subcortical volume analysis
Neda Rashidi-Ranjbar
June 4, 2019
R Markdown
library(knitr)
library(readr)
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(tidyr)
library(broom)
library(ggplot2)All.subcort.Vol <- read.csv("/projects/neda/FINAL.ANALYSIS.T1/QCd_All_data/subCortVol.All.csv")
All.subcort.Vol$EduCateg <- as.factor(All.subcort.Vol$EduCateg)
All.subcort.Vol$Sex <- as.factor(All.subcort.Vol$Sex)demographics - age
| Dx | n | MeanAge | MeanSD |
|---|---|---|---|
| AD | 41 | 75.29268 | 7.142282 |
| aMCI | 84 | 72.73810 | 8.006201 |
| HC | 56 | 69.82143 | 6.644498 |
| naMCI | 34 | 70.85294 | 6.800768 |
| rMDD | 42 | 69.66667 | 5.145050 |
| rMDD+aMCI | 45 | 71.13333 | 4.722288 |
| rMDD+naMCI | 29 | 70.51724 | 4.679901 |
boxplot age distribution in each group
## `stat_bindot()` using `bins = 30`. Pick better value with `binwidth`.
compare age between groups : AD is sig older than HC and rMDD
## Df Sum Sq Mean Sq F value Pr(>F)
## Dx 6 1064 177.40 4.107 0.000546 ***
## Residuals 324 13995 43.19
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = Age ~ Dx, data = All.subcort.Vol)
##
## $Dx
## diff lwr upr p adj
## aMCI-AD -2.5545877 -6.269514 1.16033892 0.3913725
## HC-AD -5.4712544 -9.479245 -1.46326344 0.0012432
## naMCI-AD -4.4397418 -8.962736 0.08325263 0.0582073
## rMDD-AD -5.6260163 -9.907056 -1.34497636 0.0022368
## rMDD+aMCI-AD -4.1593496 -8.369308 0.05060919 0.0552403
## rMDD+naMCI-AD -4.7754415 -9.506790 -0.04409351 0.0462337
## HC-aMCI -2.9166667 -6.280676 0.44734245 0.1379778
## naMCI-aMCI -1.8851541 -5.848744 2.07843577 0.7956182
## rMDD-aMCI -3.0714286 -6.756516 0.61365879 0.1727145
## rMDD+aMCI-aMCI -1.6047619 -5.207028 1.99750392 0.8414337
## rMDD+naMCI-aMCI -2.2208539 -6.420642 1.97893428 0.7022822
## naMCI-HC 1.0315126 -3.207987 5.27101208 0.9911987
## rMDD-HC -0.1547619 -4.135111 3.82558736 0.9999998
## rMDD+aMCI-HC 1.3119048 -2.591892 5.21570171 0.9544073
## rMDD+naMCI-HC 0.6958128 -3.765300 5.15692611 0.9992572
## rMDD-naMCI -1.1862745 -5.684793 3.31224383 0.9865272
## rMDD+aMCI-naMCI 0.2803922 -4.150535 4.71131955 0.9999963
## rMDD+naMCI-naMCI -0.3356998 -5.264698 4.59329796 0.9999942
## rMDD+aMCI-rMDD 1.4666667 -2.716985 5.65031843 0.9442851
## rMDD+naMCI-rMDD 0.8505747 -3.857381 5.55853004 0.9982884
## rMDD+naMCI-rMDD+aMCI -0.6160920 -5.259506 4.02732205 0.9997076sex difference among groups
##
## Pearson's Chi-squared test
##
## data: sex.diff
## X-squared = 6.0593, df = 6, p-value = 0.4166calculating z-score and taking outliers out (+-3)
hippo R & L
amyg R & L
accumbens R & L
thalamus R & L
caudate R & L
putamen R & L
Anova(lm) model
## Loading required package: carData##
## Attaching package: 'car'## The following object is masked from 'package:dplyr':
##
## recode| region | term | sumsq | df | statistic | p.value |
|---|---|---|---|---|---|
| Laccumb_vol | Dx | 1.519032e+05 | 6 | 4.5780560 | 0.0001795 |
| Laccumb_vol | Age | 3.492454e+05 | 1 | 63.1532944 | 0.0000000 |
| Laccumb_vol | Sex | 1.333092e+02 | 1 | 0.0241060 | 0.8767149 |
| Laccumb_vol | ICV | 6.587727e+04 | 1 | 11.9124460 | 0.0006337 |
| Laccumb_vol | EduCateg | 1.198224e+04 | 6 | 0.3611203 | 0.9031222 |
| Laccumb_vol | Residuals | 1.741988e+06 | 315 | NA | NA |
| Lamyg_vol | Dx | 2.206984e+06 | 6 | 11.0736602 | 0.0000000 |
| Lamyg_vol | Age | 1.343914e+06 | 1 | 40.4589770 | 0.0000000 |
| Lamyg_vol | Sex | 2.942360e+05 | 1 | 8.8580683 | 0.0031440 |
| Lamyg_vol | ICV | 4.460067e+05 | 1 | 13.4271745 | 0.0002909 |
| Lamyg_vol | EduCateg | 2.939323e+05 | 6 | 1.4748212 | 0.1862097 |
| Lamyg_vol | Residuals | 1.046327e+07 | 315 | NA | NA |
| Lcaud_vol | Dx | 8.534097e+05 | 6 | 0.7360424 | 0.6209262 |
| Lcaud_vol | Age | 8.183123e+05 | 1 | 4.2346310 | 0.0404298 |
| Lcaud_vol | Sex | 4.232222e+05 | 1 | 2.1901052 | 0.1398992 |
| Lcaud_vol | ICV | 1.885521e+07 | 1 | 97.5726110 | 0.0000000 |
| Lcaud_vol | EduCateg | 1.703333e+06 | 6 | 1.4690774 | 0.1882334 |
