setwd("~/Research/02b Neural Network Research UMR/Data + Analysis/Clustering_Xavier")
umr = read.csv("UMR_all_for_R_with_courses.csv",header = TRUE)

umr = umr[which(umr$Course_collected == "Biochem 1"),]
#gsub
umr[which(umr$Term_collected == "Fall2022"),]$Course_collected = gsub('Biochem 1', 'BiocF22', umr[which(umr$Term_collected == "Fall2022"),]$Course_collected)
umr[which(umr$Term_collected == "Fall2021"),]$Course_collected = gsub('Biochem 1', 'BiocF21', umr[which(umr$Term_collected == "Fall2021"),]$Course_collected)

umrs1 = umr[which(umr$Survey=="ES_Chemical_Reaction"),]
umrs2 = umr[which(umr$Survey=="ES_Glucosidase"),]
umrs3 = umr[which(umr$Survey=="Nucleic_Acids"),]
umrs4 = umr[which(umr$Survey=="Oxygen_Binding"),]
umrs5 = umr[which(umr$Survey=="Protein_Structure"),]

expert = read.csv("Experts_all_for_R.csv",header = TRUE)
exs1 = expert[which(expert$Survey=="ES_Chemical_Equation"),]
exs2 = expert[which(expert$Survey=="ES_Glucosidase"),]
exs3 = expert[which(expert$Survey=="Nucleic_Acids"),]
exs4 = expert[which(expert$Survey=="Oxygen_Binding"),]
exs5 = expert[which(expert$Survey=="Protein_Strcuture"),]

library(psych)

analyzeUMRCourses = function(umrs1){
 #allBiochem = data.frame(matrix(ncol = 8,nrow=0))
 #myCols = c("Institution", "Course_collected", "Deidentifier","Sex_birth","Race_ethnicity","Coherency","PLC","NS")
 #colnames(allBiochem) = myCols

 #allBiochem = rbind(allBiochem,otherss1[myCols])

 ##remove UT/BIO206 and all Dennison and non-Bioc3321 at UMR
 #allBiochem = allBiochem[! grepl("Dennison",allBiochem$Institution ),]
 #allBiochem = allBiochem[! grepl("BIO206",allBiochem$Course_collected),]
 #tempo = umrs1[grep("BIOC3321",umrs1$Course_collected),]
 #allBiochem = rbind(allBiochem,tempo[myCols])
  
  allBiochem = umrs1[,c("Institution", "Course_collected", "Deidentifier","Sex_birth","Race_ethnicity","Coherency","NS","actual_year","PLC")]
  allBiochem$Coherency = as.numeric(allBiochem$Coherency)
  allBiochem$NS = as.numeric(allBiochem$NS)
  allBiochem$PLC = as.numeric(allBiochem$PLC)
  allBiochem$race_binary <- ifelse(allBiochem$Race_ethnicity == "White/Caucasian" , 'White', "Non-white")
   
  #Cluster. Setting one seed, whatever
  set.seed(42)
  df <- matrix(data=c(allBiochem$PLC,allBiochem$NS),ncol=2)
  allBiochem$cluster = kmeans(scale(df[,1:2]),3)$cluster
  
  #this is clumsy but I have to programmatically find the cluster number corresponding to HP, LP, and IP
  #Using the PLC to make sure its working
  meanPLCbyCluster = describeBy(allBiochem$PLC,allBiochem$cluster,mat=TRUE)
  maxPLC = max(meanPLCbyCluster$mean)
  HPgroup = as.numeric(meanPLCbyCluster[which(meanPLCbyCluster$mean==maxPLC),]$group1)
  minPLC = min(meanPLCbyCluster$mean)
  LPgroup = as.numeric(meanPLCbyCluster[which(meanPLCbyCluster$mean==minPLC),]$group1)
  if (HPgroup + LPgroup == 3 ){IPgroup = 3}
  if (HPgroup + LPgroup == 4 ){IPgroup = 2}
  if (HPgroup + LPgroup == 5 ){IPgroup = 1}
  allBiochem$clusterLetter = ifelse(allBiochem$cluster == HPgroup, "HP",
                                    ifelse(allBiochem$cluster == LPgroup,"LP",
                                           ifelse(allBiochem$cluster == IPgroup,"IP","Oops")))  
  allBiochem$Course_collected = factor(allBiochem$Course_collected,levels = c(
    "BiocF21","BiocF22"))
  return(allBiochem)
}

buildTables = function(allBiochem){
  mata<-describeBy(allBiochem$PLC,allBiochem$clusterLetter,mat=TRUE,digits = 2)
  print(knitr::kable(mata[,c(2,4,5,6,7,8,9,10,11,12)] ,  caption = "PLC by cluster group"))
  mata<-describeBy(allBiochem$PLC,allBiochem$Institution,mat=TRUE,digits = 2)
  print(knitr::kable(mata[,c(2,4,5,6,7,8,9,10,11,12)] ,  caption = "PLC by institution"))
  mata<-describeBy(allBiochem$PLC,allBiochem$actual_year,mat=TRUE,digits = 2)
  print(knitr::kable(mata[,c(2,4,5,6,7,8,9,10,11,12)] ,  caption = "PLC by Actual Year"))
  mata<-describeBy(allBiochem$PLC,allBiochem$Course_collected,mat=TRUE,digits = 2)
  print(knitr::kable(mata[,c(2,4,5,6,7,8,9,10,11,12)] ,  caption = "PLC by course"))
  mata<-describeBy(allBiochem$PLC,allBiochem$Sex_birth,mat=TRUE,digits = 2)
  print(knitr::kable(mata[,c(2,4,5,6,7,8,9,10,11,12)] ,  caption = "PLC by Sex"))
  mata<-describeBy(allBiochem$PLC,allBiochem$race_binary,mat=TRUE,digits = 2)
  print(knitr::kable(mata[,c(2,4,5,6,7,8,9,10,11,12)] ,  caption = "PLC by Race"))
}
calcStats = function(allBiochem,mycategory){
  #using the term course as a generic category
   for (course in unique(allBiochem$Course_collected)){
     if ( course == "Expert") next
     header = paste("<b>Results for category: ",course,"</b></br></br>")
     cat(header)
     umrTot= sum(allBiochem$Course_collected == course )
     umrHP = sum(allBiochem$Course_collected == course & allBiochem$clusterLetter == "HP")
     umrIP = sum(allBiochem$Course_collected == course & allBiochem$clusterLetter == "IP")
     umrLP = sum(allBiochem$Course_collected == course & allBiochem$clusterLetter == "LP")
     
     umrMale = sum(allBiochem$Course_collected == course & allBiochem$Sex_birth == "Male")
     umrHPmale = sum(allBiochem$Course_collected == course & allBiochem$Sex_birth == "Male" & allBiochem$clusterLetter == "HP")
     umrIPmale = sum(allBiochem$Course_collected == course & allBiochem$Sex_birth == "Male" & allBiochem$clusterLetter == "IP")
     umrLPmale = sum(allBiochem$Course_collected == course & allBiochem$Sex_birth == "Male" & allBiochem$clusterLetter == "LP")
      
