library(ggplot2)
library(psych)
##
## Attaching package: 'psych'
##
## The following object is masked from 'package:ggplot2':
##
## %+%
require(RCurl)
## Loading required package: RCurl
## Loading required package: bitops
library(RCurl)
library(gsheet)
## Warning: package 'gsheet' was built under R version 3.1.3
require(graphics)
library(car)
##
## Attaching package: 'car'
##
## The following object is masked from 'package:psych':
##
## logit
setwd("~/Google Drive/Fat_data/") #this needs to be where you save the datasheets
# Download a sheet
# michelle_url <- 'https://docs.google.com/spreadsheets/d/1lokeoeVa4z9iGwnf6nofGrjopOvXDFXVO26o8QsmYNs/pubhtml'
# a <- gsheet2tbl(michelle_url)
#
# lisa_url<- 'https://docs.google.com/spreadsheets/d/1EKG5b24MM4tLqrugrsOkDsTEtYatyhIQgcZuqu8kne4/pubhtml'
# b <- gsheet2tbl(lisa_url)
# names(b)<-NULL
#
# katey_url<-'https://docs.google.com/spreadsheets/d/1QeMCQOrQeqVWu_PJnZ0kV68gYSnHZo2x1GRqyjCSYFQ/pubhtml'
# c <- gsheet2tbl(katey_url)
# names(c)<-NULL
#
# ellen_url<-'https://docs.google.com/spreadsheets/d/1PQ4u68Yx1JJCqItxob6bmZnvPU2LS3Wp8Z5LLtjw--s/pubhtml'
# d <- gsheet2tbl(ellen_url)
# names(d)<-NULL
#
# total_data<-rbind(a,b,c,d)
# Download the same sheet by id
#b <- gsheet2tbl('https://docs.google.com/spreadsheets/d/1lokeoeVa4z9iGwnf6nofGrjopOvXDFXVO26o8QsmYNs/pubhtml', sheetid = 1)
#total_data<-read.csv("data.csv", header=T, sep=",")
Lisa_data<-read.csv("lisa_data.csv", header=T, sep=",")
Michelle_data<-read.csv("michelle_data.csv", header=T, sep=",")
#names(Michelle_data) <- NULL
Ellen_data<-read.csv("ellen_data.csv", header=T, sep=",")
#names(Ellen_data) <- NULL
Katey_data<-read.csv("katey_data.csv", header=T, sep=",")
#names(Katey_data) <- NULL
total_data <- rbind(Lisa_data, Michelle_data, Ellen_data, Katey_data)
total_data$coder<-as.factor(total_data$coder)
total_data$subjNum<-as.factor(total_data$subjNum)
total_data<-na.omit(total_data)
write.table(total_data, "FHS_fat_data.csv", row.names=F, sep=",")
#####HEPATIC FAT#####
plot(Hep_fat ~ coder, data = total_data)
describeBy(total_data$Hep_fat, total_data$coder)
## group: Lisa
## vars n mean sd median trimmed mad min max range skew kurtosis
## 1 1 3 20.71 7.09 22.7 20.71 5.74 12.83 26.58 13.75 -0.26 -2.33
## se
## 1 4.09
## --------------------------------------------------------
## group: Michelle
## vars n mean sd median trimmed mad min max range skew kurtosis
## 1 1 8 23.96 9.16 21.72 23.96 4.16 16.14 45.36 29.22 1.46 0.81
## se
## 1 3.24
## --------------------------------------------------------
## group: ellen
## vars n mean sd median trimmed mad min max range skew kurtosis
## 1 1 3 25.57 5.09 26.15 25.57 6.22 20.22 30.35 10.12 -0.11 -2.33
## se
## 1 2.94
## --------------------------------------------------------
## group: Katey
## vars n mean sd median trimmed mad min max range skew kurtosis
## 1 1 6 22.04 11.25 18.64 22.04 6.32 12.62 43.49 30.87 1 -0.68
## se
## 1 4.59
hepFat<-aov(Hep_fat~coder, data=total_data)
summary(hepFat)
