You are on page 1of 27

Given are five observations for two variables, x and y.

xi 1 2 3 4 5
yi 3 7 5 11 14
a. Develop a scatter diagram for these data.
b. What does the scatter diagram developed in part (a) indicate about the relationship
between the two variables?
c. Try to approximate the relationship between x and y by drawing a straight line
through the data.
d. Develop the estimated regression equation by computing the values of b0 and b1 using
equations (14.6) and (14.7).
e. Use the estimated regression equation to predict the value of y when x _x0002_ 4.

xi yi
1 3
2 7
3 5
4 11
5 14
Given are five observations for two variables, x and y.
xi 1 2 3 4 5
yi 3 7 5 11 14
a. Develop a scatter diagram for these data.
b. What does the scatter diagram developed in part (a) indicate about the relationship
between the two variables?
c. Try to approximate the relationship between x and y by drawing a straight line
through the data.
d. Develop the estimated regression equation by computing the values of b0 and b1 using
equations (14.6) and (14.7).
e. Use the estimated regression equation to predict the value of y when x _x0002_ 4.

xi yi
1 3 16
2 7 14
3 5 12 f(x) = 2.6545
R² = 0.96890
4 11
10
5 14

Axis Title
8

n 5 6
4
2
0
There appears to be a positive linear relationship between x and y. 0.5 1 1.5

x(bar) 3
Y(bar) 8

slope 2.6
intercept 0.2

equation y=(2.6)x+0.2
Chart Title
16
14
12 f(x) = 2.65454545454545 x
R² = 0.968909090909091
10
Axis Title

8
6
4
2
0
0.5 1 1.5 2 2.5 3 3.5 4 4.5 5 5.5

X
The data from exercise 1 follow.
xi 1 2 3 4 5
yi 3 7 5 11 14
The estimated regression equation for these data is _x0002_ .20 + 2.60x.
a. Compute SSE, SST, and SSR using equations (14.8), (14.9), and (14.10).
b. Compute the coefficient of determination r2. Comment on the goodness of fit.
c. Compute the sample correlation coefficient.

xi yi yi-y(bar) equation y=0.2+2.6*x


1 3
2 7
3 5
4 11
5 14
The data from exercise 1 follow.
xi 1 2 3 4 5
yi 3 7 5 11 14
The estimated regression equation for these data is _x0002_ .20 + 2.60x.
a. Compute SSE, SST, and SSR using equations (14.8), (14.9), and (14.10).
b. Compute the coefficient of determination r2. Comment on the goodness of fit.
c. Compute the sample correlation coefficient.

xi yi yi-y(bar) equation y=0.2+2.6*x


1 3 -5 25 2.8 0.2 0.04
2 7 -1 1 5.4 1.6 2.56
3 5 -3 9 8 -3 9
4 11 3 9 10.6 0.4 0.16
5 14 6 36 13.2 0.8 0.64
80 12.4
Y = 0.2+2.6(x)

y(bar) 8
SST 80
SSE 12.4

SST = SSR +SSE


SSR = SST - SSE
SSR 67.6

r^2 SSR / SST 0.845


least squre line provided a very good fit, i.e. 84.5% of the variablity in y has been
explained by the least square lines
a. The estimated regression equation and the mean for the dependent variable are:

yi  0.2  2.6 xi y 8

The sum of squares due to error and the total sum of squares are

SSE  ( yi  yi ) 2  12.40 SST  ( yi  y ) 2  80


Thus, SSR = SST - SSE = 80 - 12.4 = 67.6

b. r2 = SSR/SST = 67.6/80 = .845


The least squares line provided a very good fit; 84.5% of the variability in y ha

