Вы находитесь на странице: 1из 10

6/30/2015 7:56:39 PM

Welcome to Minitab, press F1 for help.

Regression Analysis: YES versus BIG, PRIN, SIZE, VAL, LIVE, SALE
The regression equation is
YES = 82.2 - 0.012 BIG - 0.191 PRIN - 0.335 SIZE - 0.098 VAL + 0.177 LIVE
+ 0.833 SALE
Predictor
Constant
BIG
PRIN
SIZE
VAL
LIVE
SALE

Coef
82.23
-0.0121
-0.1911
-0.3348
-0.0984
0.17692
0.8330

S = 9.62640

SE Coef
11.47
0.1636
0.2296
0.1177
0.1354
0.07930
0.3952

R-Sq = 40.9%

T
7.17
-0.07
-0.83
-2.85
-0.73
2.23
2.11

P
0.000
0.941
0.409
0.006
0.471
0.030
0.040

R-Sq(adj) = 33.7%

Analysis of Variance
Source
Regression
Residual Error
Total
Source
BIG
PRIN
SIZE
VAL
LIVE
SALE

DF
1
1
1
1
1
1

DF
6
49
55

SS
3148.44
4540.72
7689.16

MS
524.74
92.67

F
5.66

P
0.000

Seq SS
1482.29
5.21
674.30
254.28
320.73
411.63

Unusual Observations
Obs
10
18
30
56

BIG
84.4
70.5
74.8
29.1

YES
87.20
52.00
89.90
63.70

Fit
68.67
73.44
65.80
83.62

SE Fit
3.57
3.54
4.29
3.91

Residual
18.53
-21.44
24.10
-19.92

St Resid
2.07R
-2.39R
2.80R
-2.26R

R denotes an observation with a large standardized residual.

Scatterplot of YES vs BIG


Scatterplot of YES vs PRIN
Scatterplot of YES vs SIZE

Scatterplot of YES vs VAL


Scatterplot of YES vs LIVE
Scatterplot of YES vs SALE
Best Subsets Regression: YES versus BIG, PRIN, SIZE, VAL, LIVE, SALE
Response is YES

Vars
1
1
2
2
3
3
4
4
5
5
6

R-Sq
25.0
19.3
29.6
27.9
37.7
34.2
40.3
38.9
40.9
40.3
40.9

Mallows
Cp
10.2
15.0
8.4
9.8
3.7
6.6
3.6
4.7
5.0
5.5
7.0

R-Sq(adj)
23.7
17.8
26.9
25.2
34.1
30.4
35.6
34.1
35.0
34.3
33.7

S
10.331
10.721
10.108
10.225
9.6005
9.8657
9.4910
9.6003
9.5302
9.5809
9.6264

P S
B R I V
I I Z A
G N E L
X
X
X
X X
X
X X
X X
X
X
X X X
X X X
X X X X

L
I
V
E

S
A
L
E

X
X X
X
X X
X X
X X
X X
X X

6/30/2015 8:22:11 PM
Welcome to Minitab, press F1 for help.
Retrieving project from file: 'C:\USERS\PNUTHAKY\DESKTOP\BEEF.MPJ'

Stepwise Regression: YES versus BIG, PRIN, SIZE, VAL, LIVE, SALE
Alpha-to-Enter: 0.15

Alpha-to-Remove: 0.15

Response is YES on 6 predictors, with N = 56


Step
Constant
SIZE
T-Value
P-Value
LIVE
T-Value
P-Value
SALE

1
85.49

2
79.47

3
68.10

4
81.86

-0.289
-4.25
0.000

-0.299
-4.48
0.000

-0.429
-5.31
0.000

-0.371
-4.17
0.000

0.108
1.85
0.071

0.219
3.13
0.003

0.173
2.28
0.027

0.48

0.58

T-Value
P-Value

2.60
0.012

PRIN
T-Value
P-Value

2.99
0.004

S
R-Sq
R-Sq(adj)
Mallows Cp

-0.20
-1.49
0.144
10.3
25.05
23.66
10.2

10.1
29.57
26.91
8.4

9.60
37.67
34.07
3.7

9.49
40.25
35.57
3.6

Scatterplot of YES vs BIG


Scatterplot of YES vs PRIN
Scatterplot of YES vs SIZE
Scatterplot of YES vs VAL
Scatterplot of YES vs LIVE
Scatterplot of YES vs SALE
Regression Analysis: YES versus BIG, PRIN, SIZE, VAL, LIVE, SALE
The regression equation is
YES = 82.2 - 0.012 BIG - 0.191 PRIN - 0.335 SIZE - 0.098 VAL + 0.177 LIVE
+ 0.833 SALE
Predictor
Constant
BIG
PRIN
SIZE
VAL
LIVE
SALE

