## Loading required package: Matrix
## Loading required package: mvtnorm
## Loading required package: TH.data
IPV/Sex/CES1 ##Depression as a dichotomous variable
mm2 = lmer(log(TrailsAtestSec) ~ Age + IPVstatus + PovStat + Sex + CES1 + (Age |
HNDid) + (1 | subclass) + Age:IPVstatus + Age:PovStat + Age:Sex + Age:CES1 +
IPVstatus:PovStat + IPVstatus:Sex + IPVstatus:CES1 + PovStat:Sex + PovStat:CES1 +
Sex:CES1 + Age:IPVstatus:PovStat + Age:IPVstatus:Sex + Age:IPVstatus:CES1 +
Age:PovStat:Sex + Age:Sex:CES1 + IPVstatus:PovStat:Sex + IPVstatus:Sex:CES1 +
PovStat:Sex:CES1 + Age:IPVstatus:PovStat:Sex + Age:IPVstatus:Sex:CES1, data = IPVandCognitionDataSet2,
na.action = na.omit)
## Warning: number of observations <= rank(Z); variance-covariance matrix
## will be unidentifiable
cftest(mm2)
##
## Simultaneous Tests for General Linear Hypotheses
##
## Fit: lmer(formula = log(TrailsAtestSec) ~ Age + IPVstatus + PovStat +
## Sex + CES1 + (Age | HNDid) + (1 | subclass) + Age:IPVstatus +
## Age:PovStat + Age:Sex + Age:CES1 + IPVstatus:PovStat + IPVstatus:Sex +
## IPVstatus:CES1 + PovStat:Sex + PovStat:CES1 + Sex:CES1 +
## Age:IPVstatus:PovStat + Age:IPVstatus:Sex + Age:IPVstatus:CES1 +
## Age:PovStat:Sex + Age:Sex:CES1 + IPVstatus:PovStat:Sex +
## IPVstatus:Sex:CES1 + PovStat:Sex:CES1 + Age:IPVstatus:PovStat:Sex +
## Age:IPVstatus:Sex:CES1, data = IPVandCognitionDataSet2, na.action = na.omit)
##
## Linear Hypotheses:
## Estimate Std. Error z value
## (Intercept) == 0 3.33888 0.15151 22.04
## Age == 0 0.01541 0.01058 1.46
## IPVstatus1 == 0 0.52046 0.27764 1.87
## PovStatBelow == 0 0.06531 0.22812 0.29
## SexMen == 0 0.04786 0.20260 0.24
## CES11 == 0 0.56162 0.21589 2.60
## Age:IPVstatus1 == 0 0.04911 0.02308 2.13
## Age:PovStatBelow == 0 -0.02151 0.01582 -1.36
## Age:SexMen == 0 -0.00831 0.01538 -0.54
## Age:CES11 == 0 0.02193 0.01553 1.41
## IPVstatus1:PovStatBelow == 0 1.11844 0.43889 2.55
## IPVstatus1:SexMen == 0 -0.50893 0.59436 -0.86
## IPVstatus1:CES11 == 0 -1.12804 0.36396 -3.10
## PovStatBelow:SexMen == 0 0.31044 0.33102 0.94
## PovStatBelow:CES11 == 0 -0.43739 0.16015 -2.73
## SexMen:CES11 == 0 -0.86284 0.36807 -2.34
## Age:IPVstatus1:PovStatBelow == 0 0.11210 0.03810 2.94
## Age:IPVstatus1:SexMen == 0 -0.06167 0.04061 -1.52
## Age:IPVstatus1:CES11 == 0 -0.10191 0.02999 -3.40
## Age:PovStatBelow:SexMen == 0 0.02842 0.02713 1.05
## Age:SexMen:CES11 == 0 -0.03213 0.03002 -1.07
## IPVstatus1:PovStatBelow:SexMen == 0 -1.02604 0.63179 -1.62
## IPVstatus1:SexMen:CES11 == 0 1.50363 0.58314 2.58
## PovStatBelow:SexMen:CES11 == 0 0.59532 0.36539 1.63
## Age:IPVstatus1:PovStatBelow:SexMen == 0 -0.08707 0.05190 -1.68
## Age:IPVstatus1:SexMen:CES11 == 0 0.15271 0.04701 3.25
## Pr(>|z|)
## (Intercept) == 0 < 2e-16
## Age == 0 0.14498
## IPVstatus1 == 0 0.06085
## PovStatBelow == 0 0.77464
## SexMen == 0 0.81324
## CES11 == 0 0.00928
## Age:IPVstatus1 == 0 0.03337
## Age:PovStatBelow == 0 0.17382
## Age:SexMen == 0 0.58884
## Age:CES11 == 0 0.15774
## IPVstatus1:PovStatBelow == 0 0.01082
## IPVstatus1:SexMen == 0 0.39185
## IPVstatus1:CES11 == 0 0.00194
## PovStatBelow:SexMen == 0 0.34833
## PovStatBelow:CES11 == 0 0.00631
## SexMen:CES11 == 0 0.01907
## Age:IPVstatus1:PovStatBelow == 0 0.00326
## Age:IPVstatus1:SexMen == 0 0.12883
## Age:IPVstatus1:CES11 == 0 0.00068
## Age:PovStatBelow:SexMen == 0 0.29474
## Age:SexMen:CES11 == 0 0.28449
## IPVstatus1:PovStatBelow:SexMen == 0 0.10437
## IPVstatus1:SexMen:CES11 == 0 0.00992
## PovStatBelow:SexMen:CES11 == 0 0.10325
## Age:IPVstatus1:PovStatBelow:SexMen == 0 0.09343
## Age:IPVstatus1:SexMen:CES11 == 0 0.00116
## (Univariate p values reported)
pCES1 = (c(0, 1))
