In murihpusparum/IRI_app: IRI app
pxtablek <- function(x, ...) {
if(class(x)=='list'){
print(xtable::xtable(x[[1]], digits=x$digits, caption=paste('</br>',x$caption) ),type='html', ...)
}else{
print(xtable::xtable(x),type='html', ...)
}
}
opts_chunk$set(echo=FALSE, results='asis',fig.path='tempFiguresForKnitrReport/', fig.width=9, fig.height=7)
This report was created using the BV tool for analyzing biological variation data. BV is developed by Turcosa Analytics and can be accessed online at http://opensoft.turcosa.com.tr/BioVar/
Additional documentation for the BV, including instructions on how to download the application for offline use, can be found at https://github.com/selcukorkmaz/BioVar
Introduction
The steps of analyzing the BV data can be divided into seven steps: (i) detecting outliers, (ii) controlling normality assumption, (iii) checking steady-state condition, (iv) checking homogeneity assumptions, (v) performing subset analysis for genders, (vi) performing analysis of variance and (vii) identifying analytical performance specifications. Here, we presented an online tool for the statistical analysis of the BV data based on guideline by Bartlett et al. (2015), the pipeline by Braga and Panteghini (2016) and the updated checklist by Aarsand et al. (2018).
Bartlett WA, Braga F, Carobene A, Coskun A, Prusa R, et al. A checklist for critical appraisal of studies of biological variation. Clin Chem Lab Med 2015; 53(6):879-85.
Braga F, Panteghini M. Generation of data on within-subject biological variation in laboratory medicine: An update. Crit Rev Clin Lab Sci 2016; 53(5):313-25.
Aarsand AK, Roraas T, Fernandez-Calle P, Ricos C, Diaz-Garzon J, et al. The Biological Variation Data Critical Appraisal Checklist: A Standard for Evaluating Studies on Biological Variation. Clin Chem 2018; 64(3):501-14.
Here are the abbreviations we used in this report:
CV: coefficient of variation
CVA: analytical CV
CVI: within CV
CVG: between CV
II: index of individuality
RCV: reference change values
1. Outlier Detection
It is recommended that outlier detection should be performed using Cochran’s test and Reed’s criterion in three steps:
Step 1: Use the Cochran’s test to check outliers among replicates.
1.1. Table 1: Outliers in the sets of duplicate results using the Cochran test
DT::datatable(outlierResults()[[1]], extensions = c('Buttons','KeyTable', 'Responsive'), options = list(dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
Step 2: Use the Cochran’s test to determine whether a subject distribution was greater or smaller than those of the group as a whole.
1.2. Table 2: Outliers in the variances of the results from each subject using the Cochran test
DT::datatable(outlierResults()[[2]], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
Step 3: Use the Reed’s criterion to determine whether mean value of any subject is significantly greater or smaller compared to other subjects.
1.3 Table 3: Outliers in the variances of the results from each subject using the Cochran test
DT::datatable(outlierResults()[[3]], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
Normality Test
The Shapiro-Wilk test is one of the most widely used and powerful tests for checking normality assumption.
The normality control should be performed in two steps:
Step 1: The normality of each measurand
2.1. Table 1: On set of results from each individual
DT::datatable(normalityResults()[[1]], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
Step 2: The normality of mean values of all subjects
2.2. Table 2: On mean values of subjects
DT::datatable(normalityResults()[[2]], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
3. Steady-State
Subjects is considered in the steady-state, if the 95% confidence interval of the slope of the regression line contains 0.
3.1. Table 1: Linear regression result
DT::datatable(steadyStateResult(), extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
4. Homogeneity
The homogeneity of within-subject and analytical variability should be checked using the Bartlett test.
4.1. Table 1: Homogeneity of analytical variability
res = homogeneityAnalytical(dataSetWithoutOutliers(), subject = "subject", time = "time", replicate="replicate", alpha = input$alphaLevel, decimal = input$decimal, correction = TRUE, test = input$homogeneityTest)
DT::datatable(res, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
4.2. Table 2: Homogeneity of within-subject variability
res = homogeneityWithin(dataSetWithoutOutliers(), subject = "subject", time = "time", replicate="replicate", alpha = input$alphaLevel, decimal = input$decimal, correction = TRUE , test = input$homogeneityTest)
DT::datatable(res, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
5. Subset Analysis
The significant differences in the CVI and CVG between gender groups (i.e. female and male) must be controlled in order to determine whether the estimates should be reported separately for genders. If the 95% confidence intervals of CVI and CVG overlap between genders, then, it is concluded that there is no significant differences between gender groups. Therefore, all-subjects results should be reported for CVI and CVG. In the case of non-overlapping confidence intervals, the results of CVI and CVG should be reported separately for each gender.
