## Loading required package: Matrix
## Loading required package: mvtnorm
## Loading required package: TH.data
## Warning: number of observations <= rank(Z); variance-covariance matrix
## will be unidentifiable
## Linear mixed model fit by REML ['lmerMod']
## Formula: log(TrailsAtestSec) ~ Age + IPVstatus + PovStat + CES1 + (Age | HNDid) + (1 | subclass) + Age:IPVstatus + Age:PovStat + Age:CES1 + IPVstatus:PovStat + IPVstatus:CES1 + PovStat:CES1 + Age:IPVstatus:PovStat + Age:IPVstatus:CES1
## Data: WomenlogTrailsA
## REML criterion at convergence: 72.71
## Random effects:
## Groups Name Std.Dev. Corr
## HNDid (Intercept) 0.307
## Age 0.019 1.00
## subclass (Intercept) 0.252
## Residual 0.206
## Number of obs: 72, groups: HNDid, 36; subclass, 19
## Fixed Effects:
## (Intercept) Age
## 3.3549 0.0108
## IPVstatus1 PovStatBelow
## 0.5179 -0.0470
## CES11 Age:IPVstatus1
## 0.5437 0.0457
## Age:PovStatBelow Age:CES11
## -0.0195 0.0263
## IPVstatus1:PovStatBelow IPVstatus1:CES11
## 1.1428 -1.1419
## PovStatBelow:CES11 Age:IPVstatus1:PovStatBelow
## -0.3517 0.1122
## Age:IPVstatus1:CES11
## -0.1001
##
## Simultaneous Tests for General Linear Hypotheses
##
## Fit: lmer(formula = log(TrailsAtestSec) ~ Age + IPVstatus + PovStat +
## CES1 + (Age | HNDid) + (1 | subclass) + Age:IPVstatus + Age:PovStat +
## Age:CES1 + IPVstatus:PovStat + IPVstatus:CES1 + PovStat:CES1 +
## Age:IPVstatus:PovStat + Age:IPVstatus:CES1, data = WomenlogTrailsA,
## na.action = na.omit)
##
## Linear Hypotheses:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) == 0 3.3549 0.1673 20.05 <2e-16
## Age == 0 0.0108 0.0124 0.87 0.3823
## IPVstatus1 == 0 0.5179 0.2980 1.74 0.0822
## PovStatBelow == 0 -0.0470 0.2542 -0.19 0.8532
## CES11 == 0 0.5437 0.2359 2.30 0.0212
## Age:IPVstatus1 == 0 0.0457 0.0253 1.81 0.0703
## Age:PovStatBelow == 0 -0.0195 0.0180 -1.09 0.2774
## Age:CES11 == 0 0.0263 0.0174 1.51 0.1314
## IPVstatus1:PovStatBelow == 0 1.1428 0.4827 2.37 0.0179
## IPVstatus1:CES11 == 0 -1.1419 0.3943 -2.90 0.0038
## PovStatBelow:CES11 == 0 -0.3517 0.1655 -2.12 0.0336
## Age:IPVstatus1:PovStatBelow == 0 0.1122 0.0427 2.63 0.0085
## Age:IPVstatus1:CES11 == 0 -0.1001 0.0331 -3.02 0.0025
## (Univariate p values reported)
Age/IPV/Depression Note: Age/IPV/Depression interaction was significant for women
hatIPVcog1 = zMixHat(WomenlogTrailsA, mm2, vary = "Age=pAge, CES1=zQ(0,1),IPVstatus=zQ(0,1)",
fixedCov = c("PovStat"))
head(hatIPVcog1)
## Age CES1 IPVstatus log TrailsAtestSec PovStat hat
## 1 30 0 0 0 0 0.3333 3.468
## 2 31 0 0 0 0 0.3333 3.472
## 3 32 0 0 0 0 0.3333 3.476
## 4 33 0 0 0 0 0.3333 3.481
## 5 34 0 0 0 0 0.3333 3.485
## 6 35 0 0 0 0 0.3333 3.489
par(mar = c(4, 4, 0.5, 2), las = 1, lwd = 2)
