Statistics 200 B1
Exam 2
Name:_Solutions _
Closed book and notes. You are allowed a calculator and one 8.5 x 11 inch sheet
(two-sided) of formulas and other information.
Please be aware that assisting another student on the exam or receiving assistance fr
R code
2.110
Without Outlier
To find the slope and y intercept I used: cor(Isotope,Silicon)*sd(Silicon)/sd(Isotope) and
mean(Silicon)-cor(Isotope,Silicon)*sd(Silicon)/sd(Isotope)*mean(Isotope). The slope is -75.517
and a y intercept of -137.156
With outli
Statistics 200 Exam 1
Name:_SOLUTIONS_
Each problem is worth the same total number of points. Show how you get your answers.
If you use a calculator function, then say what function you used and what you entered.
Here are a few formulas and expressions as
Statistics 200 B1 Exam 1
3/04/2010
Name:_Solutions_
NetID: _
There are 6 problems and a bonus problem.
Each problem is worth the same total number of points.
Here are a few formulas and expressions as reminders:
xi x y i
1
n 1 s x s y
r=
y
b1 = r
P ( A
Lee Rushing
10/15/12
6.71
a. The null hypothesis is the mean is 0. The alternative hypothesis is not 0. The mean is the
mean difference.
mean(Diff)*sqrt(20)/3
[1]4.069644
The z score is 4.07 which gives a really small probability.
hist(MPG)
It is not appr
Homework 9 Solutions
Its also right if you state the alternative hypothesis as p1 p2
If you use R for (e), use: >chisq.test(table, correct=FALSE),because R in
default use |observation-expected|(absolute instead of square) for 2X2 table. Look for details
i
7.41. (a) We test Ho: ,0; = 0 versus Ha: ,u, > 0, where ,u, is the mean 0 6
change in score (that is, the mean improvement). (b) The distlibu 3
tion is slightly leftskewed, with mean .1? = 2.5 and s i 2.8928. :0 O
_2.5U; 'f _ [' . _ . . a
(c)r 3.864), df
Example of regression diagnostic plots in R commander
UN data on fertility
1. Launch R commander
2. Import the data from UN2.csv
3. Statistics Fit models Linear model
(regress logFertility on logPPgdp and Purban)
4. Models Graphs Basic diagnostic graphs (
# Looking at relations between qualitative variables:
# Two-way tables
# Read in data on flight delays from MMC p. 150
# Enter the cell counts in a matrix and convert to a table
delay = matrix(c(718,5534,74,532),ncol=2,byrow=T)
colnames(delay)=c("Alaska