## Df Sum Sq Mean Sq F value Pr(>F)
## coder 3 48.2 16.08 0.187 0.903
## Residuals 16 1373.2 85.82
summary.lm(hepFat)
##
## Call:
## aov(formula = Hep_fat ~ coder, data = total_data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -9.4165 -5.4540 -0.7779 1.7344 21.4536
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 20.705 5.349 3.871 0.00135 **
## coderMichelle 3.259 6.272 0.520 0.61043
## coderellen 4.868 7.564 0.644 0.52896
## coderKatey 1.335 6.551 0.204 0.84107
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 9.264 on 16 degrees of freedom
## Multiple R-squared: 0.03394, Adjusted R-squared: -0.1472
## F-statistic: 0.1874 on 3 and 16 DF, p-value: 0.9034
pairwise.t.test(total_data$Hep_fat, total_data$coder, paired=FALSE, p.adjust.method="bonferroni")
##
## Pairwise comparisons using t tests with pooled SD
##
## data: total_data$Hep_fat and total_data$coder
##
## Lisa Michelle ellen
## Michelle 1 - -
## ellen 1 1 -
## Katey 1 1 1
##
## P value adjustment method: bonferroni
fullPlot1<-ggplot(
total_data, aes(
coder, Hep_fat, fill=as.factor(coder)))+stat_summary(
fun.y=mean, geom="bar", position="dodge")+stat_summary(
fun.data=mean_cl_normal, geom="errorbar", position=position_dodge(width=0.90), width=0.2)+labs(
x = "coder", y = "hep fat")+ labs(
title="hep fat")
fullPlot1
bartlett.test(Hep_fat ~ coder, data = total_data)
##
## Bartlett test of homogeneity of variances
##
## data: Hep_fat by coder
## Bartlett's K-squared = 1.4687, df = 3, p-value = 0.6895
leveneTest(Hep_fat ~ coder, data = total_data)
## Levene's Test for Homogeneity of Variance (center = median)
## Df F value Pr(>F)
## group 3 0.2334 0.8717
## 16
#####SAT FAT#####
plot(SAT ~ coder, data = total_data)
describeBy(total_data$SAT, total_data$coder)
## group: Lisa
## vars n mean sd median trimmed mad min max range skew
## 1 1 3 476.35 429.52 344.21 476.35 319.92 128.43 956.42 827.99 0.28
## kurtosis se
## 1 -2.33 247.98
## --------------------------------------------------------
## group: Michelle
## vars n mean sd median trimmed mad min max range skew
## 1 1 8 592.47 329.76 516.86 592.47 375.17 202.69 1048.6 845.91 0.26
## kurtosis se
## 1 -1.81 116.59
## --------------------------------------------------------
## group: ellen
## vars n mean sd median trimmed mad min max range skew
## 1 1 3 887.31 651.82 670.11 887.31 442.23 371.83 1620 1248.17 0.3
## kurtosis se
## 1 -2.33 376.33
## --------------------------------------------------------
## group: Katey
## vars n mean sd median trimmed mad min max range skew
## 1 1 6 704.65 450.06 762.55 704.65 593.19 143.02 1300 1156.98 -0.07
## kurtosis se
## 1 -1.83 183.74
satFat<-aov(SAT~coder, data=total_data)
summary(satFat)
## Df Sum Sq Mean Sq F value Pr(>F)
## coder 3 303641 101214 0.541 0.661
## Residuals 16 2992690 187043
summary.lm(satFat)
##
## Call:
## aov(formula = SAT ~ coder, data = total_data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -561.63 -303.96 -68.54 349.69 732.69
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 476.4 249.7 1.908 0.0745 .