hatIPVcog1 = zMixHat(IPVandCognitionDataSet2, mm2, vary = "CES1=pCES1,IPVstatus=zQ(0,1),Sex=zQ(Women,Men)",
fixedCov = c("PovStat", "Age"))
head(hatIPVcog1)
## CES1 IPVstatus Sex log TrailsAtestSec PovStat Age hat
## 1 0 0 Women 0 0 0.3333 -7.111 3.302
## 2 1 0 Women 0 0 0.3333 -7.111 3.562
## 3 0 1 Women 0 0 0.3333 -7.111 3.580
## 4 1 1 Women 0 0 0.3333 -7.111 3.437
## 5 0 0 Men 0 0 0.3333 -7.111 3.445
## 6 1 0 Men 0 0 0.3333 -7.111 3.269
par(mar = c(4, 4, 0.5, 2), las = 1, lwd = 2)
HNDcolors = HNDpltColors()
with(hatIPVcog1[hatIPVcog1$Sex == "Women" & hatIPVcog1$IPVstatus == "0", ],
plot(CES1, hat, lty = 1, col = "red", type = "l", ylim = c(3, 4), ylab = "log(Trails A)",
xlab = "Depression"))
with(hatIPVcog1[hatIPVcog1$Sex == "Women" & hatIPVcog1$IPVstatus == "1", ],
lines(CES1, hat, lty = 2, col = "red"))
with(hatIPVcog1[hatIPVcog1$Sex == "Men" & hatIPVcog1$IPVstatus == "0", ], lines(CES1,
hat, lty = 1, col = "blue", typ = "l", ylim = c(3, 4), ylab = "Trails A",
xlab = "Depression"))
with(hatIPVcog1[hatIPVcog1$Sex == "Men" & hatIPVcog1$IPVstatus == "1", ], lines(CES1,
hat, lty = 2, col = "blue"))
legend(0, 4, zQ(NoIPV, IPV), lty = 1:2, col = "black", cex = 0.9, bty = "n")
text(0, 3, "Women in red", adj = c(0, 0), col = "red", cex = 0.95)
text(0, 3.1, "Men in blue", adj = c(0, 0), col = "blue", cex = 0.95)
IPV/Sex/w1CES ##Depression as a continous variable
(mm2 = lmer(log(TrailsAtestSec) ~ Age + IPVstatus + PovStat + Sex + w1CES +
(Age | HNDid) + (1 | subclass) + Age:IPVstatus + Age:PovStat + Age:Sex +
Age:w1CES + IPVstatus:PovStat + IPVstatus:Sex + IPVstatus:w1CES + Sex:w1CES +
Age:IPVstatus:PovStat + Age:IPVstatus:Sex + Age:IPVstatus:w1CES + Age:Sex:w1CES +
IPVstatus:Sex:w1CES + Age:IPVstatus:Sex:w1CES, data = IPVandCognitionDataSet2,
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 + IPVstatus + PovStat + Sex + w1CES + (Age | HNDid) + (1 | subclass) + Age:IPVstatus + Age:PovStat + Age:Sex + Age:w1CES + IPVstatus:PovStat + IPVstatus:Sex + IPVstatus:w1CES + Sex:w1CES + Age:IPVstatus:PovStat + Age:IPVstatus:Sex + Age:IPVstatus:w1CES + Age:Sex:w1CES + IPVstatus:Sex:w1CES + Age:IPVstatus:Sex:w1CES
## Data: IPVandCognitionDataSet2
## REML criterion at convergence: 159
## Random effects:
## Groups Name Std.Dev. Corr
## HNDid (Intercept) 0.3410
## Age 0.0115 1.00
## subclass (Intercept) 0.1467
## Residual 0.1837
## Number of obs: 126, groups: HNDid, 63; subclass, 21
## Fixed Effects:
## (Intercept) Age
## 3.23474 -0.00926
## IPVstatus1 PovStatBelow
## 0.59224 0.12779
## SexMen w1CES
## 0.24496 0.01678
## Age:IPVstatus1 Age:PovStatBelow
## 0.07240 -0.00362
## Age:SexMen Age:w1CES
## 0.02460 0.00188
## IPVstatus1:PovStatBelow IPVstatus1:SexMen
## 0.51803 -1.22585
## IPVstatus1:w1CES SexMen:w1CES
## -0.02898 -0.01930
## Age:IPVstatus1:PovStatBelow Age:IPVstatus1:SexMen
## 0.06480 -0.18358
## Age:IPVstatus1:w1CES Age:SexMen:w1CES
## -0.00377 -0.00202
## IPVstatus1:SexMen:w1CES Age:IPVstatus1:SexMen:w1CES
## 0.05989 0.00934
cftest(mm2)