| Lcaud_vol | Residuals | 6.087151e+07 | 315 | NA | NA |
| Lhippo_vol | Dx | 1.012522e+07 | 6 | 12.8133836 | 0.0000000 |
| Lhippo_vol | Age | 9.439089e+06 | 1 | 71.6705485 | 0.0000000 |
| Lhippo_vol | Sex | 2.924165e+04 | 1 | 0.2220304 | 0.6378233 |
| Lhippo_vol | ICV | 6.686750e+06 | 1 | 50.7721743 | 0.0000000 |
| Lhippo_vol | EduCateg | 1.778980e+06 | 6 | 2.2512853 | 0.0383743 |
| Lhippo_vol | Residuals | 4.148584e+07 | 315 | NA | NA |
| Lput_vol | Dx | 2.804200e+06 | 6 | 1.8225536 | 0.0941765 |
| Lput_vol | Age | 1.530497e+06 | 1 | 5.9683626 | 0.0151137 |
| Lput_vol | Sex | 2.247295e+06 | 1 | 8.7636014 | 0.0033063 |
| Lput_vol | ICV | 5.325943e+06 | 1 | 20.7691695 | 0.0000074 |
| Lput_vol | EduCateg | 5.343144e+05 | 6 | 0.3472707 | 0.9112461 |
| Lput_vol | Residuals | 8.077705e+07 | 315 | NA | NA |
| Lthal_vol | Dx | 3.496367e+06 | 6 | 1.8174750 | 0.0951514 |
| Lthal_vol | Age | 9.359723e+06 | 1 | 29.1921241 | 0.0000001 |
| Lthal_vol | Sex | 2.664287e+05 | 1 | 0.8309668 | 0.3626902 |
| Lthal_vol | ICV | 4.694679e+07 | 1 | 146.4227645 | 0.0000000 |
| Lthal_vol | EduCateg | 1.505602e+06 | 6 | 0.7826392 | 0.5840532 |
| Lthal_vol | Residuals | 1.009969e+08 | 315 | NA | NA |
| Raccumb_vol | Dx | 1.828719e+05 | 6 | 5.0494406 | 0.0000580 |
| Raccumb_vol | Age | 1.488160e+05 | 1 | 24.6545511 | 0.0000011 |
| Raccumb_vol | Sex | 1.175009e+03 | 1 | 0.1946654 | 0.6593644 |
| Raccumb_vol | ICV | 1.612805e+05 | 1 | 26.7195563 | 0.0000004 |
| Raccumb_vol | EduCateg | 3.290350e+04 | 6 | 0.9085279 | 0.4888926 |
| Raccumb_vol | Residuals | 1.901354e+06 | 315 | NA | NA |
| Ramyg_vol | Dx | 1.959003e+06 | 6 | 8.8785589 | 0.0000000 |
| Ramyg_vol | Age | 4.721636e+05 | 1 | 12.8395905 | 0.0003931 |
| Ramyg_vol | Sex | 3.716047e+05 | 1 | 10.1050812 | 0.0016255 |
| Ramyg_vol | ICV | 8.847166e+05 | 1 | 24.0581812 | 0.0000015 |
| Ramyg_vol | EduCateg | 6.066672e+04 | 6 | 0.2749527 | 0.9484800 |
| Ramyg_vol | Residuals | 1.158382e+07 | 315 | NA | NA |
| Rcaud_vol | Dx | 1.076241e+06 | 6 | 0.7357571 | 0.6211538 |
| Rcaud_vol | Age | 3.907652e+05 | 1 | 1.6028471 | 0.2064357 |
| Rcaud_vol | Sex | 4.648046e+05 | 1 | 1.9065428 | 0.1683267 |
| Rcaud_vol | ICV | 2.141606e+07 | 1 | 87.8447514 | 0.0000000 |
| Rcaud_vol | EduCateg | 3.199205e+06 | 6 | 2.1870916 | 0.0440351 |
| Rcaud_vol | Residuals | 7.679525e+07 | 315 | NA | NA |
| Rhippo_vol | Dx | 1.298714e+07 | 6 | 15.0689186 | 0.0000000 |
| Rhippo_vol | Age | 6.790720e+06 | 1 | 47.2754529 | 0.0000000 |
| Rhippo_vol | Sex | 1.580804e+05 | 1 | 1.1005199 | 0.2949562 |
| Rhippo_vol | ICV | 8.719861e+06 | 1 | 60.7056917 | 0.0000000 |
| Rhippo_vol | EduCateg | 2.252540e+06 | 6 | 2.6136123 | 0.0173610 |
| Rhippo_vol | Residuals | 4.524710e+07 | 315 | NA | NA |
| Rput_vol | Dx | 1.408979e+06 | 6 | 0.8886037 | 0.5034171 |
| Rput_vol | Age | 2.007023e+06 | 1 | 7.5946421 | 0.0061951 |
| Rput_vol | Sex | 2.987637e+06 | 1 | 11.3053173 | 0.0008681 |
| Rput_vol | ICV | 3.572889e+06 | 1 | 13.5199300 | 0.0002774 |
| Rput_vol | EduCateg | 1.682506e+06 | 6 | 1.0611101 | 0.3858789 |
| Rput_vol | Residuals | 8.324451e+07 | 315 | NA | NA |
| Rthal_vol | Dx | 3.569964e+06 | 6 | 2.3591755 | 0.0303863 |
| Rthal_vol | Age | 5.431236e+06 | 1 | 21.5350725 | 0.0000051 |
| Rthal_vol | Sex | 7.674802e+05 | 1 | 3.0430903 | 0.0820568 |
| Rthal_vol | ICV | 3.672156e+07 | 1 | 145.6025004 | 0.0000000 |
| Rthal_vol | EduCateg | 1.039853e+06 | 6 | 0.6871767 | 0.6601388 |
| Rthal_vol | Residuals | 7.944433e+07 | 315 | NA | NA |
p value - FDR - Bonferroni
## # A tibble: 72 x 8
## # Groups: region [13]
## region term sumsq df statistic p.value FDR Bonferroni
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Rhippo_vol Dx 12987139. 6 15.1 3.61e-15 4.33e-14 4.33e-14
