Using R for Introductory Statistics : John Verzani

Using R for introductory statistics 98> the.labels = c("lm","lm w/o 1","least trimmedsquares”,+ "rlm with MM")> the.ltys = 1:4> legend(5000,6000,legend=the.labels,lty=the.Itys)Figure 3.15 Emissions data with fourdifferent regression lines3.4.7 Trend linesIf a scatterplot suggests some relationship, but not an obvious transformation to make alinear relationship, we can still superimpose a “trend line” on top of the data using one ofthe many scatterplot smoothing techniques available in R. These produce a smooth curvesummarizing the relationship between the two variables.The stats package provides several functions for creating trend lines. The scatter.smooth() function uses the loess() function from the same package to plot both thescatterplot and a trend line. Additionally, smooth. spline() will fit the data using cubicsplines, and the supsmu() function will perform Friedman’s “super smoother” algorithm.■ Example 3.9: Five years of temperature data Weather data should show seasonaltrends. The data set five.yr. temperature (UsingR) has five years of New York Citytemperature data. A scatterplot shows a periodic, sinusoidal pattern. In Figure 3.16, threetrend lines are shown, although two are nearly identical.> attach(five.yr.temperature)> scatter.smooth(temps ~ days,col=gray(.75),bty="n”)> lines(smooth.spline(temps ~ days), lty=2, lwd=2)> lines(supsmu(days, temps), lty=3, lwd=2)> legend(locator(1),lty=c(1,2,3),lwd=c(1,2,2),+ legend=c("scatter.smooth","smooth.spline","supsmu"))> detach(five.yr.temperature)