##
## Simultaneous Tests for General Linear Hypotheses
##
## Fit: lmer(formula = log(TrailsAtestSec) ~ Age + IPVstatus + PovStat +
## Sex + w1CES + (Age | HNDid) + (1 | subclass) + Age:IPVstatus +
## Age:PovStat + Age:Sex + Age:w1CES + IPVstatus:PovStat + IPVstatus:Sex +
## IPVstatus:w1CES + Sex:w1CES + Age:IPVstatus:PovStat + Age:IPVstatus:Sex +
## Age:IPVstatus:w1CES + Age:Sex:w1CES + IPVstatus:Sex:w1CES +
## Age:IPVstatus:Sex:w1CES, data = IPVandCognitionDataSet2,
## na.action = na.omit)
##
## Linear Hypotheses:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) == 0 3.234740 0.207111 15.62 <2e-16
## Age == 0 -0.009256 0.015190 -0.61 0.5423
## IPVstatus1 == 0 0.592244 0.342083 1.73 0.0834
## PovStatBelow == 0 0.127786 0.165636 0.77 0.4404
## SexMen == 0 0.244959 0.264289 0.93 0.3540
## w1CES == 0 0.016780 0.012633 1.33 0.1841
## Age:IPVstatus1 == 0 0.072400 0.026810 2.70 0.0069
## Age:PovStatBelow == 0 -0.003617 0.012381 -0.29 0.7702
## Age:SexMen == 0 0.024600 0.021262 1.16 0.2473
## Age:w1CES == 0 0.001883 0.000927 2.03 0.0421
## IPVstatus1:PovStatBelow == 0 0.518027 0.310930 1.67 0.0957
## IPVstatus1:SexMen == 0 -1.225849 0.772723 -1.59 0.1126
## IPVstatus1:w1CES == 0 -0.028981 0.016014 -1.81 0.0703
## SexMen:w1CES == 0 -0.019301 0.016452 -1.17 0.2407
## Age:IPVstatus1:PovStatBelow == 0 0.064801 0.025357 2.56 0.0106
## Age:IPVstatus1:SexMen == 0 -0.183584 0.061337 -2.99 0.0028
## Age:IPVstatus1:w1CES == 0 -0.003772 0.001248 -3.02 0.0025
## Age:SexMen:w1CES == 0 -0.002018 0.001394 -1.45 0.1477
## IPVstatus1:SexMen:w1CES == 0 0.059888 0.039541 1.51 0.1299
## Age:IPVstatus1:SexMen:w1CES == 0 0.009339 0.003412 2.74 0.0062
## (Univariate p values reported)
# pw1CES=seq(0,46)
hatIPVcog1 = zMixHat(IPVandCognitionDataSet2, mm2, vary = "w1CES=seq(0,46),IPVstatus=zQ(0,1),Sex=zQ(Women,Men)",
fixedCov = c("PovStat", "Age"))
head(hatIPVcog1)
## w1CES IPVstatus Sex log TrailsAtestSec PovStat Age hat
## 1 0 0 Women 0 0 0.3333 -7.111 3.352
## 2 1 0 Women 0 0 0.3333 -7.111 3.355
## 3 2 0 Women 0 0 0.3333 -7.111 3.359
## 4 3 0 Women 0 0 0.3333 -7.111 3.362
## 5 4 0 Women 0 0 0.3333 -7.111 3.365
## 6 5 0 Women 0 0 0.3333 -7.111 3.369
par(mar = c(4, 4, 0.5, 2), las = 1, lwd = 2)
HNDcolors = HNDpltColors()
with(hatIPVcog1[hatIPVcog1$Sex == "Women" & hatIPVcog1$IPVstatus == "0", ],
plot(w1CES, hat, lty = 1, col = "red", type = "l", ylim = c(3, 4), ylab = "log(Trails A)",
xlab = "CES-D Score"))
with(hatIPVcog1[hatIPVcog1$Sex == "Women" & hatIPVcog1$IPVstatus == "1", ],
lines(w1CES, hat, lty = 2, col = "red"))
with(hatIPVcog1[hatIPVcog1$Sex == "Men" & hatIPVcog1$IPVstatus == "0", ], lines(w1CES,
hat, lty = 1, col = "blue", typ = "l", ylim = c(3, 4), ylab = "Trails A",
xlab = "CES-D Score"))
with(hatIPVcog1[hatIPVcog1$Sex == "Men" & hatIPVcog1$IPVstatus == "1", ], lines(w1CES,
hat, lty = 2, col = "blue"))
legend(0, 4, zQ(NoIPV, IPV), lty = 1:2, col = "black", cex = 0.9, bty = "n")
text(0, 3, "Women in red", adj = c(0, 0), col = "red", cex = 0.95)
text(0, 3.1, "Men in blue", adj = c(0, 0), col = "blue", cex = 0.95)