## 2 Lhippo_vol Dx 10125219. 6 12.8 5.91e-13 3.55e-12 7.09e-12
## 3 Lamyg_vol Dx 2206984. 6 11.1 3.30e-11 1.32e-10 3.96e-10
## 4 Ramyg_vol Dx 1959003. 6 8.88 5.85e- 9 1.76e- 8 7.02e- 8
## 5 Raccumb_vol Dx 182872. 6 5.05 5.80e- 5 1.39e- 4 6.96e- 4
## 6 Laccumb_vol Dx 151903. 6 4.58 1.79e- 4 3.59e- 4 2.15e- 3
## 7 Rthal_vol Dx 3569964. 6 2.36 3.04e- 2 5.21e- 2 3.65e- 1
## 8 Lput_vol Dx 2804200. 6 1.82 9.42e- 2 1.27e- 1 1.00e+ 0
## 9 Lthal_vol Dx 3496367. 6 1.82 9.52e- 2 1.27e- 1 1.00e+ 0
## 10 Rput_vol Dx 1408979. 6 0.889 5.03e- 1 6.04e- 1 1.00e+ 0
## # … with 62 more rowshippocampus post-hoc + testing simple vs. interactive model
## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Age## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## ICV## Df Sum Sq Mean Sq F value Pr(>F)
## Dx 6 18883821 3147304 23.852 < 2e-16 ***
## Age 1 9397710 9397710 71.220 1.25e-15 ***
## ICV 1 8674983 8674983 65.743 1.22e-14 ***
## Sex 1 13834 13834 0.105 0.7463
## EduCateg 6 1778980 296497 2.247 0.0388 *
## Dx:Age 6 712281 118714 0.900 0.4954
## Residuals 309 40773559 131953
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Age
## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## ICV## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Dx, Age## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = Lhippo_vol ~ Dx * Age + ICV + Sex + EduCateg, data = All.subcort.Vol)
##
## $Dx
## diff lwr upr p adj
## aMCI-AD 382.703368 177.31320 588.09354 0.0000014
## HC-AD 754.391463 532.79841 975.98452 0.0000000
## naMCI-AD 560.512052 310.44558 810.57852 0.0000000
## rMDD-AD 749.979559 513.29022 986.66889 0.0000000
## rMDD+aMCI-AD 612.388130 379.62871 845.14755 0.0000000
## rMDD+naMCI-AD 648.393188 386.80730 909.97908 0.0000000
## HC-aMCI 371.688095 185.69939 557.67680 0.0000002
## naMCI-aMCI 177.808683 -41.32953 396.94690 0.1986365
## rMDD-aMCI 367.276190 163.53577 571.01661 0.0000036
## rMDD+aMCI-aMCI 229.684762 30.52336 428.84616 0.0123555
## rMDD+naMCI-aMCI 265.689819 33.49272 497.88692 0.0135000
## naMCI-HC -193.879412 -428.27207 40.51324 0.1797888
## rMDD-HC -4.411905 -224.47671 215.65290 1.0000000
## rMDD+aMCI-HC -142.003333 -357.83573 73.82906 0.4472030
## rMDD+naMCI-HC -105.998276 -352.64348 140.64692 0.8627427
## rMDD-naMCI 189.467507 -59.24574 438.18075 0.2666187
## rMDD+aMCI-naMCI 51.876078 -193.10021 296.85237 0.9958464
## rMDD+naMCI-naMCI 87.881136 -184.63237 360.39464 0.9625769
## rMDD+aMCI-rMDD -137.591429 -368.89639 93.71353 0.5724635
## rMDD+naMCI-rMDD -101.586371 -361.87893 158.70619 0.9090081
## rMDD+naMCI-rMDD+aMCI 36.005057 -220.71915 292.72927 0.9995958## Analysis of Variance Table
##
## Model 1: Lhippo_vol ~ Dx + Age + ICV + Sex + EduCateg
## Model 2: Lhippo_vol ~ Dx * Age + ICV + Sex + EduCateg
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 315 41485840
## 2 309 40773559 6 712281 0.8997 0.4954## Df Sum Sq Mean Sq F value Pr(>F)
## Dx 6 22263785 3710631 25.076 < 2e-16 ***
## Age 1 6961660 6961660 47.047 3.57e-11 ***
## ICV 1 10219404 10219404 69.062 2.72e-15 ***
## Sex 1 125948 125948 0.851 0.357
## Residuals 321 47499636 147974
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Age## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## ICV## Df Sum Sq Mean Sq F value Pr(>F)
## Dx 6 22263785 3710631 24.942 < 2e-16 ***
## Age 1 6961660 6961660 46.796 4.11e-11 ***
## ICV 1 10219404 10219404 68.694 3.36e-15 ***
## Sex 1 125948 125948 0.847 0.358
## Dx:Age 6 637862 106310 0.715 0.638
## Residuals 315 46861775 148768
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Age
## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## ICV## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Dx, Age## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = Rhippo_vol ~ Dx * Age + ICV + Sex, data = All.subcort.Vol)