     umrFemale = sum(allBiochem$Course_collected == course & allBiochem$Sex_birth == "Female")
     umrHPfemale = sum(allBiochem$Course_collected == course & allBiochem$Sex_birth == "Female" & allBiochem$clusterLetter == "HP")
     umrIPfemale = sum(allBiochem$Course_collected == course & allBiochem$Sex_birth == "Female" & allBiochem$clusterLetter == "IP")
     umrLPfemale = sum(allBiochem$Course_collected == course & allBiochem$Sex_birth == "Female" & allBiochem$clusterLetter == "LP")
      
     umrWhite = sum(allBiochem$Course_collected == course & allBiochem$race_binary == "White")
     umrHPWhite = sum(allBiochem$Course_collected == course & allBiochem$race_binary == "White" & allBiochem$clusterLetter == "HP")
     umrIPWhite = sum(allBiochem$Course_collected == course & allBiochem$race_binary == "White" & allBiochem$clusterLetter == "IP")
     umrLPWhite = sum(allBiochem$Course_collected == course & allBiochem$race_binary == "White" & allBiochem$clusterLetter == "LP")
      
     umrNonwhite = sum(allBiochem$Course_collected == course & allBiochem$race_binary == "Non-white")
     umrHPNonwhite = sum(allBiochem$Course_collected == course & allBiochem$race_binary == "Non-white" & allBiochem$clusterLetter == "HP")
     umrIPNonwhite = sum(allBiochem$Course_collected == course & allBiochem$race_binary == "Non-white" & allBiochem$clusterLetter == "IP")
     umrLPNonwhite = sum(allBiochem$Course_collected == course & allBiochem$race_binary == "Non-white" & allBiochem$clusterLetter == "LP")
     
     output = paste("<table >
<thead>
<tr>
  <th colspan='2'></th>
  <th colspan='2'>High Performers</th>
  <th colspan='2'>Intermediate Performers</th>
  <th colspan='2'>Low Performers</th>
  
</tr>
</thead>
<tbody>
  <tr>
    <td rowspan='5'>",course," </td>
    <td>Total N=", umrTot,"</td>
    <td colspan='2'>", signif(umrHP/umrTot*100,digits=2),"% </td>
    <td colspan='2'>", signif(umrIP/umrTot*100,digits=2),"%</td>
    <td colspan='2'>", signif(umrLP/umrTot*100,digits=2),"% </td>
  </tr>
  <tr>
    <td rowspan='2'>Sex: males N=",umrMale,"; females N=",umrFemale,"</td>
    <td>male</td>
    <td>female</td>
    <td>male</td>
    <td>female</td>
    <td>male</td>
    <td>female</td>
  </tr>
  <tr>
    <td>", signif(umrHPmale/umrMale*100,digits=2),"%</td>
    <td>", signif(umrHPfemale/umrFemale*100,digits=2),"%</td>
    <td>", signif(umrIPmale/umrMale*100,digits=2),"%</td>
    <td>", signif(umrIPfemale/umrFemale*100,digits=2),"%</td>
    <td>", signif(umrLPmale/umrMale*100,digits=2),"%</td>
    <td>", signif(umrLPfemale/umrFemale*100,digits=2),"%</td>
  </tr>
  <tr>
    <td rowspan='2'>Race: White N=",umrWhite,"; Non-white N=",umrNonwhite,"</td>
    <td>white</td>
    <td>non-white</td>
    <td>white</td>
    <td>non-white</td>
    <td>white</td>
    <td>non-white</td>
  </tr>
  <tr>
    <td>", signif(umrHPWhite/umrWhite*100,digits=2),"%</td>
    <td>", signif(umrHPNonwhite/umrNonwhite*100,digits=2),"%</td>
    <td>", signif(umrIPWhite/umrWhite*100,digits=2),"%</td>
    <td>", signif(umrIPNonwhite/umrNonwhite*100,digits=2),"%</td>
    <td>", signif(umrLPWhite/umrWhite*100,digits=2),"%</td>
    <td>", signif(umrLPNonwhite/umrNonwhite*100,digits=2),"%</td>
  </tr>
</tbody>
</table> ")
     cat(output)
   }
  
}


calcStats2 = function(allBiochem,mycategory){
  #using the term course as a generic   category
   for (course in unique(allBiochem$actual_year)){
     if ( course == "Expert") next
     header = paste("<b>Results for category: ",course,"</b></br></br>")
     cat(header)
     umrTot= sum(allBiochem$actual_year == course )
     umrHP = sum(allBiochem$actual_year == course & allBiochem$clusterLetter == "HP")
     umrIP = sum(allBiochem$actual_year == course & allBiochem$clusterLetter == "IP")
     umrLP = sum(allBiochem$actual_year == course & allBiochem$clusterLetter == "LP")
     
     umrMale = sum(allBiochem$actual_year == course & allBiochem$Sex_birth == "Male")
     umrHPmale = sum(allBiochem$actual_year == course & allBiochem$Sex_birth == "Male" & allBiochem$clusterLetter == "HP")
     umrIPmale = sum(allBiochem$actual_year == course & allBiochem$Sex_birth == "Male" & allBiochem$clusterLetter == "IP")
     umrLPmale = sum(allBiochem$actual_year == course & allBiochem$Sex_birth == "Male" & allBiochem$clusterLetter == "LP")
      
     umrFemale = sum(allBiochem$actual_year == course & allBiochem$Sex_birth == "Female")
     umrHPfemale = sum(allBiochem$actual_year == course & allBiochem$Sex_birth == "Female" & allBiochem$clusterLetter == "HP")
     umrIPfemale = sum(allBiochem$actual_year == course & allBiochem$Sex_birth == "Female" & allBiochem$clusterLetter == "IP")
     umrLPfemale = sum(allBiochem$actual_year == course & allBiochem$Sex_birth == "Female" & allBiochem$clusterLetter == "LP")
      
     umrWhite = sum(allBiochem$actual_year == course & allBiochem$race_binary == "White")
     umrHPWhite = sum(allBiochem$actual_year == course & allBiochem$race_binary == "White" & allBiochem$clusterLetter == "HP")
     umrIPWhite = sum(allBiochem$actual_year == course & allBiochem$race_binary == "White" & allBiochem$clusterLetter == "IP")
     umrLPWhite = sum(allBiochem$actual_year == course & allBiochem$race_binary == "White" & allBiochem$clusterLetter == "LP")
      
     umrNonwhite = sum(allBiochem$actual_year == course & allBiochem$race_binary == "Non-white")
     umrHPNonwhite = sum(allBiochem$actual_year == course & allBiochem$race_binary == "Non-white" & allBiochem$clusterLetter == "HP")
     umrIPNonwhite = sum(allBiochem$actual_year == course & allBiochem$race_binary == "Non-white" & allBiochem$clusterLetter == "IP")
     umrLPNonwhite = sum(allBiochem$actual_year == course & allBiochem$race_binary == "Non-white" & allBiochem$clusterLetter == "LP")
     
     output = paste("<table >
<thead>
<tr>
  <th colspan='2'></th>
  <th colspan='2'>High Performers</th>
  <th colspan='2'>Intermediate Performers</th>
  <th colspan='2'>Low Performers</th>
  