5.1. Table 1: Gender comparison for between-subject variation
DT::datatable(subsetCVResults()[[1]], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
5.2. Table 2: Gender comparison for within-subject variation
DT::datatable(subsetCVResults()[[2]], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
5.3. Table 3: Student's t test for mean differences of gender groups
DT::datatable(subsetResults()[[2]], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
The differences between mean values of genders can be compared using a Student t test. If there is no significant difference between mean values of males and females, all-subjects CVI and all-subjects CVG are used to calculate the analytical performance specifications . In the case of the significant difference between mean values of genders, the lowest of the two CVG estimate is used to calculate the analytical performance specifications
3.4. Table 4: Homogeneity test for average within-subject total variance
DT::datatable(subsetResults()[[3]], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
6. Analysis of Variance
6.1. All subjects
6.1.1. Table 1: Reference Change Values (RCV) Results
res = analysisOfVarinceResults()
if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){
result = DT::datatable(res$resultsAllOriginalLme$rcvResult, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && (input$showResult == "cv" || input$showResult == "mom" || input$showResult == "lnmom")){
result = DT::datatable(res$resultsAllCvAnova$rcvResult, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && input$showResult == "transformBack"){
result = DT::datatable(res$resultsAllTransformBackLnLme$rcvResult, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
result
6.1.2. Table 2: Mean and associated confidence interval of the measurand, index of individuality (II) and the number of samples (n)
res = analysisOfVarinceResults()
if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){
result = DT::datatable(res$resultsAllOriginalLme$CVresults[c(1:4,8,9)], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && input$showResult == "cv"){
result = DT::datatable(res$resultsAllCvAnova$CVresults[c(1:4,8,9)], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && input$showResult == "transformBack"){
result = DT::datatable(res$resultsAllTransformBackLnLme$CVresults[c(1:4,8,9)], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
result
6.1.3. Table 3: Analysis of Variance Table
res = analysisOfVarinceResults()
if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){
result = DT::datatable(res$resultsAllOriginalLme$CVTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && input$showResult == "cv"){
result = DT::datatable(res$resultsAllCvAnova$CVTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && input$showResult == "transformBack"){
result = DT::datatable(res$resultsAllTransformBackLnLme$CVTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
result
6.1.4. Table 4: Analytical performance specifications
res = analysisOfVarinceResults()
if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){
result = DT::datatable(res$resultsAllOriginalLme$errorTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && input$showResult == "cv"){
result = DT::datatable(res$resultsAllCvAnova$errorTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && input$showResult == "transformBack"){
result = DT::datatable(res$resultsAllTransformBackLnLme$errorTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
result
6.2. Gender 1
6.2.1. Table 1: Reference Change Values (RCV) Results
res = analysisOfVarinceResults()
if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){
result = DT::datatable(res$resultsOriginalGenderLme1$rcvResult, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && (input$showResult == "cv" || input$showResult == "mom" || input$showResult == "lnmom")){
result = DT::datatable(res$resultsCvAnovaGender1$rcvResult, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && input$showResult == "transformBack"){
result = DT::datatable(res$resultsTransformBackGenderLnLme1$rcvResult, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
result
6.2.2. Table 2: Mean and associated confidence interval of the measurand, index of individuality (II) and the number of samples (n)
res = analysisOfVarinceResults()
if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){
result = DT::datatable(res$resultsOriginalGenderLme1$CVresults[c(1:4,8,9)], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && input$showResult == "cv"){
result = DT::datatable(res$resultsCvAnovaGender1$CVresults[c(1:4,8,9)], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && input$showResult == "transformBack"){
result = DT::datatable(res$resultsTransformBackGenderLnLme1$CVresults[c(1:4,8,9)], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
result
6.2.3. Table 3: Analysis of variance table
res = analysisOfVarinceResults()
