Trails A Regression Model 1
## Loading required package: Matrix
## KernSmooth 2.23 loaded
## Copyright M. P. Wand 1997-2009
##
## Attaching package: 'lmerTest'
##
## The following object is masked from 'package:lme4':
##
## lmer
##
## The following object is masked from 'package:stats':
##
## step
## Warning: number of observations <= rank(Z); variance-covariance matrix
## will be unidentifiable
## Linear mixed model fit by REML ['merModLmerTest']
## Formula: log(TrailsAtestSec) ~ (Age + IPVstatus + Sex + PovStat)^4 + (Age | HNDid) + (1 | subclass)
## Data: IPVandCognitionDataSet2
## REML criterion at convergence: 103.5
## Random effects:
## Groups Name Std.Dev. Corr
## HNDid (Intercept) 0.27421
## Age 0.00662 1.00
## subclass (Intercept) 0.14108
## Residual 0.20312
## Number of obs: 126, groups: HNDid, 63; subclass, 21
## Fixed Effects:
## (Intercept) Age
## 3.53162 0.02061
## IPVstatus1 SexMen
## -0.00392 -0.18138
## PovStatBelow Age:IPVstatus1
## -0.01420 0.00338
## Age:SexMen Age:PovStatBelow
## -0.01396 -0.01079
## IPVstatus1:SexMen IPVstatus1:PovStatBelow
## 0.04364 0.66546
## SexMen:PovStatBelow Age:IPVstatus1:SexMen
## 0.35515 -0.00607
## Age:IPVstatus1:PovStatBelow Age:SexMen:PovStatBelow
## 0.07740 0.02387
## IPVstatus1:SexMen:PovStatBelow Age:IPVstatus1:SexMen:PovStatBelow
## -0.40109 -0.06114
## Warning: number of observations <= rank(Z); variance-covariance matrix will be unidentifiable
## Warning: number of observations <= rank(Z); variance-covariance matrix will be unidentifiable
## Random term (Age | HNDid) was eliminated because of having correlation +-1 or NaN
## Warning: number of observations <= rank(Z); variance-covariance matrix
## will be unidentifiable
## Random term (Age + 0 | HNDid) was eliminated because of standard deviation being equal to 0
##
## Random effects:
## Chi.sq Chi.DF elim.num p.value
## (1 | subclass) 2.55 1 1 0.1101
## (1 | HNDid) 26.81 1 kept 0
##
## Fixed effects:
## Sum Sq Mean Sq NumDF DenDF F.value elim.num
## Age:IPVstatus:Sex:PovStat 0.0722 0.0722 1 109.93 1.7241 1
## IPVstatus:Sex:PovStat 0.0000 0.0000 1 56.04 0.0001 2
## Age:Sex:PovStat 0.0053 0.0053 1 107.15 0.1515 3
## Sex:PovStat 0.0488 0.0488 1 59.32 1.0868 4
## Age:IPVstatus:PovStat 0.0600 0.0600 1 111.44 1.3370 5
## IPVstatus:PovStat 0.0077 0.0077 1 57.34 0.4131 6
## Age:IPVstatus:Sex 0.0371 0.0371 1 108.84 0.8580 7
## Age:Sex 0.0161 0.0161 1 108.88 0.4100 8
## IPVstatus:Sex 0.0300 0.0300 1 56.88 0.7868 9
## Sex 0.0049 0.0049 1 58.63 0.0620 10
## Age:PovStat 0.0459 0.0459 1 105.01 1.2169 11
## Age:IPVstatus 0.1040 0.1040 1 110.91 2.5045 12
## IPVstatus 0.0301 0.0301 1 59.40 0.7619 13
## PovStat 0.1483 0.1483 1 61.40 3.6656 14
## Age 0.9273 0.9273 1 111.16 22.2550 kept
## Pr(>F)
## Age:IPVstatus:Sex:PovStat 0.1919
## IPVstatus:Sex:PovStat 0.9906
## Age:Sex:PovStat 0.6979
## Sex:PovStat 0.3014
## Age:IPVstatus:PovStat 0.2500
## IPVstatus:PovStat 0.5229
## Age:IPVstatus:Sex 0.3563
## Age:Sex 0.5233
## IPVstatus:Sex 0.3788
## Sex 0.8042
## Age:PovStat 0.2725
## Age:IPVstatus 0.1164
## IPVstatus 0.3862
## PovStat 0.0602
## Age 0
##
## Least squares means:
## Estimate Standard Error DF t-value Lower CI Upper CI p-value
##
## Differences of LSMEANS:
## Estimate Standard Error DF t-value Lower CI Upper CI p-value
##
## Final model:
## lme4::lmer(formula = log(TrailsAtestSec) ~ Age + (1 | HNDid),
## data = IPVandCognitionDataSet2, REML = reml, contrasts = l)
Re-run final Model 1