</tr>
</thead>
<tbody>
  <tr>
    <td rowspan='5'>",course," </td>
    <td>Total N=", umrTot,"</td>
    <td colspan='2'>", signif(umrHP/umrTot*100,digits=2),"% </td>
    <td colspan='2'>", signif(umrIP/umrTot*100,digits=2),"%</td>
    <td colspan='2'>", signif(umrLP/umrTot*100,digits=2),"% </td>
  </tr>
  <tr>
    <td rowspan='2'>Sex: males N=",umrMale,"; females N=",umrFemale,"</td>
    <td>male</td>
    <td>female</td>
    <td>male</td>
    <td>female</td>
    <td>male</td>
    <td>female</td>
  </tr>
  <tr>
    <td>", signif(umrHPmale/umrMale*100,digits=2),"%</td>
    <td>", signif(umrHPfemale/umrFemale*100,digits=2),"%</td>
    <td>", signif(umrIPmale/umrMale*100,digits=2),"%</td>
    <td>", signif(umrIPfemale/umrFemale*100,digits=2),"%</td>
    <td>", signif(umrLPmale/umrMale*100,digits=2),"%</td>
    <td>", signif(umrLPfemale/umrFemale*100,digits=2),"%</td>
  </tr>
  <tr>
    <td rowspan='2'>Race: White N=",umrWhite,"; Non-white N=",umrNonwhite,"</td>
    <td>white</td>
    <td>non-white</td>
    <td>white</td>
    <td>non-white</td>
    <td>white</td>
    <td>non-white</td>
  </tr>
  <tr>
    <td>", signif(umrHPWhite/umrWhite*100,digits=2),"%</td>
    <td>", signif(umrHPNonwhite/umrNonwhite*100,digits=2),"%</td>
    <td>", signif(umrIPWhite/umrWhite*100,digits=2),"%</td>
    <td>", signif(umrIPNonwhite/umrNonwhite*100,digits=2),"%</td>
    <td>", signif(umrLPWhite/umrWhite*100,digits=2),"%</td>
    <td>", signif(umrLPNonwhite/umrNonwhite*100,digits=2),"%</td>
  </tr>
</tbody>
</table> ")
     cat(output)
   }
  
}



library(ggplot2)
library(ggpubr)
library(psych)

plotGGbox = function(df,myx,myy,mytitle,myylab){
  df = df[complete.cases(df[[myy]]),]
  maxy = max(df[[myy]])
  ggboxplot(df, x = myx, y = myy,  
            title = mytitle,
            color = myx, add = "jitter", legend="none",ylab = myylab) + rotate_x_text(angle = 45) +  
    geom_hline( yintercept = mean(df[[myy]]), linetype = 2) + 
    stat_compare_means(method = "anova", label.y = maxy*1.10) +
    coord_cartesian(ylim = c(0, maxy*1.2)) + 
    stat_compare_means(label = "p.format", size=2.5, method = "t.test", ref.group = ".all.",label.y = maxy*1.05)
}
getAnova = function(df,myx,myy,mytitle,myylab){
  #get anova
  a<- TukeyHSD( aov(df[[myy]] ~ df[[myx]])) 
  b<-as.data.frame(a$`df[[myx]]`[,4])
  colnames(b) = c("Testing statistical significance: p-values")
  print(knitr::kable(b, caption = paste("Anova: ",mytitle)))
}
plotAndTable = function(df,myx,myy,mytitle,myylab){
  if (myx=="Sex_birth" | myx=="race_binary"){
    df = df[!grepl("(?i)Expert", df$Course_collected),]
    df = df[!grepl("(?)Prefer not to answer",df$Sex_birth),]
  }
  print(plotGGbox(df,myx,myy,mytitle,myylab))
  table = describeBy(df[[myy]],df[[myx]],mat=TRUE,digits = 2)
  print(knitr::kable(table[,c(2,4,5,6,7,10,11,12)],caption=paste("Statistics of ",myylab," based on the category",myx)))
  getAnova(df,myx,myy,mytitle,myylab)
}
addExperts = function(alldf, experts){
  alldf = allBiochem
  ex_new = as.data.frame( matrix( ncol=ncol(alldf),nrow = nrow(experts)) )
  colnames(ex_new) =  colnames(alldf)
  #colnames(ex_new) =  c("Institution", "Course_collected", "Deidentifier","Sex_birth","Race_ethnicity","Coherency","NS","actual_year","PLC","cluster","race_binary","clusterLeter")
  ex_new[,1:12] = "Expert"
  ex_new$PLC = experts$PLC
  ex_new$NS = experts$NS
  ex_new$Coherency = experts$Coherency
  alldf=rbind(alldf,ex_new)
  return(alldf)
}

library(dplyr)
library(corrplot)
plotChi = function(a){
  #I need to use droplevels otherwise it was showing Expert with zeros as a ghost category?
  b=chisq.test(table(droplevels(a)))
  cat(paste("<p><b>The Chi-square analysis gives a p=",round(b$p.value,5),"</b></p>"))
  cat(paste("<p><b>Residuals analysis:</b></p>"))
  cat("A negative residual implies that the measured value is lower than expected and a positive value higher than expected</br>")
  corrplot(b$residuals, is.cor = FALSE)
  #normalize it
  #contrib <- 100*b$residuals^2/b$statistic
  #round(contrib, 3)
  #corrplot(contrib, is.cor = FALSE)
  #corrplot(contrib, is.cor = FALSE, col.lim = c(0.3,1) )


}
plotBarAndCorr = function(df,myx,myy,myxlabel,myylabel,mytitle){
  #myx is the course or demographic variable, the independent variable
  #myy is typically the clusterLetter, the dependent variable
  #remove experts, not useful for the chisquare analysis
  a = df[!grepl("Expert",df[,1]),]
  if (myx=="Sex_birth"){
    a = a[!grepl("(?)Prefer not to answer",a$Sex_birth),]
  }
  #select the two categorical variables
  a = a[,c(myy,myx)]
  print(plotBarCategories(a,myx,myy,myxlabel,myylabel,mytitle))
  plotChi(a)
}
plotBarCategories = function(a,myx,myy,myxlabel,myylabel,mytitle){
  #using aes_string instead of aes because colnames are variables
  #ggplot(a, aes_string(x=myx,fill=myy)) + geom_bar()
  
  
  #c=prop.table(table(a$clusterLetter))
  #scales::percent(as.double(z))
  #a %>% select(clusterLetter) %>% table() %>% prop.table() %>% as.double() %>% scales::percent()
  #this one
  #myx = enquo(myx)
  #myy = enquo(myy)
  a %>% 
    count(!!sym(myy),!!sym(myx))  %>% 
    group_by(!!sym(myx)) %>% 
    mutate(lab = paste0(round(prop.table(n) * 100, 2), '%')) %>%
    ggplot(aes(!!sym(myx),n, fill=!!sym(myy))) + 
    geom_col() + geom_text(aes(label=lab),position='stack',vjust=1.5) +
    labs(x=myxlabel,y=myylabel,title=mytitle)
}

1 Introduction

What was learned from “clustering_indeces_v2” analysis about indicators

PLC seem to clearly distinguish experts from students (with significant overlap though)
NS does not distinguish as much as PLC, but the highest score and median is still significantly different between experts and students
Coherency does not seem to distinguish well and we will discard it in the subsequent analysis

Meaning of PLC and NS * PLC: path length correlation. How connected are two nodes. The closer to one more connected. Compared to expert. * NS: Neighborhood similarity. Compared to the experts.