if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){
result = DT::datatable(res$resultsOriginalGenderLme1$CVTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && input$showResult == "cv"){
result = DT::datatable(res$resultsCvAnovaGender1$CVTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && input$showResult == "transformBack"){
result = DT::datatable(res$resultsTransformBackGenderLnLme1$CVTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
result
6.2.4. Table 4: Analytical performance specifications
res = analysisOfVarinceResults()
if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){
result = DT::datatable(res$resultsOriginalGenderLme1$errorTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && input$showResult == "cv"){
result = DT::datatable(res$resultsCvAnovaGender1$errorTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && input$showResult == "transformBack"){
result = DT::datatable(res$resultsTransformBackGenderLnLme1$errorTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
result
6.3. Gender 2
6.3.1. Table 1: Reference Change Values (RCV) Results
res = analysisOfVarinceResults()
if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){
result = DT::datatable(res$resultsOriginalGenderLme2$rcvResult, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && (input$showResult == "cv" || input$showResult == "mom" || input$showResult == "lnmom")){
result = DT::datatable(res$resultsCvAnovaGender2$rcvResult, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && input$showResult == "transformBack"){
result = DT::datatable(res$resultsTransformBackGenderLnLme2$rcvResult, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
result
6.3.1. Mean and associated confidence interval of the measurand, index of individuality (II) and the number of samples (n)
result = res = analysisOfVarinceResults()
if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){
result = DT::datatable(res$resultsOriginalGenderLme2$CVresults[c(1:4,8,9)], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && input$showResult == "cv"){
result = DT::datatable(res$resultsCvAnovaGender2$CVresults[c(1:4,8,9)], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && input$showResult == "transformBack"){
result = DT::datatable(res$resultsTransformBackGenderLnLme2$CVresults[c(1:4,8,9)], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
result
6.3.2. Table 3: Analysis of variance table
res = analysisOfVarinceResults()
if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){
result = DT::datatable(res$resultsOriginalGenderLme2$CVTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && input$showResult == "cv"){
result = DT::datatable(res$resultsCvAnovaGender2$CVTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && input$showResult == "transformBack"){
result = DT::datatable(res$resultsTransformBackGenderLnLme2$CVTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
result
6.3.3. Table 4: Analytical performance specifications
res = analysisOfVarinceResults()
if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){
result = DT::datatable(res$resultsOriginalGenderLme2$errorTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && input$showResult == "cv"){
result = DT::datatable(res$resultsCvAnovaGender2$errorTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
if(input$run && input$showResult == "transformBack"){
result = DT::datatable(res$resultsTransformBackGenderLnLme2$errorTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
}
result
7. Plots
Figure 1: Mean and absolute range plot before outlier detection
data = dataAnalysis()
data$replicate.subject = as.numeric(paste0(data[,input$replicate], data[,input$subject]))
names = c(input$subject, input$gender, input$time, input$replicate, "replicate.subject", input$analyte)
dataFull = data[,names]
names(dataFull)[6] = "value"
dataFull = dataFull[complete.cases(dataFull),]
dataFull[dataFull$value <=0,"value"] = NA
dataFull = dataFull[complete.cases(dataFull),]
tbl = table(dataFull$subject)
naSubject = tbl[!(tbl%%2==0)]
naSubject2 = as.numeric(names(naSubject))
if(length(naSubject2) >0){
for(i in 1:length(naSubject2)){
nas3 = dataFull[dataFull$subject == naSubject2[i],]
tbl2 = table(nas3$time)
nas4 = tbl2[!(tbl2%%2==0)]
nas5 = as.numeric(names(nas4))
for(j in 1:length(nas5)){
dataFull[dataFull[,input$subject] == naSubject2[i] & dataFull[,input$time] == nas5[j],"value"] = NA
}
}
}
dataFull = dataFull[complete.cases(dataFull),]
dataFull = dataFull[with(dataFull, order(eval(parse(text=input$gender)))), ]
data_grp <- eval(substitute(group_by(dataFull, eval(parse(text=input$subject)))))
plotData <- dplyr::summarise(data_grp, N = n(), Mean = mean(value), Min = min(value), Max = max(value))
colnames(plotData)[1] = input$subject
gender = as.data.frame(data_grp[,c(input$subject, input$gender)][!duplicated(data_grp[,c(input$subject, input$gender)]), ])
plotData = merge(plotData, gender, by = input$subject)
plotData[,input$subject] <- as.factor(plotData[,input$subject])
