#load the xlsx package before proceeding
EColi <- read.xlsx("Ecoli.xls", 1) #Read the first (and only) worksheet in Ecoli.xls

CongWQ <- EColi[substr(EColi$STATION,1,2)=="C-",]
CongWQ$lEcoli <- log(CongWQ$Ecoli)
CongWQ$lFC <- log(CongWQ$FecalColi)
CongWQ$lEntero <- log(CongWQ$Enterococci)

#function to embed histograms in matrixplot
panel.hist <- function(x, ...)
{
    usr <- par("usr"); on.exit(par(usr))
    par(usr = c(usr[1:2], 0, 1.5) )
    h <- hist(x, plot = FALSE)
    breaks <- h$breaks; nB <- length(breaks)
    y <- h$counts; y <- y/max(y)
    rect(breaks[-nB], 0, breaks[-1], y, col="pink ", ...)
}

#matrix scatter plot
pairs(CongWQ[,12:14],diag.panel=panel.hist)

lCongWQ.lm <- lm(lEcoli ~ lFC + lEntero,data=CongWQ)
summary(lCongWQ.lm)

par(mfrow=c(2,2))
plot(lCongWQ.lm)

confint(lCongWQ.lm, level=0.90)

#SENIC data set
senic <- read.delim("SENIC.txt",header=T)
pairs(senic[,-1],cex=.5)

SENIC.lm <- lm(Infection ~ Stay + Facilities + Xray,data=senic)