Coef
82.23
-0.0121
-0.1911
-0.3348
-0.0984
0.17692
0.8330

S = 9.62640

SE Coef
11.47
0.1636
0.2296
0.1177
0.1354
0.07930
0.3952

R-Sq = 40.9%

T
7.17
-0.07
-0.83
-2.85
-0.73
2.23
2.11

P
0.000
0.941
0.409
0.006
0.471
0.030
0.040

VIF
8.102
7.259
3.436
11.003
2.051
9.881

R-Sq(adj) = 33.7%

Analysis of Variance
Source
Regression
Residual Error
Total

DF
6
49
55

SS
3148.44
4540.72
7689.16

MS
524.74
92.67

F
5.66

P
0.000

Source
BIG
PRIN
SIZE
VAL
LIVE
SALE

DF
1
1
1
1
1
1

Seq SS
1482.29
5.21
674.30
254.28
320.73
411.63

Unusual Observations
Obs
10
18
30
56

BIG
84.4
70.5
74.8
29.1

YES
87.20
52.00
89.90
63.70

Fit
68.67
73.44
65.80
83.62

SE Fit
3.57
3.54
4.29
3.91

Residual
18.53
-21.44
24.10
-19.92

St Resid
2.07R
-2.39R
2.80R
-2.26R

R denotes an observation with a large standardized residual.

Regression Analysis: YES versus BIG, PRIN, SIZE, VAL, LIVE, SALE
The regression equation is
YES = 82.2 - 0.012 BIG - 0.191 PRIN - 0.335 SIZE - 0.098 VAL + 0.177 LIVE
+ 0.833 SALE
Predictor
Constant
BIG
PRIN
SIZE
VAL
LIVE
SALE

Coef
82.23
-0.0121
-0.1911
-0.3348
-0.0984
0.17692
0.8330

S = 9.62640

SE Coef
11.47
0.1636
0.2296
0.1177
0.1354
0.07930
0.3952

R-Sq = 40.9%

T
7.17
-0.07
-0.83
-2.85
-0.73
2.23
2.11

P
0.000
0.941
0.409
0.006
0.471
0.030
0.040

VIF
8.102
7.259
3.436
11.003
2.051
9.881

R-Sq(adj) = 33.7%

Analysis of Variance
Source
Regression
Residual Error
Total
Source
BIG
PRIN
SIZE
VAL
LIVE
SALE

DF
1
1
1
1
1
1

DF
6
49
55

SS
3148.44
4540.72
7689.16

MS
524.74
92.67

F
5.66

P
0.000

Seq SS
1482.29
5.21
674.30
254.28
320.73
411.63

Unusual Observations
Obs

BIG

YES

Fit

SE Fit

Residual

St Resid

10
18
30
56

84.4
70.5
74.8
29.1

87.20
52.00
89.90
63.70

68.67
73.44
65.80
83.62

3.57
3.54
4.29
3.91

18.53
-21.44
24.10
-19.92

2.07R
-2.39R
2.80R
-2.26R

R denotes an observation with a large standardized residual.