plotData = plotData[with(plotData, order(eval(parse(text=input$gender)))), ]
p = ggplot(plotData, aes_string(y = "Mean", x =input$subject, color = input$gender)) +
geom_point() +
geom_errorbar(aes(ymax = Max, ymin = Min), width = 0.35) +
coord_flip() +
theme_bw(base_size = 14) +
ylab(input$analyte) +
xlab("Subjects")+
scale_x_discrete(limits=plotData[,input$subject])
p
Figure 2: Mean and absolute range plot after step 1 outlier detection
data = outlierResults()[[5]]
names = c(input$subject, input$gender, input$time, input$replicate, "replicate.subject", "value")
dataFull = data[,names]
data_grp <- eval(substitute(group_by(dataFull, eval(parse(text=input$subject)))))
plotData <- dplyr::summarise(data_grp, N = n(), Mean = mean(value), Min = min(value), Max = max(value))
colnames(plotData)[1] = input$subject
gender = as.data.frame(data_grp[,c(input$subject, input$gender)][!duplicated(data_grp[,c(input$subject, input$gender)]), ])
plotData = merge(plotData, gender, by = input$subject)
plotData[,input$subject] <- as.factor(plotData[,input$subject])
plotData = plotData[with(plotData, order(eval(parse(text=input$gender)))), ]
ggplot(plotData, aes_string(y = "Mean", x =input$subject, color = input$gender)) +
geom_point() +
geom_errorbar(aes(ymax = Max, ymin = Min), width = 0.35) +
coord_flip() +
theme_bw(base_size = 14) +
ylab(input$analyte) +
xlab("Subjects")+
scale_x_discrete(limits=plotData[,input$subject])
Figure 3: Mean and absolute range plot after step 1 outlier detection
data = outlierResults()[[6]]
names = c(input$subject, input$gender, input$time, input$replicate, "replicate.subject", "value")
dataFull = data[,names]
data_grp <- eval(substitute(group_by(dataFull, eval(parse(text=input$subject)))))
plotData <- dplyr::summarise(data_grp, N = n(), Mean = mean(value), Min = min(value), Max = max(value))
colnames(plotData)[1] = input$subject
gender = as.data.frame(data_grp[,c(input$subject, input$gender)][!duplicated(data_grp[,c(input$subject, input$gender)]), ])
plotData = merge(plotData, gender, by = input$subject)
plotData[,input$subject] <- as.factor(plotData[,input$subject])
plotData = plotData[with(plotData, order(eval(parse(text=input$gender)))), ]
ggplot(plotData, aes_string(y = "Mean", x =input$subject, color = input$gender)) +
geom_point() +
geom_errorbar(aes(ymax = Max, ymin = Min), width = 0.35) +
coord_flip() +
theme_bw(base_size = 14) +
ylab(input$analyte) +
xlab("Subjects")+
scale_x_discrete(limits=plotData[,input$subject])
Figure 4: Mean and absolute range plot after step 3 outlier detection
data = outlierResults()[[4]]
names(data) = c(input$subject, input$gender, input$time, input$replicate, "replicate.subject", "value")
dataFull = data
data_grp <- eval(substitute(group_by(dataFull, eval(parse(text=input$subject)))))
plotData <- dplyr::summarise(data_grp, N = n(), Mean = mean(value), Min = min(value), Max = max(value))
colnames(plotData)[1] = input$subject
gender = as.data.frame(data_grp[,c(input$subject, input$gender)][!duplicated(data_grp[,c(input$subject, input$gender)]), ])
plotData = merge(plotData, gender, by = input$subject)
plotData[,input$subject] <- as.factor(plotData[,input$subject])
plotData = plotData[with(plotData, order(eval(parse(text=input$gender)))), ]
ggplot(plotData, aes_string(y = "Mean", x =input$subject, color = input$gender)) +
geom_point() +
geom_errorbar(aes(ymax = Max, ymin = Min), width = 0.35) +
coord_flip() +
theme_bw(base_size = 14) +
ylab(input$analyte) +
xlab("Subjects")+
scale_x_discrete(limits=plotData[,input$subject])
murihpusparum/IRI_app documentation built on July 11, 2022, 11:48 p.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
pxtablek <- function(x, ...) { if(class(x)=='list'){ print(xtable::xtable(x[[1]], digits=x$digits, caption=paste('</br>',x$caption) ),type='html', ...) }else{ print(xtable::xtable(x),type='html', ...) } } opts_chunk$set(echo=FALSE, results='asis',fig.path='tempFiguresForKnitrReport/', fig.width=9, fig.height=7)
This report was created using the BV tool for analyzing biological variation data. BV is developed by Turcosa Analytics and can be accessed online at http://opensoft.turcosa.com.tr/BioVar/
Additional documentation for the BV, including instructions on how to download the application for offline use, can be found at https://github.com/selcukorkmaz/BioVar
Introduction
The steps of analyzing the BV data can be divided into seven steps: (i) detecting outliers, (ii) controlling normality assumption, (iii) checking steady-state condition, (iv) checking homogeneity assumptions, (v) performing subset analysis for genders, (vi) performing analysis of variance and (vii) identifying analytical performance specifications. Here, we presented an online tool for the statistical analysis of the BV data based on guideline by Bartlett et al. (2015), the pipeline by Braga and Panteghini (2016) and the updated checklist by Aarsand et al. (2018).