## coderMichelle 116.1 292.8 0.397 0.6969
## coderellen 411.0 353.1 1.164 0.2616
## coderKatey 228.3 305.8 0.747 0.4662
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 432.5 on 16 degrees of freedom
## Multiple R-squared: 0.09211, Adjusted R-squared: -0.07811
## F-statistic: 0.5411 on 3 and 16 DF, p-value: 0.661
pairwise.t.test(total_data$SAT, total_data$coder, paired=FALSE, p.adjust.method="bonferroni")
##
## Pairwise comparisons using t tests with pooled SD
##
## data: total_data$SAT and total_data$coder
##
## Lisa Michelle ellen
## Michelle 1 - -
## ellen 1 1 -
## Katey 1 1 1
##
## P value adjustment method: bonferroni
fullPlot2<-ggplot(
total_data, aes(
coder,SAT, fill=as.factor(coder)))+stat_summary(
fun.y=mean, geom="bar", position="dodge")+stat_summary(
fun.data=mean_cl_normal, geom="errorbar", position=position_dodge(width=0.90), width=0.2)+labs(
x = "coder", y = "SAT")+ labs(
title="SAT")
fullPlot2
bartlett.test(SAT ~ coder, data = total_data)
##
## Bartlett test of homogeneity of variances
##
## data: SAT by coder
## Bartlett's K-squared = 1.5624, df = 3, p-value = 0.6679
leveneTest(SAT ~ coder, data = total_data)
## Levene's Test for Homogeneity of Variance (center = median)
## Df F value Pr(>F)
## group 3 0.2394 0.8676
## 16
#####VAT FAT#####
plot(VAT ~ coder, data = total_data)
describeBy(total_data$VAT, total_data$coder)
## group: Lisa
## vars n mean sd median trimmed mad min max range skew
## 1 1 3 223.37 134.54 274.46 223.37 74.75 70.76 324.88 254.12 -0.32
## kurtosis se
## 1 -2.33 77.68
## --------------------------------------------------------
## group: Michelle
## vars n mean sd median trimmed mad min max range skew
## 1 1 8 150.47 70.26 118.09 150.47 52.17 59.98 254.75 194.77 0.3
## kurtosis se
## 1 -1.76 24.84
## --------------------------------------------------------
## group: ellen
## vars n mean sd median trimmed mad min max range skew
## 1 1 3 418.09 200.05 499 418.09 97.85 190.26 565 374.74 -0.34
## kurtosis se
## 1 -2.33 115.5
## --------------------------------------------------------
## group: Katey
## vars n mean sd median trimmed mad min max range skew
## 1 1 6 935.73 509.98 1038.94 935.73 587.19 233.79 1450 1216.21 -0.26
## kurtosis se
## 1 -1.93 208.2
vatFat<-aov(VAT~coder, data=total_data)
summary(vatFat)
## Df Sum Sq Mean Sq F value Pr(>F)
## coder 3 2287162 762387 8.406 0.00139 **
## Residuals 16 1451213 90701
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
summary.lm(vatFat)
##
## Call:
## aov(formula = VAT ~ coder, data = total_data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -701.94 -56.12 11.63 102.20 514.27
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 223.4 173.9 1.285 0.21721
## coderMichelle -72.9 203.9 -0.358 0.72536
## coderellen 194.7 245.9 0.792 0.44003
## coderKatey 712.4 213.0 3.345 0.00411 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 301.2 on 16 degrees of freedom
## Multiple R-squared: 0.6118, Adjusted R-squared: 0.539
## F-statistic: 8.406 on 3 and 16 DF, p-value: 0.001393
pairwise.t.test(total_data$VAT, total_data$coder, paired=FALSE, p.adjust.method="bonferroni")
##
## Pairwise comparisons using t tests with pooled SD
##
## data: total_data$VAT and total_data$coder
##
## Lisa Michelle ellen
## Michelle 1.0000 - -
## ellen 1.0000 1.0000 -
## Katey 0.0247 0.0011 0.1632
##
## P value adjustment method: bonferroni
fullPlot4<-ggplot(
total_data, aes(
coder,VAT, fill=as.factor(coder)))+stat_summary(
fun.y=mean, geom="bar", position="dodge")+stat_summary(
fun.data=mean_cl_normal, geom="errorbar", position=position_dodge(width=0.90), width=0.2)+labs(