HNDcolors = HNDpltColors()
with(hatIPVcog1[hatIPVcog1$CES1 == "0" & hatIPVcog1$IPVstatus == "0", ], plot(pAge,
hat, lty = 1, col = "black", type = "l", ylim = c(2, 12), ylab = "log(Trails A)",
xlab = "Age"))
with(hatIPVcog1[hatIPVcog1$CES1 == "0" & hatIPVcog1$IPVstatus == "1", ], lines(pAge,
hat, lty = 2, col = "red"))
with(hatIPVcog1[hatIPVcog1$CES1 == "1" & hatIPVcog1$IPVstatus == "0", ], lines(pAge,
hat, lty = 3, col = "black"))
with(hatIPVcog1[hatIPVcog1$CES1 == "1" & hatIPVcog1$IPVstatus == "1", ], lines(pAge,
hat, lty = 4, col = "red"))
legend(30, 12, zQ(nonDepressednoIPV, nonDepressedIPV, DepressednoIPV, DepressedIPV),
lty = 1:4, col = "black", cex = 0.95)
text(30, 2.5, "IPV in red", adj = c(0, 0), col = "red", cex = 0.95)
text(30, 2, "No IPV in black", adj = c(0, 0), col = "black", cex = 0.95)
library("lme4")
library("multcomp")
library("zStat")
load(file = "~/Desktop/Megan/Research/IPV and Cognition Paper/IPV R Output/MenlogTrailsA.rda")
(mm3 = lmer(log(TrailsAtestSec) ~ (Age + PovStat + IPVstatus + CES1)^4 + (Age |
HNDid) + (1 | subclass), data = MenlogTrailsA, na.action = na.omit))
## Warning: number of observations <= rank(Z); variance-covariance matrix
## will be unidentifiable
## Linear mixed model fit by REML ['lmerMod']
## Formula: log(TrailsAtestSec) ~ (Age + PovStat + IPVstatus + CES1)^4 + (Age | HNDid) + (1 | subclass)
## Data: MenlogTrailsA
## REML criterion at convergence: 43.18
## Random effects:
## Groups Name Std.Dev. Corr
## HNDid (Intercept) 0.3157
## Age 0.0132 0.73
## subclass (Intercept) 0.0000
## Residual 0.1391
## Number of obs: 54, groups: HNDid, 27; subclass, 17
## Fixed Effects:
## (Intercept) Age
## 3.447849 0.012913
## PovStatBelow IPVstatus1
## 0.260888 0.189737
## CES11 Age:PovStatBelow
## -0.192804 -0.000304
## Age:IPVstatus1 Age:CES11
## -0.012913 -0.008476
## PovStatBelow:IPVstatus1 PovStatBelow:CES11
## -0.235889 0.015006
## IPVstatus1:CES11 Age:PovStatBelow:IPVstatus1
## 0.072469 0.010065
## Age:PovStatBelow:CES11 Age:IPVstatus1:CES11
## 0.015395 0.039516
## PovStatBelow:IPVstatus1:CES11 Age:PovStatBelow:IPVstatus1:CES11
## 0.466554 -0.010697
cftest(mm3)