Bartlett WA, Braga F, Carobene A, Coskun A, Prusa R, et al. A checklist for critical appraisal of studies of biological variation. Clin Chem Lab Med 2015; 53(6):879-85.
Braga F, Panteghini M. Generation of data on within-subject biological variation in laboratory medicine: An update. Crit Rev Clin Lab Sci 2016; 53(5):313-25.
Aarsand AK, Roraas T, Fernandez-Calle P, Ricos C, Diaz-Garzon J, et al. The Biological Variation Data Critical Appraisal Checklist: A Standard for Evaluating Studies on Biological Variation. Clin Chem 2018; 64(3):501-14.
Here are the abbreviations we used in this report:
CV: coefficient of variation CVA: analytical CV CVI: within CV CVG: between CV II: index of individuality RCV: reference change values
1. Outlier Detection
It is recommended that outlier detection should be performed using Cochran’s test and Reed’s criterion in three steps:
Step 1: Use the Cochran’s test to check outliers among replicates.
1.1. Table 1: Outliers in the sets of duplicate results using the Cochran test
DT::datatable(outlierResults()[[1]], extensions = c('Buttons','KeyTable', 'Responsive'), options = list(dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
Step 2: Use the Cochran’s test to determine whether a subject distribution was greater or smaller than those of the group as a whole.
1.2. Table 2: Outliers in the variances of the results from each subject using the Cochran test
DT::datatable(outlierResults()[[2]], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
Step 3: Use the Reed’s criterion to determine whether mean value of any subject is significantly greater or smaller compared to other subjects.
1.3 Table 3: Outliers in the variances of the results from each subject using the Cochran test
DT::datatable(outlierResults()[[3]], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
Normality Test
The Shapiro-Wilk test is one of the most widely used and powerful tests for checking normality assumption.
The normality control should be performed in two steps:
Step 1: The normality of each measurand
2.1. Table 1: On set of results from each individual
DT::datatable(normalityResults()[[1]], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
Step 2: The normality of mean values of all subjects
2.2. Table 2: On mean values of subjects
DT::datatable(normalityResults()[[2]], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
3. Steady-State
Subjects is considered in the steady-state, if the 95% confidence interval of the slope of the regression line contains 0.
3.1. Table 1: Linear regression result
DT::datatable(steadyStateResult(), extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
4. Homogeneity
The homogeneity of within-subject and analytical variability should be checked using the Bartlett test.
4.1. Table 1: Homogeneity of analytical variability
res = homogeneityAnalytical(dataSetWithoutOutliers(), subject = "subject", time = "time", replicate="replicate", alpha = input$alphaLevel, decimal = input$decimal, correction = TRUE, test = input$homogeneityTest) DT::datatable(res, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
4.2. Table 2: Homogeneity of within-subject variability
res = homogeneityWithin(dataSetWithoutOutliers(), subject = "subject", time = "time", replicate="replicate", alpha = input$alphaLevel, decimal = input$decimal, correction = TRUE , test = input$homogeneityTest) DT::datatable(res, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
5. Subset Analysis
The significant differences in the CVI and CVG between gender groups (i.e. female and male) must be controlled in order to determine whether the estimates should be reported separately for genders. If the 95% confidence intervals of CVI and CVG overlap between genders, then, it is concluded that there is no significant differences between gender groups. Therefore, all-subjects results should be reported for CVI and CVG. In the case of non-overlapping confidence intervals, the results of CVI and CVG should be reported separately for each gender.
