% File src/library/datasets/man/anscombe.Rd % Part of the R package, http://www.R-project.org % Copyright 1995-2007 R Core Development Team % Distributed under GPL 2 or later \name{anscombe} \docType{data} \alias{anscombe} \title{Anscombe's Quartet of ``Identical'' Simple Linear Regressions} \description{ Four \eqn{x}-\eqn{y} datasets which have the same traditional statistical properties (mean, variance, correlation, regression line, etc.), yet are quite different. } \usage{anscombe} \format{ A data frame with 11 observations on 8 variables. \tabular{rl}{ x1 == x2 == x3 \tab the integers 4:14, specially arranged \cr x4 \tab values 8 and 19 \cr y1, y2, y3, y4 \tab numbers in (3, 12.5) with mean 7.5 and sdev 2.03} } \source{ Tufte, Edward R. (1989) \emph{The Visual Display of Quantitative Information}, 13--14. Graphics Press. } \references{ Anscombe, Francis J. (1973) Graphs in statistical analysis. \emph{American Statistician}, \bold{27}, 17--21. } \examples{ require(stats); require(graphics) summary(anscombe) ##-- now some "magic" to do the 4 regressions in a loop: ff <- y ~ x for(i in 1:4) { ff[2:3] <- lapply(paste(c("y","x"), i, sep=""), as.name) ## or ff[[2]] <- as.name(paste("y", i, sep="")) ## ff[[3]] <- as.name(paste("x", i, sep="")) assign(paste("lm.",i,sep=""), lmi <- lm(ff, data= anscombe)) print(anova(lmi)) } ## See how close they are (numerically!) sapply(objects(pattern="lm\\\\.[1-4]$"), function(n) coef(get(n))) lapply(objects(pattern="lm\\\\.[1-4]$"), function(n) coef(summary(get(n)))) ## Now, do what you should have done in the first place: PLOTS op <- par(mfrow=c(2,2), mar=.1+c(4,4,1,1), oma= c(0,0,2,0)) for(i in 1:4) { ff[2:3] <- lapply(paste(c("y","x"), i, sep=""), as.name) plot(ff, data =anscombe, col="red", pch=21, bg = "orange", cex = 1.2, xlim=c(3,19), ylim=c(3,13)) abline(get(paste("lm.",i,sep="")), col="blue") } mtext("Anscombe's 4 Regression data sets", outer = TRUE, cex=1.5) par(op) } \keyword{datasets}