R Is Not So Hard! A Tutorial, Part 3

January 11, 2013
By

(This article was originally published at The Analysis Factor, and syndicated at StatsBlogs.)

by David Lillis, Phd.

In Part 2 of this series, we created two variables and used the lm() command to perform a least squares regression on them, treating one of them as the dependent variable and the other as the independent variable. Here they are again.

height = c(176, 154, 138, 196, 132, 176, 181, 169, 150, 175)

weight = c(82, 49, 53, 112, 47, 69, 77, 71, 62, 78)

Today we learn how to obtain useful diagnostic information about a regression model and then how to draw residuals on a plot. As before, we perform the regression.

lm(height ~ weight)

Call:

lm(formula = height ~ weight)

 

Coefficients:

(Intercept)       weight 


    98.0054       0.9528 

Now let’s find out more about the regression. First, let’s store the regression model as an object called mod and then use the summary() command to learn about the regression.

mod <-  lm(height ~ weight)

summary(mod)

Here is what R gives you.

Call:

lm(formula = height ~ weight)

Residuals:


    Min      1Q  Median      3Q     Max

-10.786  -8.307   1.272   7.818  12.253

 

Coefficients:

            Estimate    Std. Error    t value      Pr(>|t|) 

(Intercept)  98.0054      11.7053      8.373       3.14e-05 ***

weight        0.9528       0.1618      5.889       0.000366 ***

---

Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 9.358 on 8 degrees of freedom

Multiple R-squared: 0.8126,     Adjusted R-squared: 0.7891

F-statistic: 34.68 on 1 and 8 DF,  p-value: 0.0003662

R has given you a great deal of diagnostic information about the regression. The most useful of this information are the coefficients themselves, the Adjusted R-squared, the F-statistic and the p-value for the model. I imagine that you know what these diagnostics mean.

Now let’s use R’s predict() command to create a vector of fitted values

regmodel <- predict(lm(height ~ weight))

regmodel

Here are the fitted values:

1           2             3             4            5

176.1334    144.6916    148.5027    204.7167    142.7861

6            7             8            9            10

163.7472    171.3695    165.6528    157.0778    172.3222

Now let’s plot the data and regression line again.

[Note: R is very picky about the quotation marks you use.  If the font that is displaying this post shows the beginning and ending quotation marks as facing in different directions, it won't work in R.  They both have to look the same--just straight lines.  You may have to retype them within R rather than cutting and pasting.]

plot(weight, height, pch = 16, cex = 1.3, col = "red", main = "MY FIRST PLOT USING R", xlab = "WEIGHT (kg)", ylab = "HEIGHT (cm)")
abline(98.0054, 0.9528)

We can plot the residuals using R’s for loop and a subscript k that runs from 1 to the number of data points. We know that there are 10 data points, but if we do not know the number of data we can find it using the length() command on either the height or weight variable.

npoints <- length(weight)

npoints

[1] 10

Now let’s implement the loop and draw the residuals using the lines() command. Note the syntax we use to draw in the residuals.

for (k in 1: npoints)  lines(c(weight[k], weight[k]), c(height[k], regmodel[k]))

Here is our plot, including the residuals.

None of this was so difficult!

In Part 4 we will look at more advanced aspects of regression models and see what R has to offer.

About the Author: David Lillis has taught R to many researchers and statisticians. His company, Sigma Statistics and Research Limited, provides both on-line instruction and face-to-face workshops on R, and coding services in R. David holds a doctorate in applied statistics.

Bookmark and Share

Like this post?

Enter your email address to have posts delivered:



Please comment on the article here: The Analysis Factor

Tags: ,


Subscribe

Email:

  Subscribe