5.1. Table 1: Gender comparison for between-subject variation
DT::datatable(subsetCVResults()[[1]], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
5.2. Table 2: Gender comparison for within-subject variation
DT::datatable(subsetCVResults()[[2]], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
5.3. Table 3: Student's t test for mean differences of gender groups
DT::datatable(subsetResults()[[2]], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
The differences between mean values of genders can be compared using a Student t test. If there is no significant difference between mean values of males and females, all-subjects CVI and all-subjects CVG are used to calculate the analytical performance specifications . In the case of the significant difference between mean values of genders, the lowest of the two CVG estimate is used to calculate the analytical performance specifications
3.4. Table 4: Homogeneity test for average within-subject total variance
DT::datatable(subsetResults()[[3]], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE))
6. Analysis of Variance
6.1. All subjects
6.1.1. Table 1: Reference Change Values (RCV) Results
res = analysisOfVarinceResults() if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){ result = DT::datatable(res$resultsAllOriginalLme$rcvResult, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && (input$showResult == "cv" || input$showResult == "mom" || input$showResult == "lnmom")){ result = DT::datatable(res$resultsAllCvAnova$rcvResult, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && input$showResult == "transformBack"){ result = DT::datatable(res$resultsAllTransformBackLnLme$rcvResult, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } result
6.1.2. Table 2: Mean and associated confidence interval of the measurand, index of individuality (II) and the number of samples (n)
res = analysisOfVarinceResults() if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){ result = DT::datatable(res$resultsAllOriginalLme$CVresults[c(1:4,8,9)], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && input$showResult == "cv"){ result = DT::datatable(res$resultsAllCvAnova$CVresults[c(1:4,8,9)], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && input$showResult == "transformBack"){ result = DT::datatable(res$resultsAllTransformBackLnLme$CVresults[c(1:4,8,9)], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } result
6.1.3. Table 3: Analysis of Variance Table
res = analysisOfVarinceResults() if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){ result = DT::datatable(res$resultsAllOriginalLme$CVTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && input$showResult == "cv"){ result = DT::datatable(res$resultsAllCvAnova$CVTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && input$showResult == "transformBack"){ result = DT::datatable(res$resultsAllTransformBackLnLme$CVTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } result
6.1.4. Table 4: Analytical performance specifications
res = analysisOfVarinceResults() if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){ result = DT::datatable(res$resultsAllOriginalLme$errorTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && input$showResult == "cv"){ result = DT::datatable(res$resultsAllCvAnova$errorTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && input$showResult == "transformBack"){ result = DT::datatable(res$resultsAllTransformBackLnLme$errorTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } result
6.2. Gender 1
6.2.1. Table 1: Reference Change Values (RCV) Results
res = analysisOfVarinceResults() if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){ result = DT::datatable(res$resultsOriginalGenderLme1$rcvResult, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && (input$showResult == "cv" || input$showResult == "mom" || input$showResult == "lnmom")){ result = DT::datatable(res$resultsCvAnovaGender1$rcvResult, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && input$showResult == "transformBack"){ result = DT::datatable(res$resultsTransformBackGenderLnLme1$rcvResult, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } result
6.2.2. Table 2: Mean and associated confidence interval of the measurand, index of individuality (II) and the number of samples (n)
res = analysisOfVarinceResults() if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){ result = DT::datatable(res$resultsOriginalGenderLme1$CVresults[c(1:4,8,9)], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && input$showResult == "cv"){ result = DT::datatable(res$resultsCvAnovaGender1$CVresults[c(1:4,8,9)], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && input$showResult == "transformBack"){ result = DT::datatable(res$resultsTransformBackGenderLnLme1$CVresults[c(1:4,8,9)], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } result