x = "coder", y = "VAT")+ labs(
title="VAT")
fullPlot4
bartlett.test(VAT ~ coder, data = total_data)
##
## Bartlett test of homogeneity of variances
##
## data: VAT by coder
## Bartlett's K-squared = 17.4819, df = 3, p-value = 0.0005625
leveneTest(VAT ~ coder, data = total_data)
## Levene's Test for Homogeneity of Variance (center = median)
## Df F value Pr(>F)
## group 3 5.7902 0.007057 **
## 16
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#####HEPATIC FAT BY SUBJECT#####
describeBy(total_data$Hep_fat, total_data$subjNum)
## group: FHS_001
## vars n mean sd median trimmed mad min max range skew kurtosis
## 1 1 4 23.11 4.77 24.8 23.11 2.32 16.27 26.58 10.31 -0.58 -1.83
## se
## 1 2.38
## --------------------------------------------------------
## group: FHS_003
## vars n mean sd median trimmed mad min max range skew kurtosis se
## 1 1 4 24.81 4.07 23.94 24.81 3.09 21 30.35 9.35 0.39 -1.93 2.04
## --------------------------------------------------------
## group: FHS_004
## vars n mean sd median trimmed mad min max range skew kurtosis
## 1 1 4 16.09 3.09 15.65 16.09 2.46 12.83 20.22 7.39 0.3 -1.88
## se
## 1 1.54
## --------------------------------------------------------
## group: FHS_005
## vars n mean sd median trimmed mad min max range skew kurtosis
## 1 1 2 44.43 1.32 44.43 44.43 1.38 43.49 45.36 1.87 0 -2.75
## se
## 1 0.93
## --------------------------------------------------------
## group: FHS_006
## vars n mean sd median trimmed mad min max range skew kurtosis
## 1 1 2 15.72 4.38 15.72 15.72 4.59 12.62 18.82 6.19 0 -2.75
## se
## 1 3.1
## --------------------------------------------------------
## group: FHS_009
## vars n mean sd median trimmed mad min max range skew kurtosis se
## 1 1 2 21.34 3.31 21.34 21.34 3.47 19 23.69 4.69 0 -2.75 2.34
## --------------------------------------------------------
## group: FHS_011
## NULL
## --------------------------------------------------------
## group: FHS_013
## vars n mean sd median trimmed mad min max range skew kurtosis se
## 1 1 1 23.79 NA 23.79 23.79 0 23.79 23.79 0 NA NA NA
## --------------------------------------------------------
## group: FHS_016
## vars n mean sd median trimmed mad min max range skew kurtosis se
## 1 1 1 19.98 NA 19.98 19.98 0 19.98 19.98 0 NA NA NA
hepFat2<-aov(Hep_fat~subjNum, data=total_data)
summary(hepFat2)
## Df Sum Sq Mean Sq F value Pr(>F)
## subjNum 7 1243.1 177.58 11.95 0.000146 ***
## Residuals 12 178.3 14.86
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
summary.lm(hepFat2)
##
## Call:
## aov(formula = Hep_fat ~ subjNum, data = total_data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -6.8395 -2.1613 0.0264 2.5168 5.5423
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 23.1123 1.9275 11.991 4.88e-08 ***
## subjNumFHS_003 1.6930 2.7259 0.621 0.5462
## subjNumFHS_004 -7.0208 2.7259 -2.576 0.0243 *
## subjNumFHS_005 21.3149 3.3385 6.385 3.48e-05 ***
## subjNumFHS_006 -7.3921 3.3385 -2.214 0.0469 *
## subjNumFHS_009 -1.7694 3.3385 -0.530 0.6058
## subjNumFHS_013 0.6804 4.3100 0.158 0.8772
## subjNumFHS_016 -3.1292 4.3100 -0.726 0.4817
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3.855 on 12 degrees of freedom
## Multiple R-squared: 0.8745, Adjusted R-squared: 0.8014
## F-statistic: 11.95 on 7 and 12 DF, p-value: 0.0001464
hepFat3<-aov(Hep_fat~subjNum+coder, data=total_data)
summary.lm(hepFat3)
##
## Call:
## aov(formula = Hep_fat ~ subjNum + coder, data = total_data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.7284 -1.2678 0.0000 0.9703 4.0973
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 22.48119 2.15044 10.454 2.47e-06 ***