First we will compare how PLC score is distributed among demographics and courses. Then we will combine students’ PLC and NS indexes as a measurement of students performance. We then cluster the PLC,NS pairs into three groups: Low performers, intermediate, and high performers. We then analyze the composition of those three groups by its demographics, year and courses.

2 UMR courses: ES Chemical Equation

2.1 PLC only: Anova

We are comparing how the PLC score is significantly different among the different categories “Course collected”, “Student year”, “White/Non-white”, and “Sex at birth”

#
allBiochem = analyzeUMRCourses(umrs1)
allBiochem = addExperts(allBiochem,exs1)
#adding experts
#buildTables(allBiochem)
plotAndTable(allBiochem,"Course_collected","PLC","PLC: Course","PLC")

Statistics of PLC based on the category Course_collected
	group1	n	mean	sd	median	min	max	range
X11	BiocF21	58	0.40	0.18	0.45	-0.18	0.67	0.85
X12	BiocF22	43	0.46	0.11	0.47	0.23	0.72	0.49
X13	Expert	6	0.67	0.12	0.69	0.49	0.82	0.33

Anova: PLC: Course
	Testing statistical significance: p-values
BiocF22-BiocF21	0.1008707
Expert-BiocF21	0.0002044
Expert-BiocF22	0.0065317

plotAndTable(allBiochem,"actual_year","PLC","PLC: Year","PLC")

Statistics of PLC based on the category actual_year
	group1	n	mean	sd	median	min	max	range
X11	Expert	6	0.67	0.12	0.69	0.49	0.82	0.33
X12	third_year	101	0.43	0.16	0.46	-0.18	0.72	0.90

Anova: PLC: Year
Testing statistical significance: p-values
0.0002908

plotAndTable(allBiochem,"race_binary","PLC","PLC: White/Non-white","PLC")

Statistics of PLC based on the category race_binary
	group1	n	mean	sd	median	min	max	range
X11	Non-white	41	0.39	0.20	0.45	-0.18	0.72	0.90
X12	White	60	0.45	0.12	0.46	0.05	0.67	0.62

Anova: PLC: White/Non-white
Testing statistical significance: p-values
0.0557923

plotAndTable(allBiochem,"Sex_birth","PLC","PLC: Sex","PLC")

Statistics of PLC based on the category Sex_birth
	group1	n	mean	sd	median	min	max	range
X11	Female	78	0.42	0.15	0.46	-0.07	0.67	0.74
X12	Male	23	0.43	0.17	0.46	-0.18	0.72	0.90

Anova: PLC: Sex
Testing statistical significance: p-values
0.7609849

2.2 NS only: Anova

plotAndTable(allBiochem,"Course_collected","NS","NS: Course","NS")

Statistics of NS based on the category Course_collected
	group1	n	mean	sd	median	min	max	range
X11	BiocF21	58	0.22	0.07	0.23	0.09	0.41	0.32
X12	BiocF22	43	0.24	0.07	0.25	0.13	0.42	0.29
X13	Expert	6	0.37	0.11	0.34	0.28	0.57	0.29

Anova: NS: Course
	Testing statistical significance: p-values
BiocF22-BiocF21	0.3402447
Expert-BiocF21	0.0000134
Expert-BiocF22	0.0002297

plotAndTable(allBiochem,"actual_year","NS","NS: Year","NS")

Statistics of NS based on the category actual_year
	group1	n	mean	sd	median	min	max	range
X11	Expert	6	0.37	0.11	0.34	0.28	0.57	0.29
X12	third_year	101	0.23	0.07	0.24	0.09	0.42	0.33

Anova: NS: Year
Testing statistical significance: p-values
1.05e-05

plotAndTable(allBiochem,"race_binary","NS","NS: White/Non-white","NS")

Statistics of NS based on the category race_binary
	group1	n	mean	sd	median	min	max	range
X11	Non-white	41	0.22	0.07	0.20	0.09	0.41	0.32
X12	White	60	0.24	0.07	0.24	0.10	0.42	0.33

Anova: NS: White/Non-white
Testing statistical significance: p-values
0.0679836

plotAndTable(allBiochem,"Sex_birth","NS","NS: Sex","NS")

Statistics of NS based on the category Sex_birth
	group1	n	mean	sd	median	min	max	range
X11	Female	78	0.23	0.07	0.23	0.09	0.42	0.33
X12	Male	23	0.25	0.05	0.25	0.15	0.35	0.20

Anova: NS: Sex
Testing statistical significance: p-values
0.1931804

2.3 PLC/NS clustering

The problem with clustering is that it is an iterative method and different “initial seeds” will yield to different results. It is only reproducible when the k-means method uses “set.seed(42)”

plotAndTable(allBiochem,"clusterLetter","PLC","PLC: Cluster letter","PLC")

Statistics of PLC based on the category clusterLetter
	group1	n	mean	sd	median	min	max	range
X11	Expert	6	0.67	0.12	0.69	0.49	0.82	0.33
X12	HP	39	0.51	0.08	0.51	0.27	0.63	0.37
X13	IP	40	0.47	0.08	0.47	0.35	0.72	0.37
X14	LP	22	0.19	0.14	0.25	-0.18	0.32	0.50

Anova: PLC: Cluster letter
	Testing statistical significance: p-values
HP-Expert	0.0012654
IP-Expert	0.0000680
LP-Expert	0.0000000
IP-HP	0.4335446
LP-HP	0.0000000
LP-IP	0.0000000

Are cluster groups unevenly distributed among these categories? A chi-square analysis will give us the probability that all three cluster groups (HP,IP,LP) contain statistically similar proportions of this category (course, year, sex, race…)

2.3.1 Analysis by course

plotBarAndCorr(allBiochem,"Course_collected","clusterLetter","Course","N of students","High, Intermediate, Low Performance cluster")

The Chi-square analysis gives a p= 0.06169

Residuals analysis:

A negative residual implies that the measured value is lower than expected and a positive value higher than expected

markerIntegers = as.integer(as.factor(allBiochem$Course_collected))
plot(allBiochem$PLC,allBiochem$NS,pch=allBiochem$clusterLetter,main = "ES_Chemical_Reaction - High(H), Intermediate(I), Low(L) performers",ylab="NS",xlab="PLC",col=markerIntegers)
legend("topleft", legend=unique(allBiochem$Course_collected), col=unique(markerIntegers), lty=1:1, cex=0.8)

calcStats(allBiochem,"Course_collected")

Results for category: BiocF21

		High Performers		Intermediate Performers		Low Performers
BiocF21	Total N= 58	31 %		40 %		29 %
	Sex: males N= 18 ; females N= 40	male	female	male	female	male	female
	Sex: males N= 18 ; females N= 40	61 %	18 %	28 %	45 %	11 %	38 %
	Race: White N= 32 ; Non-white N= 26	white	non-white	white	non-white	white	non-white
	Race: White N= 32 ; Non-white N= 26	31 %	31 %	47 %	31 %	22 %	38 %