6.2.3. Table 3: Analysis of variance table
res = analysisOfVarinceResults() if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){ result = DT::datatable(res$resultsOriginalGenderLme1$CVTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && input$showResult == "cv"){ result = DT::datatable(res$resultsCvAnovaGender1$CVTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && input$showResult == "transformBack"){ result = DT::datatable(res$resultsTransformBackGenderLnLme1$CVTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } result
6.2.4. Table 4: Analytical performance specifications
res = analysisOfVarinceResults() if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){ result = DT::datatable(res$resultsOriginalGenderLme1$errorTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && input$showResult == "cv"){ result = DT::datatable(res$resultsCvAnovaGender1$errorTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && input$showResult == "transformBack"){ result = DT::datatable(res$resultsTransformBackGenderLnLme1$errorTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } result
6.3. Gender 2
6.3.1. Table 1: Reference Change Values (RCV) Results
res = analysisOfVarinceResults() if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){ result = DT::datatable(res$resultsOriginalGenderLme2$rcvResult, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && (input$showResult == "cv" || input$showResult == "mom" || input$showResult == "lnmom")){ result = DT::datatable(res$resultsCvAnovaGender2$rcvResult, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && input$showResult == "transformBack"){ result = DT::datatable(res$resultsTransformBackGenderLnLme2$rcvResult, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } result
6.3.1. Mean and associated confidence interval of the measurand, index of individuality (II) and the number of samples (n)
result = res = analysisOfVarinceResults() if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){ result = DT::datatable(res$resultsOriginalGenderLme2$CVresults[c(1:4,8,9)], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && input$showResult == "cv"){ result = DT::datatable(res$resultsCvAnovaGender2$CVresults[c(1:4,8,9)], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && input$showResult == "transformBack"){ result = DT::datatable(res$resultsTransformBackGenderLnLme2$CVresults[c(1:4,8,9)], extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } result
6.3.2. Table 3: Analysis of variance table
res = analysisOfVarinceResults() if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){ result = DT::datatable(res$resultsOriginalGenderLme2$CVTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && input$showResult == "cv"){ result = DT::datatable(res$resultsCvAnovaGender2$CVTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && input$showResult == "transformBack"){ result = DT::datatable(res$resultsTransformBackGenderLnLme2$CVTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } result
6.3.3. Table 4: Analytical performance specifications
res = analysisOfVarinceResults() if(input$run && (input$showResult == "original" || input$showResult == "lnTransformed")){ result = DT::datatable(res$resultsOriginalGenderLme2$errorTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && input$showResult == "cv"){ result = DT::datatable(res$resultsCvAnovaGender2$errorTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } if(input$run && input$showResult == "transformBack"){ result = DT::datatable(res$resultsTransformBackGenderLnLme2$errorTable, extensions = c('Buttons','KeyTable', 'Responsive'), options = list( dom = 'Bfrtip',buttons = list('copy', 'print', list(extend = 'collection', buttons = c('csv', 'excel', 'pdf'),text = 'Download')), keys = TRUE)) } result
7. Plots
Figure 1: Mean and absolute range plot before outlier detection