(mm1 = lmer(log(TrailsAtestSec) ~ Age + (Age | HNDid) + (1 | subclass), data = IPVandCognitionDataSet2))
## Warning: number of observations <= rank(Z); variance-covariance matrix
## will be unidentifiable
## Linear mixed model fit by REML ['merModLmerTest']
## Formula: log(TrailsAtestSec) ~ Age + (Age | HNDid) + (1 | subclass)
## Data: IPVandCognitionDataSet2
## REML criterion at convergence: 60.05
## Random effects:
## Groups Name Std.Dev. Corr
## HNDid (Intercept) 0.30701
## Age 0.00866 1.00
## subclass (Intercept) 0.09158
## Residual 0.20512
## Number of obs: 126, groups: HNDid, 63; subclass, 21
## Fixed Effects:
## (Intercept) Age
## 3.5571 0.0195
summary(mm1)
## Warning: number of observations <= rank(Z); variance-covariance matrix will be unidentifiable
## Warning: number of observations <= rank(Z); variance-covariance matrix will be unidentifiable
## Linear mixed model fit by REML ['merModLmerTest']
## Formula: log(TrailsAtestSec) ~ Age + (Age | HNDid) + (1 | subclass)
## Data: IPVandCognitionDataSet2
##
## REML criterion at convergence: 60.05
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## HNDid (Intercept) 0.094257 0.30701
## Age 0.000075 0.00866 1.00
## subclass (Intercept) 0.008388 0.09158
## Residual 0.042075 0.20512
## Number of obs: 126, groups: HNDid, 63; subclass, 21
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.55710 0.06137 22.10000 57.96 < 2e-16
## Age 0.01951 0.00497 57.10000 3.93 0.00024
##
## Correlation of Fixed Effects:
## (Intr)
## Age 0.758
plot(st)
plot(mm1)
Trails A Regression Model 2 (with CES)
load("~/Desktop/Megan/Research/IPV and Cognition Paper/IPV R Output/IPVandCognitionDataSet2.rda")
library(lme4)
library(lmerTest)
(mm2 = lmer(log(TrailsAtestSec) ~ (Age + IPVstatus + PovStat + Sex + CESD)^5 +
(Age | HNDid) + (1 | subclass), data = IPVandCognitionDataSet2))
## Warning: number of observations <= rank(Z); variance-covariance matrix
## will be unidentifiable
## Linear mixed model fit by REML ['merModLmerTest']
## Formula: log(TrailsAtestSec) ~ (Age + IPVstatus + PovStat + Sex + CESD)^5 + (Age | HNDid) + (1 | subclass)
## Data: IPVandCognitionDataSet2
## REML criterion at convergence: 144.1
## Random effects:
## Groups Name Std.Dev. Corr
## HNDid (Intercept) 0.26494
## Age 0.00878 1.00
## subclass (Intercept) 0.16323
## Residual 0.21282
## Number of obs: 126, groups: HNDid, 63; subclass, 21
## Fixed Effects:
## (Intercept)
## 3.43431
## Age
## 0.01441
## IPVstatus1
## 0.02895
## PovStatBelow
## -0.15222
## SexMen
## -0.14163
## CESD1
## 0.17945
## Age:IPVstatus1
## 0.01084
## Age:PovStatBelow
## -0.02233
## Age:SexMen
## -0.01412
## Age:CESD1
## 0.01064
## IPVstatus1:PovStatBelow
## 1.90888
## IPVstatus1:SexMen
## -0.27750
## IPVstatus1:CESD1
## -0.04111
