Distances between 11 US cities
Airline distances between 11 US cities may be used as an example for multidimensional scaling or cluster analysis.
data(cities)
A data frame with 11 observations on the following 11 variables.
ATLAtlana, Georgia
BOSBoston, Massachusetts
ORDChicago, Illinois
DCAWashington, District of Columbia
DENDenver, Colorado
LAXLos Angeles, California
MIAMiami, Florida
JFKNew York, New York
SEASeattle, Washington
SFOSan Francisco, California
MSYNew Orleans, Lousianna
An 11 x11 matrix of distances between major US airports. This is a useful demonstration of multiple dimensional scaling.
city.location is a dataframe of longitude and latitude for those cities.
Note that the 2 dimensional MDS solution does not perfectly capture the data from these city distances. Boston, New York and Washington, D.C. are located slightly too far west, and Seattle and LA are slightly too far south.
data(cities)
city.location[,1] <- -city.location[,1] #included in the cities data set
plot(city.location, xlab="Dimension 1", ylab="Dimension 2",
main ="Multidimensional scaling of US cities")
#do the mds
city.loc <- cmdscale(cities, k=2) #ask for a 2 dimensional solution round(city.loc,0)
city.loc <- -city.loc #flip the axes
city.loc <- psych::rescale(city.loc,apply(city.location,2,mean),apply(city.location,2,sd))
points(city.loc,type="n") #add the date point to the map
text(city.loc,labels=names(cities))
## Not run: #we need the maps package to be available
#an overlay map can be added if the package maps is available
if(require(maps)) {
map("usa",add=TRUE)
}
## End(Not run)Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.