Results for category: BiocF22

		High Performers		Intermediate Performers		Low Performers
BiocF22	Total N= 43	49 %		40 %		12 %
	Sex: males N= 5 ; females N= 38	male	female	male	female	male	female
	Sex: males N= 5 ; females N= 38	40 %	50 %	20 %	42 %	40 %	7.9 %
	Race: White N= 28 ; Non-white N= 15	white	non-white	white	non-white	white	non-white
	Race: White N= 28 ; Non-white N= 15	57 %	33 %	36 %	47 %	7.1 %	20 %

3 UMR courses: ES Glucosidase

3.1 PLC only: Anova

We are comparing how the PLC score is significantly different among the different categories “Course collected”, “Student year”, “White/Non-white”, and “Sex at birth”

#
allBiochem = analyzeUMRCourses(umrs2)
allBiochem = addExperts(allBiochem,exs2)
#buildTables(allBiochem)
plotAndTable(allBiochem,"Course_collected","PLC","PLC: Course","PLC")

Statistics of PLC based on the category Course_collected
	group1	n	mean	sd	median	min	max	range
X11	BiocF21	58	0.44	0.17	0.46	-0.16	0.68	0.84
X12	BiocF22	43	0.47	0.10	0.48	0.24	0.65	0.41
X13	Expert	8	0.72	0.09	0.70	0.59	0.82	0.23

Anova: PLC: Course
	Testing statistical significance: p-values
BiocF22-BiocF21	0.4865706
Expert-BiocF21	0.0000021
Expert-BiocF22	0.0000399

plotAndTable(allBiochem,"actual_year","PLC","PLC: Year","PLC")

Statistics of PLC based on the category actual_year
	group1	n	mean	sd	median	min	max	range
X11	Expert	8	0.72	0.09	0.70	0.59	0.82	0.23
X12	third_year	101	0.45	0.15	0.47	-0.16	0.68	0.84

Anova: PLC: Year
Testing statistical significance: p-values
1.2e-06

plotAndTable(allBiochem,"race_binary","PLC","PLC: White/Non-white","PLC")

Statistics of PLC based on the category race_binary
	group1	n	mean	sd	median	min	max	range
X11	Non-white	41	0.42	0.19	0.48	-0.16	0.65	0.81
X12	White	60	0.47	0.10	0.47	0.25	0.68	0.43

Anova: PLC: White/Non-white
Testing statistical significance: p-values
0.058725

plotAndTable(allBiochem,"Sex_birth","PLC","PLC: Sex","PLC")

Statistics of PLC based on the category Sex_birth
	group1	n	mean	sd	median	min	max	range
X11	Female	78	0.45	0.14	0.48	-0.02	0.68	0.70
X12	Male	23	0.44	0.17	0.46	-0.16	0.65	0.81

Anova: PLC: Sex
Testing statistical significance: p-values
0.7177634

3.2 NS only: Anova

plotAndTable(allBiochem,"Course_collected","NS","NS: Course","NS")

Statistics of NS based on the category Course_collected
	group1	n	mean	sd	median	min	max	range
X11	BiocF21	58	0.25	0.09	0.26	0.04	0.45	0.41
X12	BiocF22	43	0.25	0.07	0.23	0.10	0.41	0.31
X13	Expert	8	0.40	0.06	0.42	0.29	0.47	0.17

Anova: NS: Course
	Testing statistical significance: p-values
BiocF22-BiocF21	0.9840602
Expert-BiocF21	0.0000070
Expert-BiocF22	0.0000074

plotAndTable(allBiochem,"actual_year","NS","NS: Year","NS")

Statistics of NS based on the category actual_year
	group1	n	mean	sd	median	min	max	range
X11	Expert	8	0.40	0.06	0.42	0.29	0.47	0.17
X12	third_year	101	0.25	0.08	0.25	0.04	0.45	0.41

Anova: NS: Year
Testing statistical significance: p-values
1e-06

plotAndTable(allBiochem,"race_binary","NS","NS: White/Non-white","NS")

Statistics of NS based on the category race_binary
	group1	n	mean	sd	median	min	max	range
X11	Non-white	41	0.22	0.08	0.23	0.04	0.38	0.35
X12	White	60	0.27	0.08	0.26	0.09	0.45	0.36

Anova: NS: White/Non-white
Testing statistical significance: p-values
0.0017559

plotAndTable(allBiochem,"Sex_birth","NS","NS: Sex","NS")

Statistics of NS based on the category Sex_birth
	group1	n	mean	sd	median	min	max	range
X11	Female	78	0.25	0.07	0.24	0.04	0.42	0.38
X12	Male	23	0.27	0.10	0.26	0.04	0.45	0.41

Anova: NS: Sex
Testing statistical significance: p-values
0.2450175

3.3 PLC/NS clustering

plotAndTable(allBiochem,"clusterLetter","PLC","PLC: Cluster letter","PLC")

Statistics of PLC based on the category clusterLetter
	group1	n	mean	sd	median	min	max	range
X11	Expert	8	0.72	0.09	0.70	0.59	0.82	0.23
X12	HP	22	0.54	0.08	0.55	0.39	0.68	0.29
X13	IP	55	0.49	0.08	0.50	0.28	0.65	0.37
X14	LP	24	0.26	0.15	0.30	-0.16	0.42	0.58

Anova: PLC: Cluster letter
	Testing statistical significance: p-values
HP-Expert	0.0002500
IP-Expert	0.0000002
LP-Expert	0.0000000
IP-HP	0.1805068
LP-HP	0.0000000
LP-IP	0.0000000

3.3.1 Analysis by course

plotBarAndCorr(allBiochem,"Course_collected","clusterLetter","Course","N of students","High, Intermediate, Low Performance cluster")

The Chi-square analysis gives a p= 0.17887

Residuals analysis:

A negative residual implies that the measured value is lower than expected and a positive value higher than expected

markerIntegers = as.integer(as.factor(allBiochem$Course_collected))
plot(allBiochem$PLC,allBiochem$NS,pch=allBiochem$clusterLetter,main = "ES Glucosidase - High(H), Intermediate(I), Low(L) performers",ylab="NS",xlab="PLC",col=markerIntegers)
legend("topleft", legend=unique(allBiochem$Course_collected), col=unique(markerIntegers), lty=1:1, cex=0.8)

calcStats(allBiochem,"Course_collected")

Results for category: BiocF21

		High Performers		Intermediate Performers		Low Performers
BiocF21	Total N= 58	26 %		47 %		28 %
	Sex: males N= 18 ; females N= 40	male	female	male	female	male	female
	Sex: males N= 18 ; females N= 40	28 %	25 %	50 %	45 %	22 %	30 %
	Race: White N= 32 ; Non-white N= 26	white	non-white	white	non-white	white	non-white
	Race: White N= 32 ; Non-white N= 26	34 %	15 %	47 %	46 %	19 %	38 %

Results for category: BiocF22

		High Performers		Intermediate Performers		Low Performers
BiocF22	Total N= 43	16 %		65 %		19 %
	Sex: males N= 5 ; females N= 38	male	female	male	female	male	female
	Sex: males N= 5 ; females N= 38	20 %	16 %	40 %	68 %	40 %	16 %
	Race: White N= 28 ; Non-white N= 15	white	non-white	white	non-white	white	non-white
	Race: White N= 28 ; Non-white N= 15	21 %	6.7 %	68 %	60 %	11 %	33 %