## PovStatBelow:SexMen
## 0.66266
## PovStatBelow:CESD1
## 0.16766
## SexMen:CESD1
## 0.04377
## Age:IPVstatus1:PovStatBelow
## 0.15477
## Age:IPVstatus1:SexMen
## -0.04316
## Age:IPVstatus1:CESD1
## -0.01329
## Age:PovStatBelow:SexMen
## 0.04530
## Age:PovStatBelow:CESD1
## 0.01651
## Age:SexMen:CESD1
## 0.01161
## IPVstatus1:PovStatBelow:SexMen
## -1.41976
## IPVstatus1:PovStatBelow:CESD1
## -1.54552
## IPVstatus1:SexMen:CESD1
## 0.40837
## PovStatBelow:SexMen:CESD1
## -0.56160
## Age:IPVstatus1:PovStatBelow:SexMen
## -0.10434
## Age:IPVstatus1:PovStatBelow:CESD1
## -0.08623
## Age:IPVstatus1:SexMen:CESD1
## 0.07104
## Age:PovStatBelow:SexMen:CESD1
## -0.03563
## IPVstatus1:PovStatBelow:SexMen:CESD1
## 1.32016
## Age:IPVstatus1:PovStatBelow:SexMen:CESD1
## 0.00988
(st = step(mm2))
## Warning: number of observations <= rank(Z); variance-covariance matrix will be unidentifiable
## Warning: number of observations <= rank(Z); variance-covariance matrix will be unidentifiable
## Random term (Age | HNDid) was eliminated because of having correlation +-1 or NaN
## Warning: number of observations <= rank(Z); variance-covariance matrix
## will be unidentifiable
## Random term (Age + 0 | HNDid) was eliminated because of standard deviation being equal to 0
##
## Random effects:
## Chi.sq Chi.DF elim.num p.value
## (1 | subclass) 3.59 1 kept 0.0582
## (1 | HNDid) 5.38 1 kept 0.0204
##
## Fixed effects:
## Sum Sq Mean Sq NumDF DenDF F.value
## Age:IPVstatus:PovStat:Sex:CESD 0.0017 0.0017 1 82.41 0.0370
## Age:PovStat:Sex:CESD 0.0427 0.0427 1 86.75 0.5412
## Age:IPVstatus:Sex:CESD 0.1400 0.1400 1 94.09 2.1142
## Age:Sex:CESD 0.0105 0.0105 1 89.68 0.3874
## Age:IPVstatus:PovStat:CESD 0.0119 0.0119 1 92.48 1.4156
## Age:IPVstatus:CESD 0.0005 0.0005 1 89.21 0.1883
## Age:PovStat:CESD 0.0280 0.0280 1 94.21 0.1958
## Age:IPVstatus:PovStat:Sex 0.0397 0.0397 1 94.37 2.0738
## Age:PovStat:Sex 0.0120 0.0120 1 81.77 0.1476
## IPVstatus:PovStat:Sex:CESD 0.1190 0.1190 1 93.33 1.5429
## IPVstatus:Sex:CESD 0.0036 0.0036 1 99.16 0.0318
## IPVstatus:PovStat:Sex 0.0000 0.0000 1 55.88 0.0901
## IPVstatus:PovStat:CESD 0.0132 0.0132 1 104.72 0.2268
## PovStat:Sex:CESD 0.0028 0.0028 1 103.10 0.3610
## IPVstatus:CESD 0.0282 0.0282 1 101.07 0.7134
## Sex:CESD 0.0534 0.0534 1 105.60 1.0884
## PovStat:CESD 0.0514 0.0514 1 96.28 1.5089
## Age:IPVstatus:Sex 0.0650 0.0650 1 101.73 1.6093
## IPVstatus:Sex 0.0348 0.0348 1 48.69 0.2176
## Age:Sex 0.0139 0.0139 1 81.53 1.1930
## Age:IPVstatus:PovStat 0.1152 0.1152 1 100.26 1.5780
## IPVstatus:PovStat 0.0137 0.0137 1 52.33 0.1550
## Age:PovStat 0.0610 0.0610 1 105.19 0.1931
## PovStat:Sex 0.0891 0.0891 1 46.96 2.3511
## Sex 0.0209 0.0209 1 56.96 0.3610
## Age:CESD 0.0690 0.0690 1 100.23 2.6387
## CESD 0.0393 0.0393 1 116.65 0.5074
## Age:IPVstatus 0.1579 0.1579 1 87.50 2.9113
## IPVstatus 0.0441 0.0441 1 39.31 0.8055
## Age 0.9350 0.9350 1 64.05 18.8016
## PovStat 0.2612 0.2612 1 54.85 4.0815
## elim.num Pr(>F)
## Age:IPVstatus:PovStat:Sex:CESD 1 0.8480
## Age:PovStat:Sex:CESD 2 0.4639
## Age:IPVstatus:Sex:CESD 3 0.1493
