StdDev Corr
## (Intercept) 0.705298 (Intr)
## men 1.112223 -0.873
## Residual 0.347245
##
## Variance function:
## Structure: Different standard deviations per stratum
## Formula: ~1 | men
## Parameter estimates:
## 0 1
## 1 1
## Fixed effects: Partner_enhancement__A ~ men + zNPI_A + zNPI_P + zMonths_A + zNPI_A:zMonths_A + zNPI_P:zMonths_A + zNPI_P:men + zMonths_A:men + zNPI_P:zMonths_A:men
## Value Std.Error DF t-value p-value
## (Intercept) -0.2616473 0.08903572 82 -2.938678 0.0043
## men 0.8102312 0.13781311 76 5.879202 0.0000
## zNPI_A -0.3091007 0.06271507 76 -4.928652 0.0000
## zNPI_P 0.3095041 0.09182388 76 3.370627 0.0012
## zMonths_A 0.0291891 0.09031149 82 0.323204 0.7474
## zNPI_A:zMonths_A 0.1459862 0.06063174 76 2.407752 0.0185
## zNPI_P:zMonths_A -0.1996360 0.08081574 76 -2.470262 0.0157
## men:zNPI_P -0.1586729 0.11658040 76 -1.361060 0.1775
## men:zMonths_A -0.3651712 0.13913373 76 -2.624605 0.0105
## men:zNPI_P:zMonths_A 0.3644525 0.11810013 76 3.085962 0.0028
## Correlation:
## (Intr) men zNPI_A zNPI_P zMnt_A zNPI_A: zNPI_P:
## men -0.840
## zNPI_A -0.041 0.056
## zNPI_P 0.050 -0.039 -0.377
## zMonths_A -0.010 0.009 0.055 0.064
## zNPI_A:zMonths_A 0.067 -0.030 -0.030 0.054 0.015
## zNPI_P:zMonths_A 0.048 -0.038 0.036 -0.049 -0.150 -0.349
## men:zNPI_P -0.029 0.007 0.048 -0.732 -0.069 -0.019 0.033
## men:zMonths_A 0.002 -0.008 -0.023 -0.054 -0.840 -0.076 0.124
## men:zNPI_P:zMonths_A -0.051 0.099 0.022 0.026 0.108 0.015 -0.634
## mn:NPI_P mn:M_A
## men
## zNPI_A
## zNPI_P
## zMonths_A
## zNPI_A:zMonths_A
## zNPI_P:zMonths_A
## men:zNPI_P
## men:zMonths_A 0.096
## men:zNPI_P:zMonths_A -0.004 -0.100
##
## Standardized Within-Group Residuals:
## Min Q1 Med Q3 Max
## -1.296768672 -0.362670051 0.008076295 0.343134995 1.414803485
##
## Number of Observations: 168
## Number of Groups: 84APIM_mlm1 <- lme(Partner_enhancement__A ~ women + zNPI_A + zNPI_P + zMonths_A +
zNPI_A:zMonths_A + zNPI_P:zMonths_A +
zNPI_P:women + zMonths_A:women +
zNPI_P:zMonths_A:women,
data = dyad_pairwise,
random = ~ 1 + women | dyadno,
weights = varIdent(form=~1|women),
method = "ML",
na.action = na.omit) #men coefficient
summary(APIM_mlm1)## Linear mixed-effects model fit by maximum likelihood
## Data: dyad_pairwise
## AIC BIC logLik
## 395.2186 442.0781 -182.6093
##
## Random effects:
## Formula: ~1 + women | dyadno
## Structure: General positive-definite, Log-Cholesky parametrization
## StdDev Corr
## (Intercept) 0.6094138 (Intr)
## women 1.1179381 -0.82
## Residual 0.3379449
##
## Variance function:
## Structure: Different standard deviations per stratum
## Formula: ~1 | women
## Parameter estimates:
## 1 0
## 1 1
## Fixed effects: Partner_enhancement__A ~ women + zNPI_A + zNPI_P + zMonths_A + zNPI_A:zMonths_A + zNPI_P:zMonths_A + zNPI_P:women + zMonths_A:women + zNPI_P:zMonths_A:women
## Value Std.Error DF t-value p-value
## (Intercept) 