######################################################################
# R commands      Stat 704 
# Lab 3           University of South Carolina
# Normal Data Inference
######################################################################
# This file contains the R commands for the lab.
#
# Lines beginning with the symbol '#' are comments in R.  All other
# lines contain code.
#
# In R for Windows, you may wish to open this file from the menu bar
# (File:Display file); you can then copy commands into the command
# window.  (Use the mouse to highlight one or more lines; then
# right-click and select "Paste to console".)
######################################################################
#######
############# Paired T-test Tumor Example 
tumor<-c(1.321, 0.841, 1.423, 0.932, 2.682, 2.011, 0.934, 0.762, 1.230, 0.991, 1.670,
1.120, 3.201, 2.312)
fid<-rep(c(1:7),each=2)
group<-rep(c(0, 1), 7)
group<-ifelse(group==0, "control", "treatment")


df<-data.frame(fid, group, tumor)
ggplot(df, aes(x=factor(group), y=tumor, color=factor(fid), shape=factor(group), group = fid)) + 
  geom_point(position = position_jitter(width = .01)) + 
  geom_smooth(method = 'lm', se = FALSE) + 
  labs(
    x = "x",
    color = "ID",
    shape = 'Class'
  )
  
  

###### paired t test (version1)

t.test(tumor ~ group, paired=T, data=df)

#### equivalently (version2)
control<-df$tumor[group=="control"]
trt<-df$tumor[group=="treatment"]
d<-control-trt
t.test(d)



################################

scores<-c(4.8, 6.4, 6.3, 6.0, 5.4, 
         5.8, 6.1, 6.3, 5.0, 6.2, 
         5.6, 5.0, 6.4, 5.8, 5.5, 
         6.1, 6.0, 6.0, 5.4, 5.8, 
         6.5, 6.0, 6.1, 4.7, 5.6, 
         6.1, 5.8, 4.8, 5.9, 5.4, 
         5.3, 6.0, 5.6, 6.3, 5.2, 
         6.0, 6.4, 5.8, 4.9, 4.1, 
         6.0, 6.4, 5.9, 6.6, 6.0, 
         4.4, 5.9, 6.5, 4.9, 5.4, 
         5.8, 5.6, 6.2, 6.3, 5.8, 
         5.9, 6.5, 5.4, 5.9, 6.1, 
         6.6, 4.7, 5.5, 5.0, 5.5, 
         5.7, 4.3, 4.9, 3.4, 5.1, 
         4.8, 5.0, 5.5, 5.7, 5.0, 
         5.2, 4.2, 5.7, 5.9, 5.8, 
         4.2, 5.7, 4.8, 4.6, 5.0, 
         4.9, 6.3, 5.6, 5.7, 5.1, 
         5.8, 3.8, 5.0, 6.1, 4.4, 
         3.9, 6.3, 6.3, 4.8, 6.1, 
         5.3, 5.1, 5.5, 5.9, 5.5, 
         6.0, 5.4, 5.9, 5.5, 6.0)
         
status<-c(rep("Attended", 63), rep("NotAttend", 47))
dat<-data.frame(scores, status)
str(dat)
###### plot side-by-side dotplot 

pdf("/Users/yen-yiho/Desktop/STAT704/Notes/Lecture2-RandomVariable/Teaching.pdf")
stripchart(dat[,1] ~ dat[,2], pch=16, method="jitter", jitter=0.2, vertical=TRUE, ylab="Teaching Score",  xlab="Attendance Status", ylim=c(min(dat[,1]), max(dat[,1])))
abline(v=1, col="grey", lty=2)
abline(v=2, col="grey", lty=2)
lines(x=c(0.9, 1.1), rep(mean(dat[keep,1]),2), col=4)
lines(x=c(1.9, 2.1), rep(mean(dat[-keep,1]),2), col=4)
dev.off()

boxplot(dat$scores ~ dat$status, xlab="Status", ylab="Scores")

####### perfrom independent two-sample t test  
t.test(scores ~ status, var.equal=T)
t.test(scores ~ status)


######## 
x<-factor(rep(c(1,2,3), each=10))
str(x)
table(x)
ThreeGroup<-aov(y ~ x)
sum<-summary(ThreeGroup)
sum