# Nicholas Horton, nhorton@smith.edu
# Sat Mar 19 09:18:26 EDT 2011
# What proportion of the US is within a mile of a road?
# CAUSE Activity webinar

nsamp = 50  # enough to keep students busy for a class period
long = -runif(nsamp, min=65, max=130)
lat = runif(nsamp,min=25,max=50)

data = cbind(sample=1:nsamp,
   latitude=round(lat, 4),
   longitude=round(long, 4),
   incontinent=c(rep(NA, nsamp)),
   within1mile=c(rep(NA, nsamp)),
   location=character(nsamp),
   notes=character(nsamp))
write.csv(data,file="roadless.csv")

# note filename is different to prevent inadvertent clobbering!
ds = read.csv("myroadless.csv", stringsAsFactors=FALSE)
table(ds$incontinent)

table(ds$location[ds$incontinent==0])

table(ds$location[ds$incontinent==1])

smallds = subset(ds, incontinent==1)
rm(ds)

table(smallds$within1mile)

# need to substitute values here for k (# of successes)
# and n (# of trials)
#binom.test(k, n)