## subjNumFHS_003 1.69295 2.15044 0.787 0.45136
## subjNumFHS_004 -7.02082 2.15044 -3.265 0.00976 **
## subjNumFHS_005 23.11787 2.77621 8.327 1.60e-05 ***
## subjNumFHS_006 -5.58912 2.77621 -2.013 0.07494 .
## subjNumFHS_009 0.03358 2.77621 0.012 0.99061
## subjNumFHS_013 1.17538 3.61973 0.325 0.75282
## subjNumFHS_016 -2.63422 3.61973 -0.728 0.48527
## coderMichelle 0.13613 2.32274 0.059 0.95454
## coderellen 4.86817 2.48312 1.961 0.08158 .
## coderKatey -2.47997 2.32274 -1.068 0.31346
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3.041 on 9 degrees of freedom
## Multiple R-squared: 0.9414, Adjusted R-squared: 0.8764
## F-statistic: 14.47 on 10 and 9 DF, p-value: 0.0002222
pairwise.t.test(total_data$Hep_fat, total_data$coder, paired=FALSE, p.adjust.method="bonferroni")
##
## Pairwise comparisons using t tests with pooled SD
##
## data: total_data$Hep_fat and total_data$coder
##
## Lisa Michelle ellen
## Michelle 1 - -
## ellen 1 1 -
## Katey 1 1 1
##
## P value adjustment method: bonferroni
fullPlot11<-ggplot(
total_data, aes(
subjNum, Hep_fat, fill=as.factor(coder)))+stat_summary(
fun.y=mean, geom="bar", position="dodge")+stat_summary(
fun.data=mean_cl_normal, geom="errorbar", position=position_dodge(width=0.90), width=0.2)+labs(
x = "subjNum", y = "hep fat")+ labs(
title="hep fat")
fullPlot11
#####SAT BY SUBJECT#####
describeBy(total_data$SAT, total_data$subjNum)
## group: FHS_001
## vars n mean sd median trimmed mad min max range skew
## 1 1 4 1100.88 356.47 985.81 1100.88 150.72 811.89 1620 808.11 0.62
## kurtosis se
## 1 -1.76 178.24
## --------------------------------------------------------
## group: FHS_003
## vars n mean sd median trimmed mad min max range skew
## 1 1 4 392.81 191.61 335.67 392.81 84.81 229.8 670.11 440.31 0.59
## kurtosis se
## 1 -1.77 95.81
## --------------------------------------------------------
## group: FHS_004
## vars n mean sd median trimmed mad min max range skew
## 1 1 4 211.49 111.61 172.86 211.49 55.05 128.43 371.83 243.4 0.58
## kurtosis se
## 1 -1.82 55.81
## --------------------------------------------------------
## group: FHS_005
## vars n mean sd median trimmed mad min max range skew
## 1 1 2 1174.3 177.77 1174.3 1174.3 186.36 1048.6 1300 251.4 0
## kurtosis se
## 1 -2.75 125.7
## --------------------------------------------------------
## group: FHS_006
## vars n mean sd median trimmed mad min max range skew
## 1 1 2 919.63 156.09 919.63 919.63 163.64 809.26 1030 220.74 0
## kurtosis se
## 1 -2.75 110.37
## --------------------------------------------------------
## group: FHS_009
## vars n mean sd median trimmed mad min max range skew
## 1 1 2 650.37 88.87 650.37 650.37 93.17 587.53 713.21 125.68 0
## kurtosis se
## 1 -2.75 62.84
## --------------------------------------------------------
## group: FHS_011
## NULL
## --------------------------------------------------------
## group: FHS_013
## vars n mean sd median trimmed mad min max range skew kurtosis se
## 1 1 1 446.2 NA 446.2 446.2 0 446.2 446.2 0 NA NA NA
## --------------------------------------------------------
## group: FHS_016
## vars n mean sd median trimmed mad min max range skew kurtosis se
## 1 1 1 303.16 NA 303.16 303.16 0 303.16 303.16 0 NA NA NA
satFat2<-aov(SAT~subjNum, data=total_data)
summary(satFat2)
## Df Sum Sq Mean Sq F value Pr(>F)
## subjNum 7 2703738 386248 7.822 0.00111 **
## Residuals 12 592593 49383
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
summary.lm(satFat2)