0.5485838 0.07944968 82 6.904796 0.0000
## women -0.8102312 0.13781311 76 -5.879202 0.0000
## zNPI_A -0.3091007 0.06271507 76 -4.928652 0.0000
## zNPI_P 0.1508311 0.07965190 76 1.893629 0.0621
## zMonths_A -0.3359821 0.07999427 82 -4.200077 0.0001
## zNPI_A:zMonths_A 0.1459862 0.06063174 76 2.407752 0.0185
## zNPI_P:zMonths_A 0.1648165 0.09155079 76 1.800274 0.0758
## women:zNPI_P 0.1586729 0.11658040 76 1.361060 0.1775
## women:zMonths_A 0.3651712 0.13913373 76 2.624605 0.0105
## women:zNPI_P:zMonths_A -0.3644525 0.11810013 76 -3.085962 0.0028
## Correlation:
## (Intr) women zNPI_A zNPI_P zMnt_A zNPI_A: zNPI_P:
## women -0.794
## zNPI_A 0.051 -0.056
## zNPI_P -0.042 0.034 -0.364
## zMonths_A -0.015 0.003 0.022 0.104
## zNPI_A:zMonths_A 0.022 0.030 -0.030 0.034 -0.115
## zNPI_P:zMonths_A 0.138 -0.094 0.060 0.023 -0.028 -0.289
## women:zNPI_P 0.019 0.007 -0.048 -0.619 -0.089 0.019 -0.024
## women:zMonths_A 0.012 -0.008 0.023 -0.077 -0.791 0.076 0.020
## women:zNPI_P:zMonths_A -0.115 0.099 -0.022 -0.024 0.052 -0.015 -0.731
## wm:NPI_P wm:M_A
## women
## zNPI_A
## zNPI_P
## zMonths_A
## zNPI_A:zMonths_A
## zNPI_P:zMonths_A
## women:zNPI_P
## women:zMonths_A 0.096
## women:zNPI_P:zMonths_A -0.004 -0.100
##
## Standardized Within-Group Residuals:
## Min Q1 Med Q3 Max
## -1.262037622 -0.352956745 0.007859989 0.333944892 1.376911141
##
## Number of Observations: 168
## Number of Groups: 84dyad_pairwise$low_zNPI_A <- dyad_pairwise$zNPI_A +1
dyad_pairwise$high_zNPI_A <- dyad_pairwise$zNPI_A -1
dyad_pairwise <- dyad_pairwise %>%mutate(men = ifelse(partnum_A == 2, 0, 1), # 2 men -> 0
women = ifelse(partnum_A == 1, 0, 1)) # 1 women -> 0#men low
APIM_mlm1 <- lme(Partner_enhancement__A ~ men + low_zNPI_A + zNPI_P + zMonths_A +
low_zNPI_A:zMonths_A + zNPI_P:zMonths_A +
zNPI_P:men + zMonths_A:men +
zNPI_P:zMonths_A:men,
data = dyad_pairwise,
random = ~ 1 + men | dyadno,
weights = varIdent(form=~1|men),
method = "ML",
na.action = na.omit)
summary(APIM_mlm1)## Linear mixed-effects model fit by maximum likelihood
## Data: dyad_pairwise
## AIC BIC logLik
## 395.2186 442.0781 -182.6093
##
## Random effects:
## Formula: ~1 + men | dyadno
## Structure: General positive-definite, Log-Cholesky parametrization
## StdDev Corr
## (Intercept) 0.6094138 (Intr)
## men 1.1179381 -0.82
## Residual 0.3379449
##
## Variance function:
## Structure: Different standard deviations per stratum
## Formula: ~1 | men
## Parameter estimates:
## 1 0
## 1 1
## Fixed effects: Partner_enhancement__A ~ men + low_zNPI_A + zNPI_P + zMonths_A + low_zNPI_A:zMonths_A + zNPI_P:zMonths_A + zNPI_P:men + zMonths_A:men + zNPI_P:zMonths_A:men
## Value Std.Error DF t-value p-value
## (Intercept) 0.8576846 0.09869596 82 8.690169 0.0000
## men -0.8102312 0.13781311 76 -5.879202 0.0000
## low_zNPI_A -0.3091007 0.06271507 76 -4.928652 0.0000
## zNPI_P 0.1508311 0.07965190 76 1.893629 0.0621
## zMonths_A -0.4819683 0.10579704 82 -4.555593 0.0000
## low_zNPI_A:zMonths_A 0.1459862 0.06063174 76 2.407752 0.0185
## zNPI_P:zMonths_A 0.1648165 0.09155079 76 1.800274 0.0758
## men:zNPI_P 0.1586729 0.11658040 76 1.361060 0.1775
## men:zMonths_A 0.3651712 0.13913373 76 2.624605 0.0105
## men:zNPI_P:zMonths_A -0.3644525 0.11810013 76 -3.085962 0.0028
## Correlation:
## (Intr) men lw_NPI_A zNPI_P zMnt_A l_NPI_A: zNPI_P:
## men -0.603
## low_zNPI_A -0.595 -0.056
## zNPI_P 0.197 0.034 -0.364
## zMonths_A -0.041 -0.015 0.034 0.059
## low_zNPI_A:zMonths_A 0.037 0.030 -0.030 0.034 -0.660
## zNPI_P:zMonths_A 0.073 -0.094 0.060 0.023 0.145 -0.289
## men:zNPI_P 0.046 0.007 -0.048 -0.619 -0.078 0.019 -0.024
## men:zMonths_A -0.005 -0.008 0.023 -0.077 -0.642 0.076 0.020
## men:zNPI_P:zMonths_A -0.079 0.099 -0.022 -0.024 0.048 -0.015 -0.731
## mn:NPI_P mn:M_A
## men
## low_zNPI_A
## zNPI_P
## zMonths_A
## low_zNPI_A:zMonths_A
## zNPI_P:zMonths_A
## men:zNPI_P
## men:zMonths_A 0.096
## men:zNPI_P:zMonths_A -0.004 -0.100
##
## Standardized Within-Group Residuals:
## Min Q1 Med Q3 Max
## -1.262037622 -0.352956745 0.007859989 0.333944892 1.376911141
##
## Number of Observations: 168
## Number of Groups: 84#men high
APIM_mlm1 <- lme(Partner_enhancement__A ~ men + high_zNPI_A + zNPI_P + zMonths_A +
high_zNPI_A:zMonths_A + zNPI_P:zMonths_A +
zNPI_P:men + zMonths_A:men +
zNPI_P:zMonths_A:men,
data = dyad_pairwise,
random = ~ 1 + men | dyadno,
weights = varIdent(form=~1|men),
method = "ML",
na.action = na.omit)
summary(APIM_mlm1)## Linear mixed-effects model fit by maximum likelihood
## Data: dyad_pairwise
## AIC BIC logLik
## 395.2186 442.0781 -182.6093
##
## Random effects:
## Formula: ~1 + men | dyadno
## Structure: General positive-definite, Log-Cholesky parametrization
## StdDev Corr
## (Intercept) 0.6094138 (Intr)
## men 1.1179381 -0.82
## Residual 0.3379449
##
## Variance function:
## Structure: Different standard deviations per stratum
## Formula: ~1 | men
## Parameter estimates:
## 1 0
## 1 1
## Fixed effects: Partner_enhancement__A ~ men + high_zNPI_A + zNPI_P + zMonths_A + high_zNPI_A:zMonths_A + zNPI_P:zMonths_A + zNPI_P:men + zMonths_A:men + zNPI_P:zMonths_A:men
## Value Std.Error DF t-value p-value
## (Intercept) 0.2394831 0.10368206 82 2.309783 0.0234
## men -0.8102312 0.13781311 76 -5.879202 0.0000
## high_zNPI_A -0.3091007 0.06271507 76 -4.928652 0.0000
## zNPI_P 0.1508311 0.07965190 76 1.893629 0.0621
## zMonths_A -0.1899959 0.09464444 82 -2.007470 0.0480
## high_zNPI_A:zMonths_A 0.1459862 0.06063174 76 2.407752 0.0185
## zNPI_P:zMonths_A 0.1648165 0.09155079 76 1.800274 0.0758
## men:zNPI_P 0.1586729 0.11658040 76 1.361060 0.1775
## men:zMonths_A 0.3651712 0.13913373 76 2.624605 0.0105
## men:zNPI_P:zMonths_A -0.3644525 0.11810013 76 -3.085962 0.0028
## Correlation:
## (Intr) men hg_NPI_A zNPI_P zMnt_A h_NPI_A: zNPI_P:
## men -0.642