c.
rxy  .845  .9192
it; 84.5% of the variability in y has been explained by the least squares line.
Team Yds/Att Win% The National Football League (NFL) records a variety of per
Arizona Cardinals 6.5 50 and teams. To investigate the importance of passing on the
Atlanta Falcons 7.1 63 by a team, the following data show the average number of
Carolina Panthers 7.4 38 (Yds/Att) and the percentage of games won (WinPct) for a
Chicago Bears 6.4 50 teams for the 2011 season (NFL website, February 12, 2012
Dallas Cowboys 7.4 50
New England Patriots 8.3 81 a. Develop a scatter diagram with the number of passing ya
Philadelphia Eagles 7.4 50 axis and the percentage of games won on the vertical axis.
Seattle Seahawks 6.1 44 b. What does the scatter diagram developed in part (a) ind
St. Louis Rams 5.2 13 between the two variables?
Tampa Bay Buccaneers 6.2 25 c. Develop the estimated regression equation that could be
of games won given the average number of passing yards p
d. Provide an interpretation for the slope of the estimated
e. For the 2011 season, the average number of passing yar
City Chiefs was 6.2. Use the estimated regression equation
predict the percentage of games won by the Kansas City Ch
season the Kansas City Chiefs record was 7 wins and 9 loss
to the actual percentage of games won by the Kansas City
NFL) records a variety of performance data for individuals
mportance of passing on the percentage of games won
how the average number of passing yards per attempt
games won (WinPct) for a random sample of 10 NFL
website, February 12, 2012).

th the number of passing yards per attempt on the horizontal


es won on the vertical axis.
m developed in part (a) indicate about the relationship

ssion equation that could be used to predict the percentage


e number of passing yards per attempt.
the slope of the estimated regression equation.
rage number of passing yards per attempt for the Kansas
mated regression equation developed in part (c) to
s won by the Kansas City Chiefs. (Note: For the 2011
ecord was 7 wins and 9 losses.) Compare your prediction
mes won by the Kansas City Chiefs.
Brokerage Speed Satisfaction The American Association of Individual Investors (AAII) On-Line Discount
Scottrade, 3.4 3.5 polls members on their experiences with discount brokers. As part of th
Charles Sc 3.3 3.4 members were asked to rate the quality of the speed of execution with
Fidelity Br 3.4 3.9 as provide an overall satisfaction rating for electronic trades. Possible re
TD Ameritr 3.6 3.7 were no opinion (0), unsatisfied (l), somewhat satisfied (2), satisfied (3),
E*Trade Fi 3.2 2.9 (4). For each broker summary scores were computed by calculating a we
Vanguard B 3.8 2.8 of the scores provided by each respondent. A portion of the survey resu
USAA Broke 3.8 3.6 (AAII website, February 7, 2012).
Thinkorsw 2.6 2.6
Wells Farg 2.7 2.3
Interactive 4 4 a. Develop a scatter diagram for these data with the speed of execution
Zecco.com 2.5 2.5 variable.
b. What does the scatter diagram developed in part (a) indicate about th
between the two variables?
c. Develop the least squares estimated regression equation.
d. Provide an interpretation for the slope of the estimated regression eq
e. Suppose Zecco.com developed new software to increase their speed o
If the new software is able to increase their speed of execution rating fro
value of 2.5 to the average speed of execution rating for the other 10 br
estors (AAII) On-Line Discount Broker Survey
discount brokers. As part of the survey,
f the speed of execution with their broker as well
r electronic trades. Possible responses (scores)
what satisfied (2), satisfied (3), and very satisfied
computed by calculating a weighted average
t. A portion of the survey results follow

a with the speed of execution as the independent

ed in part (a) indicate about the relationship

ression equation.
of the estimated regression equation.
ftware to increase their speed of execution rating.
ir speed of execution rating from the current
tion rating for the other 10 brokerage firm
Company Stock Pric Stock Pric % IncreaseOptions anOptions an% Gain in Options Value
Ford Moto 2.63 15.58 492 16 202.8 1168
Abercrombi 23.8 70.47 196 46.2 196.1 324
Nabors Ind 9.99 32.06 221 37.2 132.2 255
Starbucks 9.99 32.06 221 12.4 75.9 512
Salesforce 32.73 137.61 320 7.8 67 759
Starwood H 12.7 60.28 375 5.8 57.1 884
Caterpillar 27.96 111.94 300 4 47.5 1088
Oracle 18.07 34.97 94 61.9 97.5 58
Capital On 12.24 54.61 346 6 40.6 577
Dow Chemi 8.43 39.97 374 5 38.8 676
On March 31, 2009, Ford Motor Company’s shares were trading at a 26-year low of $2.63.
Ford’s board of directors gave the CEO a grant of options and restricted shares with an estimated
value of $16 million. On April 26, 2011, the price of a share of Ford had increased
to $15.58, and the CEO’s grant was worth $202.8 million, a gain in value of $186.8 million.
The following table shows the share price in 2009 and 2011 for 10 companies, the stockoption
and share grants to the CEOs in late 2008 and 2009, and the value of the options and
grants in 2011. Also shown are the percentage increases in the stock price and the percentage
gains in the options values (The Wall Street Journal, April 27, 2011)