##
## Call:
## aov(formula = SAT ~ subjNum, data = total_data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -288.99 -91.85 -55.72 74.72 519.12
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1100.88 111.11 9.908 3.96e-07 ***
## subjNumFHS_003 -708.06 157.13 -4.506 0.000719 ***
## subjNumFHS_004 -889.38 157.13 -5.660 0.000106 ***
## subjNumFHS_005 73.42 192.45 0.382 0.709487
## subjNumFHS_006 -181.25 192.45 -0.942 0.364872
## subjNumFHS_009 -450.51 192.45 -2.341 0.037324 *
## subjNumFHS_013 -654.68 248.45 -2.635 0.021773 *
## subjNumFHS_016 -797.72 248.45 -3.211 0.007482 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 222.2 on 12 degrees of freedom
## Multiple R-squared: 0.8202, Adjusted R-squared: 0.7154
## F-statistic: 7.822 on 7 and 12 DF, p-value: 0.001109
satFat3<-aov(SAT~subjNum+coder, data=total_data)
summary.lm(satFat3)
##
## Call:
## aov(formula = SAT ~ subjNum + coder, data = total_data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -195.344 -56.653 4.489 52.553 200.204
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1008.835 100.038 10.085 3.34e-06 ***
## subjNumFHS_003 -708.064 100.038 -7.078 5.81e-05 ***
## subjNumFHS_004 -889.385 100.038 -8.890 9.44e-06 ***
## subjNumFHS_005 186.863 129.149 1.447 0.18185
## subjNumFHS_006 -67.809 129.149 -0.525 0.61224
## subjNumFHS_009 -337.069 129.149 -2.610 0.02827 *
## subjNumFHS_013 -521.445 168.389 -3.097 0.01279 *
## subjNumFHS_016 -664.483 168.389 -3.946 0.00337 **
## coderMichelle -41.190 108.053 -0.381 0.71190
## coderellen 410.962 115.514 3.558 0.00614 **
## coderKatey -1.604 108.053 -0.015 0.98848
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 141.5 on 9 degrees of freedom
## Multiple R-squared: 0.9454, Adjusted R-squared: 0.8846
## F-statistic: 15.57 on 10 and 9 DF, p-value: 0.0001649
pairwise.t.test(total_data$SAT, total_data$coder, paired=FALSE, p.adjust.method="bonferroni")
##
## Pairwise comparisons using t tests with pooled SD
##
## data: total_data$SAT and total_data$coder
##
## Lisa Michelle ellen
## Michelle 1 - -
## ellen 1 1 -
## Katey 1 1 1
##
## P value adjustment method: bonferroni
fullPlot21<-ggplot(
total_data, aes(
subjNum, SAT, fill=as.factor(coder)))+stat_summary(
fun.y=mean, geom="bar", position="dodge")+stat_summary(
fun.data=mean_cl_normal, geom="errorbar", position=position_dodge(width=0.90), width=0.2)+labs(
x = "subjNum", y = "SAT")+ labs(
title="SAT")
fullPlot21
#####VAT BY SUBJECT#####
describeBy(total_data$VAT, total_data$subjNum)
## group: FHS_001
## vars n mean sd median trimmed mad min max range skew
## 1 1 4 570.59 424.61 444.94 570.59 253.9 222.49 1170 947.51 0.52
## kurtosis se
## 1 -1.87 212.3
## --------------------------------------------------------
## group: FHS_003
## vars n mean sd median trimmed mad min max range skew
## 1 1 4 365.23 119.57 353.58 365.23 131.91 254.75 499 244.25 0.09
## kurtosis se
## 1 -2.32 59.79
## --------------------------------------------------------
## group: FHS_004
## vars n mean sd median trimmed mad min max range skew
## 1 1 4 152.97 72.96 153.67 152.97 86.52 70.76 233.79 163.02 -0.01
## kurtosis se
## 1 -2.19 36.48
## --------------------------------------------------------
## group: FHS_005
## vars n mean sd median trimmed mad min max range skew
## 1 1 2 784.55 941.09 784.55 784.55 986.6 119.1 1450 1330.9 0
## kurtosis se
## 1 -2.75 665.45
## --------------------------------------------------------
## group: FHS_006
## vars n mean sd median trimmed