4 UMR courses: Nucleic Acids

4.1 PLC only: Anova

We are comparing how the PLC score is significantly different among the different categories “Course collected”, “Student year”, “White/Non-white”, and “Sex at birth”

#
allBiochem = analyzeUMRCourses(umrs3)
allBiochem = addExperts(allBiochem,exs3)
#buildTables(allBiochem)
plotAndTable(allBiochem,"Course_collected","PLC","PLC: Course","PLC")

Statistics of PLC based on the category Course_collected
	group1	n	mean	sd	median	min	max	range
X11	BiocF21	53	0.14	0.15	0.14	-0.17	0.56	0.72
X12	BiocF22	36	0.16	0.12	0.15	-0.08	0.39	0.47
X13	Expert	7	0.71	0.08	0.69	0.60	0.82	0.22

Anova: PLC: Course
	Testing statistical significance: p-values
BiocF22-BiocF21	0.9031573
Expert-BiocF21	0.0000000
Expert-BiocF22	0.0000000

plotAndTable(allBiochem,"actual_year","PLC","PLC: Year","PLC")

Statistics of PLC based on the category actual_year
	group1	n	mean	sd	median	min	max	range
X11	Expert	7	0.71	0.08	0.69	0.60	0.82	0.22
X12	third_year	89	0.15	0.14	0.14	-0.17	0.56	0.72

Anova: PLC: Year
Testing statistical significance: p-values
0

plotAndTable(allBiochem,"race_binary","PLC","PLC: White/Non-white","PLC")

Statistics of PLC based on the category race_binary
	group1	n	mean	sd	median	min	max	range
X11	Non-white	36	0.14	0.16	0.11	-0.09	0.56	0.64
X12	White	53	0.16	0.12	0.16	-0.17	0.40	0.56

Anova: PLC: White/Non-white
Testing statistical significance: p-values
0.4662513

plotAndTable(allBiochem,"Sex_birth","PLC","PLC: Sex","PLC")

Statistics of PLC based on the category Sex_birth
	group1	n	mean	sd	median	min	max	range
X11	Female	70	0.14	0.13	0.14	-0.09	0.56	0.64
X12	Male	19	0.18	0.16	0.17	-0.17	0.43	0.59

Anova: PLC: Sex
Testing statistical significance: p-values
0.3028995

4.2 NS only: Anova

plotAndTable(allBiochem,"Course_collected","NS","NS: Course","NS")

Statistics of NS based on the category Course_collected
	group1	n	mean	sd	median	min	max	range
X11	BiocF21	53	0.17	0.08	0.15	0.00	0.35	0.35
X12	BiocF22	36	0.17	0.07	0.18	0.03	0.30	0.27
X13	Expert	7	0.43	0.08	0.44	0.33	0.53	0.20

Anova: NS: Course
	Testing statistical significance: p-values
BiocF22-BiocF21	0.9985811
Expert-BiocF21	0.0000000
Expert-BiocF22	0.0000000

plotAndTable(allBiochem,"actual_year","NS","NS: Year","NS")

Statistics of NS based on the category actual_year
	group1	n	mean	sd	median	min	max	range
X11	Expert	7	0.43	0.08	0.44	0.33	0.53	0.20
X12	third_year	89	0.17	0.08	0.15	0.00	0.35	0.35

Anova: NS: Year
Testing statistical significance: p-values
0

plotAndTable(allBiochem,"race_binary","NS","NS: White/Non-white","NS")

Statistics of NS based on the category race_binary
	group1	n	mean	sd	median	min	max	range
X11	Non-white	36	0.17	0.08	0.14	0.03	0.35	0.32
X12	White	53	0.17	0.07	0.17	0.00	0.35	0.35

Anova: NS: White/Non-white
Testing statistical significance: p-values
0.861886

plotAndTable(allBiochem,"Sex_birth","NS","NS: Sex","NS")

Statistics of NS based on the category Sex_birth
	group1	n	mean	sd	median	min	max	range
X11	Female	70	0.17	0.08	0.16	0.00	0.35	0.35
X12	Male	19	0.17	0.08	0.15	0.04	0.35	0.32

Anova: NS: Sex
Testing statistical significance: p-values
0.8502301

4.3 PLC/NS clustering

plotAndTable(allBiochem,"clusterLetter","PLC","PLC: Cluster letter","PLC")

Statistics of PLC based on the category clusterLetter
	group1	n	mean	sd	median	min	max	range
X11	Expert	7	0.71	0.08	0.69	0.60	0.82	0.22
X12	HP	16	0.32	0.10	0.33	0.16	0.56	0.39
X13	IP	44	0.18	0.08	0.17	0.04	0.39	0.35
X14	LP	29	0.01	0.07	0.02	-0.17	0.13	0.29

Anova: PLC: Cluster letter
	Testing statistical significance: p-values
HP-Expert	0e+00
IP-Expert	0e+00
LP-Expert	0e+00
IP-HP	1e-06
LP-HP	0e+00
LP-IP	0e+00

4.3.1 Analysis by course

plotBarAndCorr(allBiochem,"Course_collected","clusterLetter","Course","N of students","High, Intermediate, Low Performance cluster")

The Chi-square analysis gives a p= 0.96462

Residuals analysis:

A negative residual implies that the measured value is lower than expected and a positive value higher than expected

markerIntegers = as.integer(as.factor(allBiochem$Course_collected))
plot(allBiochem$PLC,allBiochem$NS,pch=allBiochem$clusterLetter,main = "Nucleic Acids - High(H), Intermediate(I), Low(L) performers",ylab="NS",xlab="PLC",col=markerIntegers)
legend("topleft", legend=unique(allBiochem$Course_collected), col=unique(markerIntegers), lty=1:1, cex=0.8)

calcStats(allBiochem,"Course_collected")

Results for category: BiocF21

		High Performers		Intermediate Performers		Low Performers
BiocF21	Total N= 53	19 %		49 %		32 %
	Sex: males N= 15 ; females N= 38	male	female	male	female	male	female
	Sex: males N= 15 ; females N= 38	27 %	16 %	53 %	47 %	20 %	37 %
	Race: White N= 29 ; Non-white N= 24	white	non-white	white	non-white	white	non-white
	Race: White N= 29 ; Non-white N= 24	21 %	17 %	59 %	38 %	21 %	46 %

Results for category: BiocF22

		High Performers		Intermediate Performers		Low Performers
BiocF22	Total N= 36	17 %		50 %		33 %
	Sex: males N= 4 ; females N= 32	male	female	male	female	male	female
	Sex: males N= 4 ; females N= 32	0 %	19 %	75 %	47 %	25 %	34 %
	Race: White N= 24 ; Non-white N= 12	white	non-white	white	non-white	white	non-white
	Race: White N= 24 ; Non-white N= 12	12 %	25 %	58 %	33 %	29 %	42 %

5 UMR courses: Oxygen Binding

5.1 PLC only: Anova

We are comparing how the PLC score is significantly different among the different categories “Course collected”, “Student year”, “White/Non-white”, and “Sex at birth”