data = dataAnalysis() data$replicate.subject = as.numeric(paste0(data[,input$replicate], data[,input$subject])) names = c(input$subject, input$gender, input$time, input$replicate, "replicate.subject", input$analyte) dataFull = data[,names] names(dataFull)[6] = "value" dataFull = dataFull[complete.cases(dataFull),] dataFull[dataFull$value <=0,"value"] = NA dataFull = dataFull[complete.cases(dataFull),] tbl = table(dataFull$subject) naSubject = tbl[!(tbl%%2==0)] naSubject2 = as.numeric(names(naSubject)) if(length(naSubject2) >0){ for(i in 1:length(naSubject2)){ nas3 = dataFull[dataFull$subject == naSubject2[i],] tbl2 = table(nas3$time) nas4 = tbl2[!(tbl2%%2==0)] nas5 = as.numeric(names(nas4)) for(j in 1:length(nas5)){ dataFull[dataFull[,input$subject] == naSubject2[i] & dataFull[,input$time] == nas5[j],"value"] = NA } } } dataFull = dataFull[complete.cases(dataFull),] dataFull = dataFull[with(dataFull, order(eval(parse(text=input$gender)))), ] data_grp <- eval(substitute(group_by(dataFull, eval(parse(text=input$subject))))) plotData <- dplyr::summarise(data_grp, N = n(), Mean = mean(value), Min = min(value), Max = max(value)) colnames(plotData)[1] = input$subject gender = as.data.frame(data_grp[,c(input$subject, input$gender)][!duplicated(data_grp[,c(input$subject, input$gender)]), ]) plotData = merge(plotData, gender, by = input$subject) plotData[,input$subject] <- as.factor(plotData[,input$subject]) plotData = plotData[with(plotData, order(eval(parse(text=input$gender)))), ] p = ggplot(plotData, aes_string(y = "Mean", x =input$subject, color = input$gender)) + geom_point() + geom_errorbar(aes(ymax = Max, ymin = Min), width = 0.35) + coord_flip() + theme_bw(base_size = 14) + ylab(input$analyte) + xlab("Subjects")+ scale_x_discrete(limits=plotData[,input$subject]) p
Figure 2: Mean and absolute range plot after step 1 outlier detection
data = outlierResults()[[5]] names = c(input$subject, input$gender, input$time, input$replicate, "replicate.subject", "value") dataFull = data[,names] data_grp <- eval(substitute(group_by(dataFull, eval(parse(text=input$subject))))) plotData <- dplyr::summarise(data_grp, N = n(), Mean = mean(value), Min = min(value), Max = max(value)) colnames(plotData)[1] = input$subject gender = as.data.frame(data_grp[,c(input$subject, input$gender)][!duplicated(data_grp[,c(input$subject, input$gender)]), ]) plotData = merge(plotData, gender, by = input$subject) plotData[,input$subject] <- as.factor(plotData[,input$subject]) plotData = plotData[with(plotData, order(eval(parse(text=input$gender)))), ] ggplot(plotData, aes_string(y = "Mean", x =input$subject, color = input$gender)) + geom_point() + geom_errorbar(aes(ymax = Max, ymin = Min), width = 0.35) + coord_flip() + theme_bw(base_size = 14) + ylab(input$analyte) + xlab("Subjects")+ scale_x_discrete(limits=plotData[,input$subject])
Figure 3: Mean and absolute range plot after step 1 outlier detection
data = outlierResults()[[6]] names = c(input$subject, input$gender, input$time, input$replicate, "replicate.subject", "value") dataFull = data[,names] data_grp <- eval(substitute(group_by(dataFull, eval(parse(text=input$subject))))) plotData <- dplyr::summarise(data_grp, N = n(), Mean = mean(value), Min = min(value), Max = max(value)) colnames(plotData)[1] = input$subject gender = as.data.frame(data_grp[,c(input$subject, input$gender)][!duplicated(data_grp[,c(input$subject, input$gender)]), ]) plotData = merge(plotData, gender, by = input$subject) plotData[,input$subject] <- as.factor(plotData[,input$subject]) plotData = plotData[with(plotData, order(eval(parse(text=input$gender)))), ] ggplot(plotData, aes_string(y = "Mean", x =input$subject, color = input$gender)) + geom_point() + geom_errorbar(aes(ymax = Max, ymin = Min), width = 0.35) + coord_flip() + theme_bw(base_size = 14) + ylab(input$analyte) + xlab("Subjects")+ scale_x_discrete(limits=plotData[,input$subject])
Figure 4: Mean and absolute range plot after step 3 outlier detection
data = outlierResults()[[4]] names(data) = c(input$subject, input$gender, input$time, input$replicate, "replicate.subject", "value") dataFull = data data_grp <- eval(substitute(group_by(dataFull, eval(parse(text=input$subject))))) plotData <- dplyr::summarise(data_grp, N = n(), Mean = mean(value), Min = min(value), Max = max(value)) colnames(plotData)[1] = input$subject gender = as.data.frame(data_grp[,c(input$subject, input$gender)][!duplicated(data_grp[,c(input$subject, input$gender)]), ]) plotData = merge(plotData, gender, by = input$subject) plotData[,input$subject] <- as.factor(plotData[,input$subject]) plotData = plotData[with(plotData, order(eval(parse(text=input$gender)))), ] ggplot(plotData, aes_string(y = "Mean", x =input$subject, color = input$gender)) + geom_point() + geom_errorbar(aes(ymax = Max, ymin = Min), width = 0.35) + coord_flip() + theme_bw(base_size = 14) + ylab(input$analyte) + xlab("Subjects")+ scale_x_discrete(limits=plotData[,input$subject])
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.