mad min max range skew
## 1 1 2 739.99 961.68 739.99 739.99 1008.18 59.98 1420 1360.02 0
## kurtosis se
## 1 -2.75 680.01
## --------------------------------------------------------
## group: FHS_009
## vars n mean sd median trimmed mad min max range skew
## 1 1 2 562.32 488.71 562.32 562.32 512.34 216.74 907.89 691.14 0
## kurtosis se
## 1 -2.75 345.57
## --------------------------------------------------------
## group: FHS_011
## NULL
## --------------------------------------------------------
## group: FHS_013
## vars n mean sd median trimmed mad min max range skew kurtosis se
## 1 1 1 105.81 NA 105.81 105.81 0 105.81 105.81 0 NA NA NA
## --------------------------------------------------------
## group: FHS_016
## vars n mean sd median trimmed mad min max range skew kurtosis se
## 1 1 1 107.81 NA 107.81 107.81 0 107.81 107.81 0 NA NA NA
vatFat2<-aov(VAT~subjNum, data=total_data)
summary(vatFat2)
## Df Sum Sq Mean Sq F value Pr(>F)
## subjNum 7 1089335 155619 0.705 0.669
## Residuals 12 2649040 220753
summary.lm(vatFat2)
##
## Call:
## aov(formula = VAT ~ subjNum, data = total_data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -680.01 -144.29 -2.80 94.06 680.01
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 570.593 234.922 2.429 0.0318 *
## subjNumFHS_003 -205.365 332.230 -0.618 0.5480
## subjNumFHS_004 -417.623 332.230 -1.257 0.2327
## subjNumFHS_005 213.957 406.897 0.526 0.6086
## subjNumFHS_006 169.399 406.897 0.416 0.6845
## subjNumFHS_009 -8.277 406.897 -0.020 0.9841
## subjNumFHS_013 -464.781 525.301 -0.885 0.3937
## subjNumFHS_016 -462.782 525.301 -0.881 0.3956
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 469.8 on 12 degrees of freedom
## Multiple R-squared: 0.2914, Adjusted R-squared: -0.122
## F-statistic: 0.7049 on 7 and 12 DF, p-value: 0.6691
satFat3<-aov(SAT~subjNum+coder, data=total_data)
summary.lm(satFat3)
##
## Call:
## aov(formula = SAT ~ subjNum + coder, data = total_data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -195.344 -56.653 4.489 52.553 200.204
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1008.835 100.038 10.085 3.34e-06 ***
## subjNumFHS_003 -708.064 100.038 -7.078 5.81e-05 ***
## subjNumFHS_004 -889.385 100.038 -8.890 9.44e-06 ***
## subjNumFHS_005 186.863 129.149 1.447 0.18185
## subjNumFHS_006 -67.809 129.149 -0.525 0.61224
## subjNumFHS_009 -337.069 129.149 -2.610 0.02827 *
## subjNumFHS_013 -521.445 168.389 -3.097 0.01279 *
## subjNumFHS_016 -664.483 168.389 -3.946 0.00337 **
## coderMichelle -41.190 108.053 -0.381 0.71190
## coderellen 410.962 115.514 3.558 0.00614 **
## coderKatey -1.604 108.053 -0.015 0.98848
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 141.5 on 9 degrees of freedom
## Multiple R-squared: 0.9454, Adjusted R-squared: 0.8846
## F-statistic: 15.57 on 10 and 9 DF, p-value: 0.0001649
pairwise.t.test(total_data$VAT, total_data$coder, paired=FALSE, p.adjust.method="bonferroni")
##
## Pairwise comparisons using t tests with pooled SD
##
## data: total_data$VAT and total_data$coder
##
## Lisa Michelle ellen
## Michelle 1.0000 - -
## ellen 1.0000 1.0000 -
## Katey 0.0247 0.0011 0.1632
##
## P value adjustment method: bonferroni
fullPlot31<-ggplot(
total_data, aes(
subjNum, VAT, fill=as.factor(coder)))+stat_summary(
fun.y=mean, geom="bar", position="dodge")+stat_summary(
fun.data=mean_cl_normal, geom="errorbar", position=position_dodge(width=0.90), width=0.2)+labs(
x = "subjNum", y = "VAT")+ labs(
title="VAT")
fullPlot31