#
allBiochem = analyzeUMRCourses(umrs4)
allBiochem = addExperts(allBiochem,exs4)
#buildTables(allBiochem)
plotAndTable(allBiochem,"Course_collected","PLC","PLC: Course","PLC")

Statistics of PLC based on the category Course_collected
	group1	n	mean	sd	median	min	max	range
X11	BiocF21	53	0.22	0.26	0.18	-0.25	0.86	1.11
X12	BiocF22	37	0.20	0.13	0.20	-0.04	0.42	0.46
X13	Expert	15	0.69	0.13	0.66	0.52	0.89	0.38

Anova: PLC: Course
	Testing statistical significance: p-values
BiocF22-BiocF21	0.8262867
Expert-BiocF21	0.0000000
Expert-BiocF22	0.0000000

plotAndTable(allBiochem,"actual_year","PLC","PLC: Year","PLC")

Statistics of PLC based on the category actual_year
	group1	n	mean	sd	median	min	max	range
X11	Expert	15	0.69	0.13	0.66	0.52	0.89	0.38
X12	third_year	90	0.21	0.21	0.19	-0.25	0.86	1.11

Anova: PLC: Year
Testing statistical significance: p-values
0

plotAndTable(allBiochem,"race_binary","PLC","PLC: White/Non-white","PLC")

Statistics of PLC based on the category race_binary
	group1	n	mean	sd	median	min	max	range
X11	Non-white	37	0.17	0.24	0.12	-0.25	0.86	1.11
X12	White	53	0.24	0.19	0.22	-0.07	0.69	0.75

Anova: PLC: White/Non-white
Testing statistical significance: p-values
0.1041397

plotAndTable(allBiochem,"Sex_birth","PLC","PLC: Sex","PLC")

Statistics of PLC based on the category Sex_birth
	group1	n	mean	sd	median	min	max	range
X11	Female	70	0.19	0.21	0.17	-0.25	0.80	1.05
X12	Male	20	0.28	0.23	0.26	-0.06	0.86	0.92

Anova: PLC: Sex
Testing statistical significance: p-values
0.1067101

5.2 NS only: Anova

plotAndTable(allBiochem,"Course_collected","NS","NS: Course","NS")

Statistics of NS based on the category Course_collected
	group1	n	mean	sd	median	min	max	range
X11	BiocF21	53	0.21	0.09	0.21	0.06	0.44	0.38
X12	BiocF22	37	0.17	0.06	0.17	0.04	0.30	0.26
X13	Expert	15	0.35	0.09	0.35	0.25	0.53	0.28

Anova: NS: Course
	Testing statistical significance: p-values
BiocF22-BiocF21	0.0601027
Expert-BiocF21	0.0000001
Expert-BiocF22	0.0000000

plotAndTable(allBiochem,"actual_year","NS","NS: Year","NS")

Statistics of NS based on the category actual_year
	group1	n	mean	sd	median	min	max	range
X11	Expert	15	0.35	0.09	0.35	0.25	0.53	0.28
X12	third_year	90	0.19	0.08	0.19	0.04	0.44	0.40

Anova: NS: Year
Testing statistical significance: p-values
0

plotAndTable(allBiochem,"race_binary","NS","NS: White/Non-white","NS")

Statistics of NS based on the category race_binary
	group1	n	mean	sd	median	min	max	range
X11	Non-white	37	0.19	0.09	0.19	0.05	0.39	0.34
X12	White	53	0.20	0.08	0.19	0.04	0.44	0.40

Anova: NS: White/Non-white
Testing statistical significance: p-values
0.7257805

plotAndTable(allBiochem,"Sex_birth","NS","NS: Sex","NS")

Statistics of NS based on the category Sex_birth
	group1	n	mean	sd	median	min	max	range
X11	Female	70	0.19	0.07	0.19	0.04	0.38	0.34
X12	Male	20	0.22	0.11	0.19	0.06	0.44	0.38

Anova: NS: Sex
Testing statistical significance: p-values
0.1452473

5.3 PLC/NS clustering

plotAndTable(allBiochem,"clusterLetter","PLC","PLC: Cluster letter","PLC")

Statistics of PLC based on the category clusterLetter
	group1	n	mean	sd	median	min	max	range
X11	Expert	15	0.69	0.13	0.66	0.52	0.89	0.38
X12	HP	13	0.56	0.16	0.55	0.30	0.86	0.56
X13	IP	40	0.25	0.12	0.26	0.01	0.49	0.48
X14	LP	37	0.04	0.12	0.05	-0.25	0.31	0.56

Anova: PLC: Cluster letter
	Testing statistical significance: p-values
HP-Expert	0.0361071
IP-Expert	0.0000000
LP-Expert	0.0000000
IP-HP	0.0000000
LP-HP	0.0000000
LP-IP	0.0000000

5.3.1 Analysis by course

plotBarAndCorr(allBiochem,"Course_collected","clusterLetter","Course","N of students","High, Intermediate, Low Performance cluster")

The Chi-square analysis gives a p= 0.00934

Residuals analysis:

A negative residual implies that the measured value is lower than expected and a positive value higher than expected

markerIntegers = as.integer(as.factor(allBiochem$Course_collected))
plot(allBiochem$PLC,allBiochem$NS,pch=allBiochem$clusterLetter,main = "Oxygen Binding - High(H), Intermediate(I), Low(L) performers",ylab="NS",xlab="PLC",col=markerIntegers)
legend("topleft", legend=unique(allBiochem$Course_collected), col=unique(markerIntegers), lty=1:1, cex=0.8)

calcStats(allBiochem,"Course_collected")

Results for category: BiocF21

		High Performers		Intermediate Performers		Low Performers
BiocF21	Total N= 53	23 %		34 %		43 %
	Sex: males N= 16 ; females N= 37	male	female	male	female	male	female
	Sex: males N= 16 ; females N= 37	31 %	19 %	25 %	38 %	44 %	43 %
	Race: White N= 29 ; Non-white N= 24	white	non-white	white	non-white	white	non-white
	Race: White N= 29 ; Non-white N= 24	28 %	17 %	34 %	33 %	38 %	50 %

Results for category: BiocF22

		High Performers		Intermediate Performers		Low Performers
BiocF22	Total N= 37	2.7 %		59 %		38 %
	Sex: males N= 4 ; females N= 33	male	female	male	female	male	female
	Sex: males N= 4 ; females N= 33	0 %	3 %	75 %	58 %	25 %	39 %
	Race: White N= 24 ; Non-white N= 13	white	non-white	white	non-white	white	non-white
	Race: White N= 24 ; Non-white N= 13	0 %	7.7 %	75 %	31 %	25 %	62 %

6 UMR courses: Protein Structure

6.1 PLC only: Anova

We are comparing how the PLC score is significantly different among the different categories “Course collected”, “Student year”, “White/Non-white”, and “Sex at birth”

#
allBiochem = analyzeUMRCourses(umrs5)
allBiochem = addExperts(allBiochem,exs5)
#buildTables(allBiochem)
plotAndTable(allBiochem,"Course_collected","PLC","PLC: Course","PLC")

