##### Laboratory Activity A
#####



### Preamble
source("http://rfs.kvasaheim.com/stat200.R")

set.seed(123456)

dt = read.csv("http://rfs.kvasaheim.com/data/heightPop.csv")
attach(dt)

dt
names(dt)
summary(dt)







#####
###  Part I: Simple Random Sampling

sampledPeople = sample(1000, 50)

sampledPeople
height[sampledPeople]

mean(height[sampledPeople])







#####
###  Part II: Cluster Sampling

galesburg = which(zipCode==61401)   ## Galesburg people
monmouth  = which(zipCode==61462)   ## Monmouth people

galSample = sample(galesburg, 10)
monSample = sample(monmouth, 40)

galMean = mean(height[galSample])
monMean = mean(height[monSample])

( galMean + monMean ) / 2







#####
###  Part III: Stratified Sampling

mPeople = which(gender=="M")
fPeople = which(gender=="F")

mSample = sample(mPeople, 10)
fSample = sample(fPeople, 40)

mMean = mean(height[mSample])
fMean = mean(height[fSample])

#
propMale = 0.75
propMale*mMean + (1-propMale)*fMean

#
propMale = 0.25
propMale*mMean + (1-propMale)*fMean


## Graphic
propMale = seq(0, 1, by=0.01)
avgHeight = propMale*mMean + (1-propMale)*fMean

plot(propMale, avgHeight,  pch=20, col="orange",
    xlab="Proportion Male", ylab="Estimated Average Height")







#####
###  Part IV: Systematic Sampling

start = sample(20, 1)
popSample = seq(start, 1000, 20)

mean(height[popSample])


## Graphic
estHeight = numeric()
for( start in 1:20) {
  popSample = seq(start, 1000, 20)
  estHeight[start] = mean(height[popSample])
}

plot(1:20, estHeight, pch=21, bg="tomato",
    xlab="Starting Person (Record)",
    ylab="Estimated Average Height [in.]" )







#####
###  Part V: Convenience Sampling

heights = c(70,65,66,70,65)
mean(heights)




### End of File