This preview shows pages 1–3. Sign up to view the full content.
Biological Statistics II
Biometry 3020 / Natural Resources 4130 / Stat Sci 3200
Homework 2
Due on Thursday February 11
1. Now that you are familiar with the grade point average data consider the
diagnostics problem KNNL 3.3, do all components of this problem except
for part e that uses the BrownForsythe test, which we did not cover in
class. Note use a stemandleaf plot in place of doing a dot plot.
a.
(2 points) Prepare a box plot for the ACT scores Xi. Are there any
noteworthy features in this plot?
boxplot(CH01PR19$ACT)
The boxplot looks pretty “normal”. It seems a symmetric, with
most of the data clustered around the middle (kind of bell shaped)
but
with no extreme outliers. Appears to be what would come
from a random sample.
15
20
25
30
35
b.
(2 points) Prepare a stemandleaf plot of the residuals. What
information does this plot provide?
It looks like there are one or two outliers. We may be concerned if they act
as leverage points. But, they may also influence our estimates of the
variance and affect normality assumptions.
stem(resid(GPA.lm))
N = 120
Median = 0.0406183
Quartiles = 0.3456104, 0.444013
Decimal point is at the colon
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentLow:
2.740036
1 : 8
1 : 2221000
0 : 99887766655555
0 : 4444444333333322222211111111000000
0 : 000011111111222222233333344444444
0 : 5555555556666677777888888
1 : 00002
Here is what the stem() plot looks like in R (a little different):
> CH01PR19 = read.table("CH01PR19.txt")
> names(CH01PR19)=c("GPA","ACT")
> GPA.lm = lm(GPA~ACT,data=CH01PR19)
> stem(resid(GPA.lm))
The decimal point is 1 digit(s) to the left of the 
26  4
24 
22 
20 
18  3
16 
14 
12  43
10  7341
8  887
This is the end of the preview. Sign up
to
access the rest of the document.
 Spring '10
 SULLIVAN

Click to edit the document details