Statistics of PLC based on the category Course_collected
	group1	n	mean	sd	median	min	max	range
X11	BiocF21	51	0.26	0.15	0.29	-0.13	0.54	0.67
X12	BiocF22	35	0.27	0.13	0.27	0.01	0.51	0.51
X13	Expert	7	0.76	0.10	0.79	0.59	0.89	0.30

Anova: PLC: Course
	Testing statistical significance: p-values
BiocF22-BiocF21	0.9552617
Expert-BiocF21	0.0000000
Expert-BiocF22	0.0000000

plotAndTable(allBiochem,"actual_year","PLC","PLC: Year","PLC")

Statistics of PLC based on the category actual_year
	group1	n	mean	sd	median	min	max	range
X11	Expert	7	0.76	0.10	0.79	0.59	0.89	0.30
X12	third_year	86	0.26	0.14	0.28	-0.13	0.54	0.67

Anova: PLC: Year
Testing statistical significance: p-values
0

plotAndTable(allBiochem,"race_binary","PLC","PLC: White/Non-white","PLC")

Statistics of PLC based on the category race_binary
	group1	n	mean	sd	median	min	max	range
X11	Non-white	35	0.26	0.13	0.28	-0.06	0.46	0.52
X12	White	51	0.27	0.15	0.27	-0.13	0.54	0.67

Anova: PLC: White/Non-white
Testing statistical significance: p-values
0.8041316

plotAndTable(allBiochem,"Sex_birth","PLC","PLC: Sex","PLC")

Statistics of PLC based on the category Sex_birth
	group1	n	mean	sd	median	min	max	range
X11	Female	67	0.26	0.14	0.27	-0.13	0.54	0.67
X12	Male	19	0.26	0.16	0.31	-0.03	0.48	0.51

Anova: PLC: Sex
Testing statistical significance: p-values
0.8295141

6.2 NS only: Anova

plotAndTable(allBiochem,"Course_collected","NS","NS: Course","NS")

Statistics of NS based on the category Course_collected
	group1	n	mean	sd	median	min	max	range
X11	BiocF21	51	0.17	0.07	0.17	0.04	0.33	0.29
X12	BiocF22	35	0.18	0.06	0.17	0.08	0.42	0.34
X13	Expert	7	0.35	0.08	0.35	0.24	0.44	0.21

Anova: NS: Course
	Testing statistical significance: p-values
BiocF22-BiocF21	0.7667017
Expert-BiocF21	0.0000000
Expert-BiocF22	0.0000001

plotAndTable(allBiochem,"actual_year","NS","NS: Year","NS")

Statistics of NS based on the category actual_year
	group1	n	mean	sd	median	min	max	range
X11	Expert	7	0.35	0.08	0.35	0.24	0.44	0.21
X12	third_year	86	0.18	0.06	0.17	0.04	0.42	0.38

Anova: NS: Year
Testing statistical significance: p-values
0

plotAndTable(allBiochem,"race_binary","NS","NS: White/Non-white","NS")

Statistics of NS based on the category race_binary
	group1	n	mean	sd	median	min	max	range
X11	Non-white	35	0.17	0.07	0.17	0.04	0.29	0.24
X12	White	51	0.18	0.07	0.17	0.08	0.42	0.34

Anova: NS: White/Non-white
Testing statistical significance: p-values
0.414361

plotAndTable(allBiochem,"Sex_birth","NS","NS: Sex","NS")

Statistics of NS based on the category Sex_birth
	group1	n	mean	sd	median	min	max	range
X11	Female	67	0.18	0.07	0.18	0.07	0.42	0.35
X12	Male	19	0.16	0.06	0.15	0.04	0.29	0.24

Anova: NS: Sex
Testing statistical significance: p-values
0.186288

6.3 PLC/NS clustering

plotAndTable(allBiochem,"clusterLetter","PLC","PLC: Cluster letter","PLC")

Statistics of PLC based on the category clusterLetter
	group1	n	mean	sd	median	min	max	range
X11	Expert	7	0.76	0.10	0.79	0.59	0.89	0.30
X12	HP	24	0.37	0.09	0.37	0.26	0.54	0.29
X13	IP	39	0.30	0.08	0.29	0.16	0.48	0.32
X14	LP	23	0.08	0.09	0.08	-0.13	0.22	0.35

Anova: PLC: Cluster letter
	Testing statistical significance: p-values
HP-Expert	0.0000000
IP-Expert	0.0000000
LP-Expert	0.0000000
IP-HP	0.0354329
LP-HP	0.0000000
LP-IP	0.0000000

6.3.1 Analysis by course

plotBarAndCorr(allBiochem,"Course_collected","clusterLetter","Course","N of students","High, Intermediate, Low Performance cluster")

The Chi-square analysis gives a p= 0.30345

Residuals analysis:

A negative residual implies that the measured value is lower than expected and a positive value higher than expected

markerIntegers = as.integer(as.factor(allBiochem$Course_collected))
plot(allBiochem$PLC,allBiochem$NS,pch=allBiochem$clusterLetter,main = "Protein Structure - High(H), Intermediate(I), Low(L) performers",ylab="NS",xlab="PLC",col=markerIntegers)
legend("topleft", legend=unique(allBiochem$Course_collected), col=unique(markerIntegers), lty=1:1, cex=0.8)

calcStats(allBiochem,"Course_collected")

Results for category: BiocF21

		High Performers		Intermediate Performers		Low Performers
BiocF21	Total N= 51	33 %		39 %		27 %
	Sex: males N= 15 ; females N= 36	male	female	male	female	male	female
	Sex: males N= 15 ; females N= 36	33 %	33 %	33 %	42 %	33 %	25 %
	Race: White N= 28 ; Non-white N= 23	white	non-white	white	non-white	white	non-white
	Race: White N= 28 ; Non-white N= 23	36 %	30 %	36 %	43 %	29 %	26 %

Results for category: BiocF22

		High Performers		Intermediate Performers		Low Performers
BiocF22	Total N= 35	20 %		54 %		26 %
	Sex: males N= 4 ; females N= 31	male	female	male	female	male	female
	Sex: males N= 4 ; females N= 31	0 %	23 %	50 %	55 %	50 %	23 %
	Race: White N= 23 ; Non-white N= 12	white	non-white	white	non-white	white	non-white
	Race: White N= 23 ; Non-white N= 12	22 %	17 %	52 %	58 %	26 %	25 %

Clustering only BIOC3321: F21 vs F22

Xavier Prat-Resina

2023-02-20

1 Introduction

2 UMR courses: ES Chemical Equation

2.1 PLC only: Anova

2.2 NS only: Anova

2.3 PLC/NS clustering

2.3.1 Analysis by course

3 UMR courses: ES Glucosidase

3.1 PLC only: Anova

3.2 NS only: Anova

3.3 PLC/NS clustering

3.3.1 Analysis by course

4 UMR courses: Nucleic Acids

4.1 PLC only: Anova

4.2 NS only: Anova

4.3 PLC/NS clustering

4.3.1 Analysis by course

5 UMR courses: Oxygen Binding

5.1 PLC only: Anova

5.2 NS only: Anova

5.3 PLC/NS clustering

5.3.1 Analysis by course

6 UMR courses: Protein Structure

6.1 PLC only: Anova

6.2 NS only: Anova

6.3 PLC/NS clustering

6.3.1 Analysis by course