17

In an effort to help populate the R tag here, I am posting a few questions I have often received from students. I have developed my own answers to these over the years, but perhaps there are better ways floating around that I don't know about.

The question: I just ran a regression with continuous y and x but factor f (where levels(f) produces c("level1","level2"))

 thelm <- lm(y~x*f,data=thedata)

Now I would like to plot the predicted values of y by x broken down by groups defined by f. All of the plots I get are ugly and show too many lines.

My answer: Try the predict() function.

##restrict prediction to the valid data 
##from the model by using thelm$model rather than thedata

 thedata$yhat <- predict(thelm,
      newdata=expand.grid(x=range(thelm$model$x),
                          f=levels(thelm$model$f)))

 plot(yhat~x,data=thethedata,subset=f=="level1")
 lines(yhat~x,data=thedata,subset=f=="level2")

Are there other ideas out there that are (1) easier to understand for a newcomer and/or (2) better from some other perspective?

Ben Bolker
  • 211,554
  • 25
  • 370
  • 453
Jake
  • 743
  • 1
  • 5
  • 10

4 Answers4

20

The effects package has good ploting methods for visualizing the predicted values of regressions.

thedata<-data.frame(x=rnorm(20),f=rep(c("level1","level2"),10))
thedata$y<-rnorm(20,,3)+thedata$x*(as.numeric(thedata$f)-1)

library(effects)
model.lm <- lm(formula=y ~ x*f,data=thedata)
plot(effect(term="x:f",mod=model.lm,default.levels=20),multiline=TRUE)
Ian Fellows
  • 17,228
  • 10
  • 49
  • 63
3

I am no expert in R. But I use:

xyplot(y ~ x, groups= f, data= Dat, type= c('p','r'), 
   grid= T, lwd= 3, auto.key= T,)

This is also an option:

interaction.plot(f,x,y, type="b", col=c(1:3), 
             leg.bty="0", leg.bg="beige", lwd=1, pch=c(18,24), 
             xlab="", 
             ylab="",
             trace.label="",
             main="Interaction Plot")
Helgi Guðmundsson
  • 736
  • 1
  • 6
  • 18
3

Huh - still trying to wrap my brain around expand.grid(). Just for comparison's sake, this is how I'd do it (using ggplot2):

thedata <- data.frame(predict(thelm), thelm$model$x, thelm$model$f)

ggplot(thedata, aes(x = x, y = yhat, group = f, color = f)) + geom_line()

The ggplot() logic is pretty intuitive, I think - group and color the lines by f. With increasing numbers of groups, not having to specify a layer for each is increasingly helpful.

Matt Parker
  • 26,709
  • 7
  • 54
  • 72
  • 2
    Note that `ggplot2` has a function `fortify.lm` that supplement data with a number of linear model fit statistics – mnel Oct 22 '12 at 22:57
1

Here is a small change to the excellent suggestion by Matt and a solution similar to Helgi but with ggplot. Only difference from above is that I have used the geom_smooth(method='lm) which plots regression lines directly. 

set.seed(1)
y = runif(100,1,10)
x = runif(100,1,10)
f = rep(c('level 1','level 2'),50)
thedata = data.frame(x,y,f)
library(ggplot2)
ggplot(thedata,aes(x=x,y=y,color=f))+geom_smooth(method='lm',se=F)
Vishal Lala
  • 49
  • 3