##
## $Dx
## diff lwr upr p adj
## aMCI-AD 495.829384 277.77292 713.88585 0.0000000
## HC-AD 843.364503 608.10593 1078.62307 0.0000000
## naMCI-AD 648.269440 382.78152 913.75736 0.0000000
## rMDD-AD 816.667480 565.38165 1067.95331 0.0000000
## rMDD+aMCI-AD 644.780813 397.66726 891.89437 0.0000000
## rMDD+naMCI-AD 798.175526 520.45779 1075.89326 0.0000000
## HC-aMCI 347.535119 150.07659 544.99364 0.0000066
## naMCI-aMCI 152.440056 -80.21229 385.09240 0.4525657
## rMDD-aMCI 320.838095 104.53312 537.14307 0.0002945
## rMDD+aMCI-aMCI 148.951429 -62.49214 360.39500 0.3608690
## rMDD+naMCI-aMCI 302.346141 55.82958 548.86271 0.0058471
## naMCI-HC -195.095063 -443.94258 53.75245 0.2346453
## rMDD-HC -26.697024 -260.33310 206.93905 0.9998774
## rMDD+aMCI-HC -198.583690 -427.72635 30.55897 0.1382943
## rMDD+naMCI-HC -45.188978 -307.04464 216.66669 0.9986769
## rMDD-naMCI 168.398039 -95.65321 432.44928 0.4868051
## rMDD+aMCI-naMCI -3.488627 -263.57246 256.59521 1.0000000
## rMDD+naMCI-naMCI 149.906085 -139.41317 439.22534 0.7218889
## rMDD+aMCI-rMDD -171.886667 -417.45607 73.68273 0.3688868
## rMDD+naMCI-rMDD -18.491954 -294.83660 257.85269 0.9999948
## rMDD+naMCI-rMDD+aMCI 153.394713 -119.16153 425.95095 0.6365279## Analysis of Variance Table
##
## Model 1: Rhippo_vol ~ Dx + Age + ICV + Sex
## Model 2: Rhippo_vol ~ Dx * Age + ICV + Sex
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 321 47499636
## 2 315 46861775 6 637862 0.7146 0.6381amygdala post-hoc + testing simple vs. interactive model
## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Age## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## ICV## Df Sum Sq Mean Sq F value Pr(>F)
## Dx 6 3367028 561171 17.311 < 2e-16 ***
## Age 1 1155026 1155026 35.630 6.54e-09 ***
## ICV 1 1299093 1299093 40.074 8.59e-10 ***
## Sex 1 318477 318477 9.824 0.00189 **
## EduCateg 6 293932 48989 1.511 0.17390
## Dx:Age 6 446417 74403 2.295 0.03496 *
## Residuals 309 10016849 32417
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Age
## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## ICV## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Dx, Age## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = Lamyg_vol ~ Dx * Age + ICV + Sex + EduCateg, data = All.subcort.Vol)
##
## $Dx
## diff lwr upr p adj
## aMCI-AD 155.832782 54.0308758 257.63469 0.0001605
## HC-AD 321.585758 211.7528710 431.41864 0.0000000
## naMCI-AD 263.897418 139.9516451 387.84319 0.0000000
## rMDD-AD 296.226829 178.9114508 413.54221 0.0000000
## rMDD+aMCI-AD 268.606829 153.2393207 383.97434 0.0000000
## rMDD+naMCI-AD 259.164760 129.5093732 388.82015 0.0000002
## HC-aMCI 165.752976 73.5674296 257.93852 0.0000038
## naMCI-aMCI 108.064636 -0.5515069 216.68078 0.0521579
## rMDD-aMCI 140.394048 39.4098410 241.37825 0.0009277
## rMDD+aMCI-aMCI 112.774048 14.0594388 211.48866 0.0137420
## rMDD+naMCI-aMCI 103.331979 -11.7568191 218.42078 0.1109187
## naMCI-HC -57.688340 -173.8653667 58.48869 0.7602779
## rMDD-HC -25.358929 -134.4343382 83.71648 0.9930908
## rMDD+aMCI-HC -52.978929 -159.9565383 53.99868 0.7625631
## rMDD+naMCI-HC -62.420998 -184.6710133 59.82902 0.7354556
## rMDD-naMCI 32.329412 -90.9456322 155.60446 0.9868819
## rMDD+aMCI-naMCI 4.709412 -116.7134051 126.13223 0.9999998
## rMDD+naMCI-naMCI -4.732657 -139.8043339 130.33902 0.9999999
## rMDD+aMCI-rMDD -27.620000 -142.2666048 87.02660 0.9916336
## rMDD+naMCI-rMDD -37.062069 -166.0764145 91.95228 0.9789873
## rMDD+naMCI-rMDD+aMCI -9.442069 -136.6877579 117.80362 0.9999904## Analysis of Variance Table
##
## Model 1: Lamyg_vol ~ Dx + Age + ICV + Sex + EduCateg
## Model 2: Lamyg_vol ~ Dx * Age + ICV + Sex + EduCateg
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 315 10463266
## 2 309 10016849 6 446417 2.2952 0.03496 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Age## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## ICV## Df Sum Sq Mean Sq F value Pr(>F)
## Dx 6 2788183 464697 12.717 7.82e-13 ***
## Age 1 336756 336756 9.216 0.00260 **
## ICV 1 2325496 2325496 63.642 2.94e-14 ***
## Sex 1 373246 373246 10.215 0.00154 **
## EduCateg 6 60667 10111 0.277 0.94768
## Dx:Age 6 292944 48824 1.336 0.24062
## Residuals 309 11290879 36540
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Age
## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## ICV## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Dx, Age## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = Ramyg_vol ~ Dx * Age + ICV + Sex + EduCateg, data = All.subcort.Vol)
##
## $Dx
## diff lwr upr p adj
## aMCI-AD 192.15136 84.06915 300.23358 0.0000051
## HC-AD 311.91803 195.30940 428.52667 0.0000000
## naMCI-AD 246.65143 115.05927 378.24360 0.0000012
## rMDD-AD 286.86684 162.31411 411.41957 0.0000000
## rMDD+aMCI-AD 237.28509 114.80040 359.76979 0.0000004
## rMDD+naMCI-AD 257.73490 120.08089 395.38892 0.0000012
## HC-aMCI 119.76667 21.89406 217.63927 0.0060263
## naMCI-aMCI 54.50007 -60.81676 169.81690 0.8001922
## rMDD-aMCI 94.71548 -12.49859 201.92954 0.1229776
## rMDD+aMCI-aMCI 45.13373 -59.67072 149.93818 0.8615744
## rMDD+naMCI-aMCI 65.58354 -56.60525 187.77233 0.6869743
## naMCI-HC -65.26660 -188.61075 58.07756 0.7013369
## rMDD-HC -25.05119 -140.85562 90.75324 0.9953309
## rMDD+aMCI-HC -74.63294 -188.21015 38.94427 0.4487909
## rMDD+naMCI-HC -54.18313 -183.97492 75.60867 0.8783640
## rMDD-naMCI 40.21541 -90.66465 171.09546 0.9705073
## rMDD+aMCI-naMCI -9.36634 -138.27990 119.54722 0.9999915
## rMDD+naMCI-naMCI 11.08347 -132.32097 154.48791 0.9999878
## rMDD+aMCI-rMDD -49.58175 -171.30106 72.13757 0.8903974
## rMDD+naMCI-rMDD -29.13194 -166.10536 107.84149 0.9957459
## rMDD+naMCI-rMDD+aMCI 20.44981 -114.64585 155.54547 0.9993728## Analysis of Variance Table
##
## Model 1: Ramyg_vol ~ Dx + Age + ICV + Sex + EduCateg
## Model 2: Ramyg_vol ~ Dx * Age + ICV + Sex + EduCateg
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 315 11583823
## 2 309 11290879 6 292944 1.3362 0.2406accumbens post-hoc + testing simple vs. interactive model
## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Age## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## ICV## Df Sum Sq Mean Sq F value Pr(>F)
## Dx 6 296529 49422 8.901 5.71e-09 ***
## Age 1 330649 330649 59.554 1.66e-13 ***
## ICV 1 105444 105444 18.992 1.79e-05 ***
## Sex 1 124 124 0.022 0.882
## EduCateg 6 11982 1997 0.360 0.904
## Dx:Age 6 26403 4401 0.793 0.576
## Residuals 309 1715585 5552
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Age
## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## ICV## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Dx, Age## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = Laccumb_vol ~ Dx * Age + ICV + Sex + EduCateg, data = All.subcort.Vol)
##
## $Dx
## diff lwr upr p adj
## aMCI-AD 73.120006 30.98952 115.25049 0.0000096
## HC-AD 89.663458 44.20937 135.11755 0.0000003
## naMCI-AD 76.716714 25.42204 128.01139 0.0002525
## rMDD-AD 100.078339 51.52764 148.62904 0.0000001
## rMDD+aMCI-AD 81.790244 34.04566 129.53482 0.0000132
## rMDD+naMCI-AD 104.383347 50.72576 158.04093 0.0000004
## HC-aMCI 16.543452 -21.60732 54.69423 0.8576001
## naMCI-aMCI 3.596709 -41.35383 48.54725 0.9999850
## rMDD-aMCI 26.958333 -14.83375 68.75042 0.4722787
## rMDD+aMCI-aMCI 8.670238 -32.18258 49.52305 0.9957953
## rMDD+naMCI-aMCI 31.263342 -16.36589 78.89258 0.4501883
## naMCI-HC -12.946744 -61.02634 35.13285 0.9849410
## rMDD-HC 10.414881 -34.72573 55.55549 0.9933700
## rMDD+aMCI-HC -7.873214 -52.14565 36.39922 0.9984304
## rMDD+naMCI-HC 14.719889 -35.87300 65.31278 0.9775831
## rMDD-naMCI 23.361625 -27.65547 74.37872 0.8230038
## rMDD+aMCI-naMCI 5.073529 -45.17703 55.32408 0.9999406
## rMDD+naMCI-naMCI 27.666633 -28.23247 83.56574 0.7630720
## rMDD+aMCI-rMDD -18.288095 -65.73433 29.15814 0.9138883
## rMDD+naMCI-rMDD 4.305008 -49.08728 57.69730 0.9999843
## rMDD+naMCI-rMDD+aMCI 22.593103 -30.06723 75.25344 0.8636943## Analysis of Variance Table
##
## Model 1: Laccumb_vol ~ Dx + Age + ICV + Sex + EduCateg
## Model 2: Laccumb_vol ~ Dx * Age + ICV + Sex + EduCateg
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 315 1741988
