Beruflich Dokumente
Kultur Dokumente
by Ken Black
Chapter 13
Discrete Distributions
Simple Regression
Analysis
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-1
Learning Objectives
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-2
Regression and Correlation
• Regression analysis is the process of
constructing a mathematical model or
function that can be used to predict or
determine one variable by another variable.
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-3
Simple Regression Analysis
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-4
Airline Cost Data
Number of
Passengers Cost ($1,000)
X Y
61 4.280
63 4.080
67 4.420
69 4.170
70 4.480
74 4.300
76 4.820
81 4.700
86 5.110
91 5.130
95 5.640
97 5.560
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-5
Scatter Plot of Airline Cost Data
4
Cost ($1000)
0
0 20 40 60 80 100 120
Number of Passengers
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-6
Regression Models
Deterministic Regression Model
Y = 0 + 1X
Y = 0 + 1X +
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-7
Equation of the Simple Regression
Line
Yˆ b0 b1 X
where : b 0
= the sample intercept
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-8
Least Squares Analysis
X Y
X X Y Y XY nXY XY
n
b
X X X n X
2 2 2
1 2
X 2
X
n
Y X
b Y b X n b n
0 1 1
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-9
Least Squares Analysis
X Y
SSXY X X Y Y XY n
X X
2
X
X
2
SSXX
2
n
SSXY
b1 SSXX
Y X
b Y b X n b n
0 1 1
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-10
Solving for b1 and b0 of the Regression
Line: Airline Cost Example (Part 1)
Number of
Passengers Cost ($1,000)
X Y X2 XY
X = 930 Y = 56.69 X 2
= 73,764 XY = 4,462.22
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-11
Solving for b1 and b0 of the Regression
Line: Airline Cost Example (Part 2)
SS XY XY X Y 4,462.22
(930)(56.69)
68.745
n 12
( X ) 2 (930) 2
SS XX X 2
n
73,764
12
1689
SS XY 68.745
b1 .0407
SS XX 1689
b0
Y b1
X
56.69
(.0407)
930
1.57
n n 12 12
Yˆ 1.57 .0407 X
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-12
Graph of Regression Line
for the Airline Cost Example
4
Cost ($1000)
0
0 20 40 60 80 100 120
Number of Passengers
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-13
Airline Cost: Excel Summary Output
SUMMARY OUTPUT
Regression Statistics
Multiple R 0.94820033
R Square 0.89908386
Observations 12
ANOVA
df SS MS F Significance F
Total 11 3.11209
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-14
Residual Analysis:
Airline Cost Example
Number of Predicted
Passengers Cost ($1,000) Value Residual
X Y Ŷ Y Yˆ
(Y Yˆ ) .001
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-15
Excel Graph of Residuals
for the Airline Cost Example
0.2
0.1
Residual
0.0
-0.1
-0.2
-0.3
60 70 80 90 100
Number of Passengers
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-16
Nonlinear Residual Plot
0 X
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-17
Nonconstant Error Variance
0 X
0 X
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-18
Graphs of Nonindependent
Error Terms
0 X 0 X
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-19
Healthy Residual Plot
0 X
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-20
Standard Error of the Estimate
Sum of Squares Error
2
SSE Y Y
Y b0 Y b1 XY
2
Standard Error
of the
Estimate SSE
Se n2
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-21
Determining SSE
for the Airline Cost Example
Number of
Passengers Cost ($1,000) Residual
X Y Y Yˆ (Y Yˆ ) 2
(Y Yˆ ) .001 (Y Yˆ ) 2
=.31434
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-22
Standard Error of the Estimate
for the Airline Cost Example
Y Yˆ
Sum of Squares Error
2
SSE
SSYY Y Y Y
2
2
n
SSYY exp lained var iation un exp lained var iation
SSYY SSR SSE
SSR SSE
1
SSYY SSYY
2 SSR
r SSYY
SSE
1
SSYY
SSE
1
0 r 1
2
2
Y
Y n
2
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-24
Coefficient of Determination
for the Airline Cost Example
SSE 0.31434
SSYY Y
Y
270.9251
2
56.69
3.11209
2 2
n 12
SSE
r 1
2
89.9% of the variability
SSYY of the cost of flying a
.31434 Boeing 737 is accounted for
1 by the number of passengers.
3.11209
.899
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-25
Hypothesis Tests for the Slope
of the Regression Model
b 1
t
H 0: 1 0
1
S b
H 1: 1 0 where: S
S e
b
SSXX
H 0: 1 0
SSE
S e
n2
H 1: 1 0
SSXX
2
X
2
X
H 0: 1 0 n
the hypothesized slope
H 1: 1 0
1
df n 2
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-26
Hypothesis Test: Airline Cost
Example (Part 1)
H 0: 1 0 df n 2 10 2 10
.05
H 1: 1 0 2.228
t .025,10
If | t | 2.228, reject H0
If 2.228 t 2.228, do not reject H0
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-27
Hypothesis Test: Airline Cost
Example (Part 2)
.0407 0
t
.1773
2
73,764
(930)
12
9.43
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-28
Testing the Overall Model (Part 1)
H 0: 1 0
dfreg k 1
dferr n k 1 12 1 1 10
H 1: 1 0 .05
F .05,1,10
4.96
IfF 4.96, reject H0
If F 4.96, do not reject H0
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-29
Testing the Overall Model (Part 2)
ANOVA
df SS MS F Significance F
Total 11 3.11209
SSreg 2.7980
2.7980
F 1 89.09
dfreg MSreg 0.3141 0.03141
F 10
SSerr MSerr
dferr F = 89.09 > 4.96, reject H0
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-30
Point Estimation
for the Airline Cost Example
Yˆ 1.57 0.0407 X
For X 73,
Yˆ 1.57 0.040773
4.5411 or $4,541.10
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-31
Confidence Interval to Estimate Y :
Airline Cost Example
1 X X
Yˆ t , n 2 S e
0
2
2 n SSXX
where : X 0 a particular value of X
SSXX = X 2
X
2
n
For X 0 73 and a 95% confidence level ,
73 77.5
2
4.5411 2.2280.1773
1
930
2
12
73,764
12
4.5411 1220
4.4191 E Y 73 4.6631
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-32
Confidence Interval to Estimate the
Average Value of Y for some Values of X:
Airline Cost Example
X Confidence Interval
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-33
Prediction Interval to Estimate Y
for a given value of X
ˆ 1 X 0 X
Y t ,n 2 S e 1
2
2 n SSXX
where : X 0 a particular value of X
SSXX = X
2
X
2
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-34
Confidence Intervals for Estimation
Regression Plot
6
5
Cost
4 Regression
95% CI
95% PI
60 70 80 90 100
Number of Passengers
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-35
MINITAB Regression Analysis of
the Airline Cost Example
The regression equation is
Cost = 1.57 + 0.0407 Number of Passengers
Analysis of Variance
Source DF SS MS F P
Regression 1 2.7980 2.7980 89.09 0.000
Residual Error 10 0.3141 0.0314
Total 11 3.1121
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-36
Pearson Product-Moment
Correlation Coefficient
SSXY
r
SSX SSY
X X Y Y
X X Y Y
2 2
X Y
XY n
X
2
Y 2
Y
2
1 r 1
2
X n n
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-37
Three Degrees of Correlation
r<0 r>0
r=0
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
13-38