## Age:Sex:CESD 4 0.5352
## Age:IPVstatus:PovStat:CESD 5 0.2372
## Age:IPVstatus:CESD 6 0.6654
## Age:PovStat:CESD 7 0.6592
## Age:IPVstatus:PovStat:Sex 8 0.1532
## Age:PovStat:Sex 9 0.7018
## IPVstatus:PovStat:Sex:CESD 10 0.2173
## IPVstatus:Sex:CESD 11 0.8589
## IPVstatus:PovStat:Sex 12 0.7652
## IPVstatus:PovStat:CESD 13 0.6349
## PovStat:Sex:CESD 14 0.5493
## IPVstatus:CESD 15 0.4003
## Sex:CESD 16 0.2992
## PovStat:CESD 17 0.2223
## Age:IPVstatus:Sex 18 0.2075
## IPVstatus:Sex 19 0.6429
## Age:Sex 20 0.2779
## Age:IPVstatus:PovStat 21 0.2120
## IPVstatus:PovStat 22 0.6954
## Age:PovStat 23 0.6613
## PovStat:Sex 24 0.1319
## Sex 25 0.5503
## Age:CESD 26 0.1074
## CESD 27 0.4777
## Age:IPVstatus 28 0.0915
## IPVstatus 29 0.3749
## Age kept 1e-04
## PovStat kept 0.0482
##
## Least squares means:
## PovStat Estimate Standard Error DF t-value Lower CI
## PovStat Above 1.0 3.3683 0.0475 26.2 70.9000 3.27
## PovStat Below 2.0 3.5312 0.0665 38.9 53.1000 3.40
## Upper CI p-value
## PovStat Above 3.47 <2e-16
## PovStat Below 3.67 <2e-16
##
## Differences of LSMEANS:
## Estimate Standard Error DF t-value Lower CI Upper CI
## PovStat Above-Below -0.2 0.0806 54.8 -2.02 -0.324 -0.0013
## p-value
## PovStat Above-Below 0.05
##
## Final model:
## lme4::lmer(formula = log(TrailsAtestSec) ~ Age + PovStat + (1 |
## subclass) + (1 | HNDid), data = IPVandCognitionDataSet2,
## REML = reml, contrasts = l)
Re-run suggested final Model 2
(mm2 = lmer(log(TrailsAtestSec) ~ Age + PovStat + (Age | HNDid) + (1 | subclass),
data = IPVandCognitionDataSet2))
## Warning: number of observations <= rank(Z); variance-covariance matrix
## will be unidentifiable
## Linear mixed model fit by REML ['merModLmerTest']
## Formula: log(TrailsAtestSec) ~ Age + PovStat + (Age | HNDid) + (1 | subclass)
## Data: IPVandCognitionDataSet2
## REML criterion at convergence: 60
## Random effects:
## Groups Name Std.Dev. Corr
## HNDid (Intercept) 0.28847
## Age 0.00763 1.00
## subclass (Intercept) 0.10581
## Residual 0.20492
## Number of obs: 126, groups: HNDid, 63; subclass, 21
## Fixed Effects:
## (Intercept) Age PovStatBelow
## 3.505 0.019 0.149
summary(mm2)
## Warning: number of observations <= rank(Z); variance-covariance matrix will be unidentifiable
## Warning: number of observations <= rank(Z); variance-covariance matrix will be unidentifiable
## Linear mixed model fit by REML ['merModLmerTest']
## Formula: log(TrailsAtestSec) ~ Age + PovStat + (Age | HNDid) + (1 | subclass)
## Data: IPVandCognitionDataSet2
##
## REML criterion at convergence: 60
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## HNDid (Intercept) 8.32e-02 0.28847
## Age 5.82e-05 0.00763 1.00
## subclass (Intercept) 1.12e-02 0.10581
## Residual 4.20e-02 0.20492
## Number of obs: 126, groups: HNDid, 63; subclass, 21
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.50520 0.06760 32.10000 51.85 < 2e-16
## Age 0.01902 0.00496 62.60000 3.84 0.00029
## PovStatBelow 0.14932 0.08052 56.10000 1.85 0.06894
##
## Correlation of Fixed Effects:
## (Intr) Age
## Age 0.702
## PovStatBelw -0.445 -0.103
plot(st)
plot(mm2)