## 2 309 1715585 6 26403 0.7926 0.5763## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Age## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## ICV## Df Sum Sq Mean Sq F value Pr(>F)
## Dx 6 243772 40629 6.719 1.06e-06 ***
## Age 1 133053 133053 22.002 4.09e-06 ***
## ICV 1 209615 209615 34.663 1.02e-08 ***
## Sex 1 933 933 0.154 0.695
## EduCateg 6 32903 5484 0.907 0.490
## Dx:Age 6 32764 5461 0.903 0.493
## Residuals 309 1868591 6047
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Age
## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## ICV## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Dx, Age## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = Raccumb_vol ~ Dx * Age + ICV + Sex + EduCateg, data = All.subcort.Vol)
##
## $Dx
## diff lwr upr p adj
## aMCI-AD 80.4987515 36.52966 124.46784 0.0000023
## HC-AD 77.9082753 30.47054 125.34601 0.0000358
## naMCI-AD 67.0299139 13.49670 120.56312 0.0044538
## rMDD-AD 90.4666086 39.79712 141.13610 0.0000046
## rMDD+aMCI-AD 73.4508943 23.62271 123.27908 0.0003318
## rMDD+naMCI-AD 90.0768713 34.07763 146.07611 0.0000570
## HC-aMCI -2.5904762 -42.40618 37.22523 0.9999956
## naMCI-aMCI -13.4688375 -60.38105 33.44338 0.9790482
## rMDD-aMCI 9.9678571 -33.64806 53.58378 0.9937026
## rMDD+aMCI-aMCI -7.0478571 -49.68352 35.58780 0.9989626
## rMDD+naMCI-aMCI 9.5781199 -40.12969 59.28593 0.9975378
## naMCI-HC -10.8783613 -61.05618 39.29946 0.9952748
## rMDD-HC 12.5583333 -34.55224 59.66891 0.9857127
## rMDD+aMCI-HC -4.4573810 -50.66190 41.74714 0.9999546
## rMDD+naMCI-HC 12.1685961 -40.63220 64.96939 0.9934101
## rMDD-naMCI 23.4366947 -29.80682 76.68021 0.8486703
## rMDD+aMCI-naMCI 6.4209804 -46.02254 58.86450 0.9998163
## rMDD+naMCI-naMCI 23.0469574 -35.29162 81.38554 0.9040127
## rMDD+aMCI-rMDD -17.0157143 -66.53254 32.50111 0.9492027
## rMDD+naMCI-rMDD -0.3897373 -56.11211 55.33263 1.0000000
## rMDD+naMCI-rMDD+aMCI 16.6259770 -38.33249 71.58445 0.9727134## Analysis of Variance Table
##
## Model 1: Raccumb_vol ~ Dx + Age + ICV + Sex + EduCateg
## Model 2: Raccumb_vol ~ Dx * Age + ICV + Sex + EduCateg
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 315 1901354
## 2 309 1868591 6 32764 0.903 0.4929thalamus : not sign
## Df Sum Sq Mean Sq F value Pr(>F)
## Dx 6 9887734 1647956 5.161 4.40e-05 ***
## Age 1 8888888 8888888 27.837 2.43e-07 ***
## ICV 1 63523894 63523894 198.933 < 2e-16 ***
## Sex 1 209698 209698 0.657 0.418
## Residuals 321 102502462 319322
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Age## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## ICV## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = Lthal_vol ~ Dx + Age + ICV + Sex, data = All.subcort.Vol)
##
## $Dx
## diff lwr upr p adj
## aMCI-AD 215.7689605 -103.66188 535.1998 0.4139715
## HC-AD 546.9963415 202.36614 891.6265 0.0000753
## naMCI-AD 344.5081062 -44.40506 733.4213 0.1209568
## rMDD-AD 480.7891986 112.68067 848.8977 0.0024518
## rMDD+aMCI-AD 373.6863415 11.68978 735.6829 0.0379721
## rMDD+naMCI-AD 480.4256518 73.59703 887.2543 0.0093590
## HC-aMCI 331.2273810 41.97045 620.4843 0.0133734
## naMCI-aMCI 128.7391457 -212.07319 469.5515 0.9214348
## rMDD-aMCI 265.0202381 -51.84485 581.8853 0.1694534
## rMDD+aMCI-aMCI 157.9173810 -151.82623 467.6610 0.7370734
## rMDD+naMCI-aMCI 264.6566913 -96.46534 625.7787 0.3123280
## naMCI-HC -202.4882353 -567.02488 162.0484 0.6510596
## rMDD-HC -66.2071429 -408.46055 276.0463 0.9974883
## rMDD+aMCI-HC -173.3100000 -508.98100 162.3610 0.7253444
## rMDD+naMCI-HC -66.5706897 -450.16297 317.0216 0.9986354
## rMDD-naMCI 136.2810924 -250.52749 523.0897 0.9429490
## rMDD+aMCI-naMCI 29.1782353 -351.81848 410.1750 0.9999884
## rMDD+naMCI-naMCI 135.9175456 -287.90614 559.7412 0.9636379
## rMDD+aMCI-rMDD -107.1028571 -466.83739 252.6317 0.9748563
## rMDD+naMCI-rMDD -0.3635468 -405.18073 404.4536 1.0000000
## rMDD+naMCI-rMDD+aMCI 106.7393103 -292.52824 506.0069 0.9855226## Df Sum Sq Mean Sq F value Pr(>F)
## Dx 6 9887734 1647956 5.117 4.93e-05 ***
## Age 1 8888888 8888888 27.600 2.75e-07 ***
## ICV 1 63523894 63523894 197.241 < 2e-16 ***
## Sex 1 209698 209698 0.651 0.420
## Dx:Age 6 1053044 175507 0.545 0.774
## Residuals 315 101449418 322062
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Age
## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## ICV## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Dx, Age## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = Lthal_vol ~ Dx * Age + ICV + Sex, data = All.subcort.Vol)
##
## $Dx
## diff lwr upr p adj
## aMCI-AD 215.7689605 -105.06799 536.6059 0.4194399
## HC-AD 546.9963415 200.84911 893.1436 0.0000831
## naMCI-AD 344.5081062 -46.11703 735.1332 0.1243015
## rMDD-AD 480.7891986 111.06029 850.5181 0.0026183
## rMDD+aMCI-AD 373.6863415 10.09630 737.2764 0.0394932
## rMDD+naMCI-AD 480.4256518 71.80620 889.0451 0.0098684
## HC-aMCI 331.2273810 40.69717 621.7576 0.0140528
## naMCI-aMCI 128.7391457 -213.57342 471.0517 0.9229231
## rMDD-aMCI 265.0202381 -53.23966 583.2801 0.1734996
## rMDD+aMCI-aMCI 157.9173810 -153.18970 469.0245 0.7409613
## rMDD+naMCI-aMCI 264.6566913 -98.05497 627.3684 0.3175483
## naMCI-HC -202.4882353 -568.62954 163.6531 0.6556883
## rMDD-HC -66.2071429 -409.96713 277.5528 0.9975467
## rMDD+aMCI-HC -173.3100000 -510.45860 163.8386 0.7293467
## rMDD+naMCI-HC -66.5706897 -451.85151 318.7101 0.9986676
## rMDD-naMCI 136.2810924 -252.23019 524.7924 0.9440710
## rMDD+aMCI-naMCI 29.1782353 -353.49560 411.8521 0.9999887
## rMDD+naMCI-naMCI 135.9175456 -289.77178 561.6069 0.9643839
## rMDD+aMCI-rMDD -107.1028571 -468.42091 254.2152 0.9753868
## rMDD+naMCI-rMDD -0.3635468 -406.96270 406.2356 1.0000000
## rMDD+naMCI-rMDD+aMCI 106.7393103 -294.28578 507.7644 0.9858383## Analysis of Variance Table
##
## Model 1: Lthal_vol ~ Dx + Age + ICV + Sex
## Model 2: Lthal_vol ~ Dx * Age + ICV + Sex
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 321 102502462
## 2 315 101449418 6 1053044 0.5449 0.7738## Df Sum Sq Mean Sq F value Pr(>F)
## Dx 6 8092645 1348774 5.379 2.6e-05 ***
## Age 1 5051598 5051598 20.148 1.0e-05 ***
## ICV 1 45916817 45916817 183.133 < 2e-16 ***
## Sex 1 624294 624294 2.490 0.116
## Residuals 321 80484179 250730
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Age## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## ICV## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = Rthal_vol ~ Dx + Age + ICV + Sex, data = All.subcort.Vol)
##
## $Dx
## diff lwr upr p adj
## aMCI-AD 170.655314 -112.39586 453.70648 0.5565224
## HC-AD 474.846385 169.46579 780.22698 0.0001159
## naMCI-AD 273.520230 -71.10000 618.14046 0.2215351
## rMDD-AD 401.077933 74.89293 727.26294 0.0056515
## rMDD+aMCI-AD 230.137615 -90.63151 550.90674 0.3382658
## rMDD+naMCI-AD 468.214550 107.71925 828.70985 0.0026609
## HC-aMCI 304.191071 47.87734 560.50481 0.0088155
## naMCI-aMCI 102.864916 -199.13263 404.86247 0.9513612
## rMDD-aMCI 230.422619 -50.35501 511.20025 0.1875047
## rMDD+aMCI-aMCI 59.482302 -214.98491 333.94951 0.9952929
## rMDD+naMCI-aMCI 297.559236 -22.43496 617.55343 0.0874818
## naMCI-HC -201.326155 -524.34607 121.69376 0.5157219
## rMDD-HC -73.768452 -377.04295 229.50605 0.9912084
## rMDD+aMCI-HC -244.708770 -542.15052 52.73298 0.1850738
## rMDD+naMCI-HC -6.631835 -346.53716 333.27349 1.0000000
## rMDD-naMCI 127.557703 -215.19762 470.31303 0.9265556
## rMDD+aMCI-naMCI -43.382614 -380.98799 294.22276 0.9997570
## rMDD+naMCI-naMCI 194.694320 -180.86049 570.24914 0.7214861
## rMDD+aMCI-rMDD -170.940317 -489.70503 147.82440 0.6881399
## rMDD+naMCI-rMDD 67.136617 -291.57633 425.84956 0.9979119
## rMDD+naMCI-rMDD+aMCI 238.076935 -115.71842 591.87229 0.4187915## Df Sum Sq Mean Sq F value Pr(>F)
## Dx 6 8092645 1348774 5.355 2.78e-05 ***
## Age 1 5051598 5051598 20.056 1.05e-05 ***
## ICV 1 45916817 45916817 182.299 < 2e-16 ***
## Sex 1 624294 624294 2.479 0.116
## Dx:Age 6 1143043 190507 0.756 0.605
## Residuals 315 79341136 251877
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Age
## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## ICV## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## Dx, Age## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = Rthal_vol ~ Dx * Age + ICV + Sex, data = All.subcort.Vol)
##
## $Dx
## diff lwr upr p adj
## aMCI-AD 170.655314 -113.07700 454.38763 0.5593021
## HC-AD 474.846385 168.73090 780.96187 0.0001223
## naMCI-AD 273.520230 -71.92931 618.96977 0.2240226
## rMDD-AD 401.077933 74.10798 728.04788 0.0058362
## rMDD+aMCI-AD 230.137615 -91.40342 551.67865 0.3411326
## rMDD+naMCI-AD 468.214550 106.85173 829.57737 0.0027592
## HC-aMCI 304.191071 47.26053 561.12161 0.0090813
## naMCI-aMCI 102.864916 -199.85938 405.58921 0.9518793
## rMDD-aMCI 230.422619 -51.03069 511.87592 0.1898072
## rMDD+aMCI-aMCI 59.482302 -215.64540 334.61001 0.9953501
## rMDD+naMCI-aMCI 297.559236 -23.20501 618.32348 0.0889624
## naMCI-HC -201.326155 -525.12340 122.47109 0.5185847
## rMDD-HC -73.768452 -377.77277 230.23586 0.9913129
## rMDD+aMCI-HC -244.708770 -542.86630 53.44876 0.1873615
## rMDD+naMCI-HC -6.631835 -347.35512 334.09145 1.0000000
## rMDD-naMCI 127.557703 -216.02244 471.13785 0.9273038
## rMDD+aMCI-naMCI -43.382614 -381.80042 295.03519 0.9997602
## rMDD+naMCI-naMCI 194.694320 -181.76425 571.15289 0.7236478
## rMDD+aMCI-rMDD -170.940317 -490.47212 148.59149 0.6904624
## rMDD+naMCI-rMDD 67.136617 -292.43955 426.71279 0.9979378
## rMDD+naMCI-rMDD+aMCI 238.076935 -116.56981 592.72368 0.4217328## Analysis of Variance Table
##
## Model 1: Rthal_vol ~ Dx + Age + ICV + Sex
## Model 2: Rthal_vol ~ Dx * Age + ICV + Sex
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 321 80484179
## 2 315 79341136 6 1143043 0.7564 0.6048figures Hippo
## Installing package into '/home/nrashidi/R/x86_64-pc-linux-gnu-library/3.5'
## (as 'lib' is unspecified)##
## Attaching package: 'magrittr'## The following object is masked from 'package:tidyr':
##
## extractfor changing colors
# wes_palettes <- list(
# BottleRocket1 = c("#A42820", "#5F5647", "#9B110E", "#3F5151", "#4E2A1E", "#550307", "#0C1707"),
# BottleRocket2 = c("#FAD510", "#CB2314", "#273046", "#354823", "#1E1E1E"),
# Rushmore1 = c("#E1BD6D", "#EABE94", "#0B775E", "#35274A" ,"#F2300F"),
# Rushmore = c("#E1BD6D", "#EABE94", "#0B775E", "#35274A" ,"#F2300F"),
# Royal1 = c("#899DA4", "#C93312", "#FAEFD1", "#DC863B"),
# Royal2 = c("#9A8822", "#F5CDB4", "#F8AFA8", "#FDDDA0", "#74A089"),
# Zissou1 = c("#3B9AB2", "#78B7C5", "#EBCC2A", "#E1AF00", "#F21A00"),
# Darjeeling1 = c("#FF0000", "#00A08A", "#F2AD00", "#F98400", "#5BBCD6"),
# Darjeeling2 = c("#ECCBAE", "#046C9A", "#D69C4E", "#ABDDDE", "#000000"),
# Chevalier1 = c("#446455", "#FDD262", "#D3DDDC", "#C7B19C"),
# FantasticFox1 = c("#DD8D29", "#E2D200", "#46ACC8", "#E58601", "#B40F20"),
# Moonrise1 = c("#F3DF6C", "#CEAB07", "#D5D5D3", "#24281A"),
# Moonrise2 = c("#798E87", "#C27D38", "#CCC591", "#29211F"),
# Moonrise3 = c("#85D4E3", "#F4B5BD", "#9C964A", "#CDC08C", "#FAD77B"),
# Cavalcanti1 = c("#D8B70A", "#02401B", "#A2A475", "#81A88D", "#972D15"),
# GrandBudapest1 = c("#F1BB7B", "#FD6467", "#5B1A18", "#D67236"),
# GrandBudapest2 = c("#E6A0C4", "#C6CDF7", "#D8A499", "#7294D4"),
# IsleofDogs1 = c("#9986A5", "#79402E", "#CCBA72", "#0F0D0E", "#D9D0D3", "#8D8680"),
# IsleofDogs2 = c("#EAD3BF", "#AA9486", "#B6854D", "#39312F", "#1C1718")
# )
#
# g + scale_fill_manual(wes_palette(7, name="BottleRocket1"))boxplot hippo
## Saving 7 x 5 in image
## Saving 7 x 5 in image
## Saving 7 x 5 in image
## Saving 7 x 5 in imageboxplot Amygdala
## Saving 7 x 5 in image
## Saving 7 x 5 in image
## Saving 7 x 5 in image
## Saving 7 x 5 in imageboxplot accumbens
## Saving 7 x 5 in image
## Saving 7 x 5 in image
## Saving 7 x 5 in image
## Saving 7 x 5 in imageNote that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.