a. Develop a scatter diagram for these data with the percentage increase in the stock price
as the independent variable.
b. What does the scatter diagram developed in part (a) indicate about the relationship
between the two variables?
c. Develop the least squares estimated regression equation.
d. Provide an interpretation for the slope of the estimated regression equation.
e. Do the rewards for the CEO appear to be based on performance increases as measured
by the stock price?
Years Sales a. Use the data to develop an estimated regression equation that could be used to estimate
1 80 the price for a bike given the weight.
3 97 a. Compute SST, SSR, and SSE.
4 92 b. Compute the coefficient of determination r2. Comment on the goodness of fit.
4 102 c. What is the value of the sample correlation coefficient?
6 103
8 111
10 119
10 123
11 117
13 136
7 108
at could be used to estimate

e goodness of fit.
Brand Weight Price Bicycling, the world’s leading cycling magazine, reviews
FELT F5 17.8 2100 the year. Their “Road-Race” category contains reviews o
PINARELLO Paris 16.1 6250 interested in racing. One of the most important factors
ORBEA Orca GDR 14.9 8370 weight of the bike. The following data show the weight
EDDY MERCKX EMX-7 15.9 6200 bikes reviewed by the magazine (Bicycling website, Mar
BH RC1 Ultegra 17.2 4000
BH Ultralight 386 13.1 8600 a. Use the data to develop an estimated regression equa
CERVELO S5 Team 16.2 6000 the price for a bike given the weight.
GIANT TCR Advanced 2 17.1 2580 b. Compute r2. Did the estimated regression equation p
WILIER TRIESTINA Gran Tu 17.6 3400 c. Predict the price for a bike that weighs 15 pounds.
SPECIALIZED S-Works Amira 14.1 8000
cling magazine, reviews hundreds of bicycles throughout
egory contains reviews of bikes used by riders primarily
most important factors in selecting a bike for racing is the
ng data show the weight (pounds) and price ($) for 10 racing
e (Bicycling website, March 8, 2012).

stimated regression equation that could be used to estimate

ed regression equation provide a good fit?


at weighs 15 pounds.
Fatal
Percent Accidents
Under 21 per 1000
13 2.962 Case Study (Page 673) US Department of Transportation
12 0.708
8 0.885 As part of a study on transportation safety, the U.S. Department of Transportation collected
12 1.652 data on the number of fatal accidents per 1000 licenses and the percentage of licensed driver
11 2.091 under the age of 21 in a sample of 42 cities. Data collected over a one-year period follow.
17 2.627 These data are contained in the file named Safety.
18 3.83
8 0.368 Managerial Report
13 1.142 1. Develop numerical and graphical summaries of the data.
8 0.645 2. Use regression analysis to investigate the relationship between the number of fatal
9 1.028 accidents and the percentage of drivers under the age of 21. Discuss your findings.
16 2.801 3. What conclusion and recommendations can you derive from your analysis?
12 1.405
9 1.433
10 0.039
9 0.338
11 1.849
12 2.246
14 2.855
14 2.352
11 1.294
17 4.1
8 2.19
16 3.623
15 2.623
9 0.835
8 0.82
14 2.89
8 1.267
15 3.224
10 1.014
10 0.493
14 1.443
18 3.614
10 1.926
14 1.643
16 2.943
12 1.913
15 2.814
13 2.634
9 0.926
17 3.256
t of Transportation collected
percentage of licensed drivers
a one-year period follow.

en the number of fatal


scuss your findings.
your analysis?

You might also like