##
## Simultaneous Tests for General Linear Hypotheses
##
## Fit: lmer(formula = log(TrailsAtestSec) ~ (Age + PovStat + IPVstatus +
## CES1)^4 + (Age | HNDid) + (1 | subclass), data = MenlogTrailsA,
## na.action = na.omit)
##
## Linear Hypotheses:
## Estimate Std. Error z value
## (Intercept) == 0 3.447849 0.133653 25.80
## Age == 0 0.012913 0.010736 1.20
## PovStatBelow == 0 0.260888 0.235508 1.11
## IPVstatus1 == 0 0.189737 0.908793 0.21
## CES11 == 0 -0.192804 0.299159 -0.64
## Age:PovStatBelow == 0 -0.000304 0.021713 -0.01
## Age:IPVstatus1 == 0 -0.012913 0.052026 -0.25
## Age:CES11 == 0 -0.008476 0.024836 -0.34
## PovStatBelow:IPVstatus1 == 0 -0.235889 0.970372 -0.24
## PovStatBelow:CES11 == 0 0.015006 0.434551 0.03
## IPVstatus1:CES11 == 0 0.072469 0.972183 0.07
## Age:PovStatBelow:IPVstatus1 == 0 0.010065 0.058693 0.17
## Age:PovStatBelow:CES11 == 0 0.015395 0.044577 0.35
## Age:IPVstatus1:CES11 == 0 0.039516 0.060233 0.66
## PovStatBelow:IPVstatus1:CES11 == 0 0.466554 1.085133 0.43
## Age:PovStatBelow:IPVstatus1:CES11 == 0 -0.010697 0.078571 -0.14
## Pr(>|z|)
## (Intercept) == 0 <2e-16
## Age == 0 0.23
## PovStatBelow == 0 0.27
## IPVstatus1 == 0 0.83
## CES11 == 0 0.52
## Age:PovStatBelow == 0 0.99
## Age:IPVstatus1 == 0 0.80
## Age:CES11 == 0 0.73
## PovStatBelow:IPVstatus1 == 0 0.81
## PovStatBelow:CES11 == 0 0.97
## IPVstatus1:CES11 == 0 0.94
## Age:PovStatBelow:IPVstatus1 == 0 0.86
## Age:PovStatBelow:CES11 == 0 0.73
## Age:IPVstatus1:CES11 == 0 0.51
## PovStatBelow:IPVstatus1:CES11 == 0 0.67
## Age:PovStatBelow:IPVstatus1:CES11 == 0 0.89
## (Univariate p values reported)
pAge = seq(30, 70)
Age/IPV/Depression Note: Age/IPV/Depression interaction was NOT significant for Men
hatIPVcog1 = zMixHat(MenlogTrailsA, mm3, vary = "Age=pAge, CES1=zQ(0,1),IPVstatus=zQ(0,1)",
fixedCov = c("PovStat"))
head(hatIPVcog1)
## Age CES1 IPVstatus log TrailsAtestSec PovStat hat
## 1 30 0 0 0 0 0.3333 3.919
## 2 31 0 0 0 0 0.3333 3.932
## 3 32 0 0 0 0 0.3333 3.945
## 4 33 0 0 0 0 0.3333 3.958
## 5 34 0 0 0 0 0.3333 3.970
## 6 35 0 0 0 0 0.3333 3.983
par(mar = c(4, 4, 0.5, 2), las = 1, lwd = 2)
HNDcolors = HNDpltColors()
with(hatIPVcog1[hatIPVcog1$CES1 == "0" & hatIPVcog1$IPVstatus == "0", ], plot(pAge,
hat, lty = 1, col = "black", type = "l", ylim = c(2, 12), ylab = "log(Trails A)",
xlab = "Age"))
with(hatIPVcog1[hatIPVcog1$CES1 == "0" & hatIPVcog1$IPVstatus == "1", ], lines(pAge,
hat, lty = 2, col = "red"))
with(hatIPVcog1[hatIPVcog1$CES1 == "1" & hatIPVcog1$IPVstatus == "0", ], lines(pAge,
hat, lty = 3, col = "black"))
with(hatIPVcog1[hatIPVcog1$CES1 == "1" & hatIPVcog1$IPVstatus == "1", ], lines(pAge,
hat, lty = 4, col = "red"))
legend(30, 12, zQ(nonDepressednoIPV, nonDepressedIPV, DepressednoIPV, DepressedIPV),
lty = 1:4, col = "black", cex = 0.95)
text(30, 2.5, "IPV in red", adj = c(0, 0), col = "red", cex = 0.95)
text(30, 2, "No IPV in black", adj = c(0, 0), col = "black", cex = 0.95)