## high_zNPI_A 0.644 -0.056
## zNPI_P -0.253 0.034 -0.364
## zMonths_A 0.001 0.022 -0.001 0.109
## high_zNPI_A:zMonths_A -0.001 0.030 -0.030 0.034 0.543
## zNPI_P:zMonths_A 0.141 -0.094 0.060 0.023 -0.209 -0.289
## men:zNPI_P -0.014 0.007 -0.048 -0.619 -0.063 0.019 -0.024
## men:zMonths_A 0.023 -0.008 0.023 -0.077 -0.620 0.076 0.020
## men:zNPI_P:zMonths_A -0.101 0.099 -0.022 -0.024 0.035 -0.015 -0.731
## mn:NPI_P mn:M_A
## men
## high_zNPI_A
## zNPI_P
## zMonths_A
## high_zNPI_A:zMonths_A
## zNPI_P:zMonths_A
## men:zNPI_P
## men:zMonths_A 0.096
## men:zNPI_P:zMonths_A -0.004 -0.100
##
## Standardized Within-Group Residuals:
## Min Q1 Med Q3 Max
## -1.262037622 -0.352956745 0.007859989 0.333944892 1.376911141
##
## Number of Observations: 168
## Number of Groups: 84#women low
APIM_mlm1 <- lme(Partner_enhancement__A ~ women + low_zNPI_A + zNPI_P + zMonths_A +
low_zNPI_A:zMonths_A + zNPI_P:zMonths_A +
zNPI_P:women + zMonths_A:women +
zNPI_P:zMonths_A:women,
data = dyad_pairwise,
random = ~ 1 + women | dyadno,
weights = varIdent(form=~1|women),
method = "ML",
na.action = na.omit)
summary(APIM_mlm1)## Linear mixed-effects model fit by maximum likelihood
## Data: dyad_pairwise
## AIC BIC logLik
## 395.2186 442.0781 -182.6093
##
## Random effects:
## Formula: ~1 + women | dyadno
## Structure: General positive-definite, Log-Cholesky parametrization
## StdDev Corr
## (Intercept) 0.705298 (Intr)
## women 1.112223 -0.873
## Residual 0.347245
##
## Variance function:
## Structure: Different standard deviations per stratum
## Formula: ~1 | women
## Parameter estimates:
## 0 1
## 1 1
## Fixed effects: Partner_enhancement__A ~ women + low_zNPI_A + zNPI_P + zMonths_A + low_zNPI_A:zMonths_A + zNPI_P:zMonths_A + zNPI_P:women + zMonths_A:women + zNPI_P:zMonths_A:women
## Value Std.Error DF t-value p-value
## (Intercept) 0.0474534 0.11098503 82 0.427566 0.6701
## women 0.8102312 0.13781311 76 5.879202 0.0000
## low_zNPI_A -0.3091007 0.06271507 76 -4.928652 0.0000
## zNPI_P 0.3095041 0.09182388 76 3.370627 0.0012
## zMonths_A -0.1167971 0.10800398 82 -1.081415 0.2827
## low_zNPI_A:zMonths_A 0.1459862 0.06063174 76 2.407752 0.0185
## zNPI_P:zMonths_A -0.1996360 0.08081574 76 -2.470262 0.0157
## women:zNPI_P -0.1586729 0.11658040 76 -1.361060 0.1775
## women:zMonths_A -0.3651712 0.13913373 76 -2.624605 0.0105
## women:zNPI_P:zMonths_A 0.3644525 0.11810013 76 3.085962 0.0028
## Correlation:
## (Intr) women lw_NPI_A zNPI_P zMnt_A l_NPI_A: zNPI_P:
## women -0.705
## low_zNPI_A -0.598 0.056
## zNPI_P 0.253 -0.039 -0.377
## zMonths_A -0.072 0.025 0.063 0.023
## low_zNPI_A:zMonths_A 0.071 -0.030 -0.030 0.054 -0.549
## zNPI_P:zMonths_A 0.018 -0.038 0.036 -0.049 0.070 -0.349
## women:zNPI_P -0.050 0.007 0.048 -0.732 -0.047 -0.019 0.033
## women:zMonths_A 0.014 -0.008 -0.023 -0.054 -0.660 -0.076 0.124
## women:zNPI_P:zMonths_A -0.053 0.099 0.022 0.026 0.082 0.015 -0.634
## wm:NPI_P wm:M_A
## women
## low_zNPI_A
## zNPI_P
## zMonths_A
## low_zNPI_A:zMonths_A
## zNPI_P:zMonths_A
## women:zNPI_P
## women:zMonths_A 0.096
## women:zNPI_P:zMonths_A -0.004 -0.100
##
## Standardized Within-Group Residuals:
## Min Q1 Med Q3 Max
## -1.296768672 -0.362670051 0.008076295 0.343134995 1.414803485
##
## Number of Observations: 168
## Number of Groups: 84#women high
APIM_mlm1 <- lme(Partner_enhancement__A ~ women + high_zNPI_A + zNPI_P + zMonths_A +
high_zNPI_A:zMonths_A + zNPI_P:zMonths_A +
zNPI_P:women + zMonths_A:women +
zNPI_P:zMonths_A:women,
data = dyad_pairwise,
random = ~ 1 + women | dyadno,
weights = varIdent(form=~1|women),
method = "ML",
na.action = na.omit)
summary(APIM_mlm1)## Linear mixed-effects model fit by maximum likelihood
## Data: dyad_pairwise
## AIC BIC logLik
## 395.2186 442.0781 -182.6093
##
## Random effects:
## Formula: ~1 + women | dyadno
## Structure: General positive-definite, Log-Cholesky parametrization
## StdDev Corr
## (Intercept) 0.705298 (Intr)
## women 1.112223 -0.873
## Residual 0.347245
##
## Variance function:
## Structure: Different standard deviations per stratum
## Formula: ~1 | women
## Parameter estimates:
## 0 1
## 1 1
## Fixed effects: Partner_enhancement__A ~ women + high_zNPI_A + zNPI_P + zMonths_A + high_zNPI_A:zMonths_A + zNPI_P:zMonths_A + zNPI_P:women + zMonths_A:women + zNPI_P:zMonths_A:women
## Value Std.Error DF t-value p-value
## (Intercept) -0.5707480 0.10678671 82 -5.344748 0.0000
## women 0.8102312 0.13781311 76 5.879202 0.0000
## high_zNPI_A -0.3091007 0.06271507 76 -4.928652 0.0000
## zNPI_P 0.3095041 0.09182388 76 3.370627 0.0012
## zMonths_A 0.1751752 0.10954399 82 1.599131 0.1136
## high_zNPI_A:zMonths_A 0.1459862 0.06063174 76 2.407752 0.0185
## zNPI_P:zMonths_A -0.1996360 0.08081574 76 -2.470262 0.0157
## women:zNPI_P -0.1586729 0.11658040 76 -1.361060 0.1775
## women:zMonths_A -0.3651712 0.13913373 76 -2.624605 0.0105
## women:zNPI_P:zMonths_A 0.3644525 0.11810013 76 3.085962 0.0028
## Correlation:
## (Intr) women hg_NPI_A zNPI_P zMnt_A h_NPI_A: zNPI_P:
## women -0.667
## high_zNPI_A 0.553 0.056
## zNPI_P -0.180 -0.039 -0.377
## zMonths_A 0.041 -0.009 0.029 0.082
## high_zNPI_A:zMonths_A 0.038 -0.030 -0.030 0.054 0.566
## zNPI_P:zMonths_A 0.061 -0.038 0.036 -0.049 -0.317 -0.349
## women:zNPI_P 0.004 0.007 0.048 -0.732 -0.067 -0.019 0.033
## women:zMonths_A -0.012 -0.008 -0.023 -0.054 -0.735 -0.076 0.124
## women:zNPI_P:zMonths_A -0.030 0.099 0.022 0.026 0.097 0.015 -0.634
## wm:NPI_P wm:M_A
## women
## high_zNPI_A
## zNPI_P
## zMonths_A
## high_zNPI_A:zMonths_A
## zNPI_P:zMonths_A
## women:zNPI_P
## women:zMonths_A 0.096
## women:zNPI_P:zMonths_A -0.004 -0.100
##
## Standardized Within-Group Residuals:
## Min Q1 Med Q3 Max
## -1.296768672 -0.362670051 0.008076295 0.343134995 1.414803485
##
## Number of Observations: 168
## Number of Groups: 84