Residual Plots for YES

Regression Analysis: YES versus BIG, PRIN, SIZE, LIVE, SALE


The regression equation is
YES = 82.5 + 0.033 BIG - 0.240 PRIN - 0.380 SIZE + 0.177 LIVE + 0.584 SALE
Predictor
Constant
BIG
PRIN
SIZE
LIVE
SALE

Coef
82.51
0.0329
-0.2401
-0.38021
0.17697
0.5843

S = 9.58088

SE Coef
11.41
0.1507
0.2185
0.09923
0.07892
0.1970

R-Sq = 40.3%

T
7.23
0.22
-1.10
-3.83
2.24
2.97

P
0.000
0.828
0.277
0.000
0.029
0.005

VIF
6.943
6.633
2.467
2.051
2.479

R-Sq(adj) = 34.3%

Analysis of Variance
Source
Regression
Residual Error
Total
Source
BIG
PRIN
SIZE
LIVE
SALE

DF
1
1
1
1
1

DF
5
50
55

SS
3099.49
4589.67
7689.16

MS
619.90
91.79

F
6.75

P
0.000

Seq SS
1482.29
5.21
674.30
130.07
807.62

Unusual Observations
Obs
18
30
56

BIG
70.5
74.8
29.1

YES
52.00
89.90
63.70

Fit
74.01
66.79
85.83

SE Fit
3.43
4.05
2.45

Residual
-22.01
23.11
-22.13

St Resid
-2.46R
2.66R
-2.39R

R denotes an observation with a large standardized residual.

Residual Plots for YES

Regression Analysis: YES versus BIG, PRIN, SIZE, LIVE, SALE


The regression equation is
YES = 90.5 + 0.083 BIG - 0.390 PRIN - 0.351 SIZE + 0.147 LIVE + 0.652 SALE
Predictor
Constant
BIG
PRIN
SIZE
LIVE
SALE

Coef
90.47
0.0829
-0.3901
-0.35113
0.14657
0.6525

S = 9.07354

SE Coef
11.24
0.1441
0.2148
0.09464
0.07565
0.1884

R-Sq = 43.0%

T
8.05
0.58
-1.82
-3.71
1.94
3.46

P
0.000
0.568
0.076
0.001
0.058
0.001

VIF
7.044
7.144
2.472
2.073
2.479

R-Sq(adj) = 37.2%

Analysis of Variance
Source
Regression
Residual Error
Total
Source
BIG
PRIN
SIZE
LIVE
SALE

DF
1
1
1
1
1

DF
5
49
54

SS
3043.06
4034.13
7077.19

MS
608.61
82.33

F
7.39

P
0.000

Seq SS
1375.40
47.21
586.18
46.86
987.40

Unusual Observations
Obs
10
29
55

BIG
84.4
74.8
29.1

YES
87.20
89.90
63.70

Fit
69.96
69.02
85.73

SE Fit
3.20
3.93
2.32

Residual
17.24
20.88
-22.03

St Resid
2.03R
2.55R
-2.51R

R denotes an observation with a large standardized residual.

Residual Plots for YES


Regression Analysis: YES versus BIG, PRIN, SIZE, LIVE, SALE
The regression equation is
YES = 88.3 + 0.048 BIG - 0.381 PRIN - 0.345 SIZE + 0.176 LIVE + 0.727 SALE
Predictor
Constant
BIG
PRIN
SIZE
LIVE
SALE

Coef
88.26
0.0477
-0.3807
-0.34499
0.17559
0.7273

SE Coef
10.92
0.1403
0.2078
0.09156
0.07445
0.1856

T
8.09
0.34
-1.83
-3.77
2.36
3.92

P
0.000
0.735
0.073
0.000
0.022
0.000

VIF
6.996
7.057
2.466
2.034
2.571

S = 8.77349

R-Sq = 47.0%

R-Sq(adj) = 41.5%

Analysis of Variance
Source
Regression
Residual Error
Total
Source
BIG
PRIN
SIZE
LIVE
SALE

DF
1
1
1
1
1

DF
5
48
53

SS
3275.67
3694.76
6970.43

MS
655.13
76.97

F
8.51

P
0.000

Seq SS
1520.71
37.15
467.44
68.74
1181.63

Unusual Observations
Obs
28
54

BIG
74.8
29.1

YES
89.90
63.70

Fit
70.04
86.25

SE Fit
3.83
2.26

Residual
19.86
-22.55

St Resid
2.52R
-2.66R

R denotes an observation with a large standardized residual.

Residual Plots for YES


Regression Analysis: YES versus BIG, PRIN, SIZE, LIVE, SALE
The regression equation is
YES = 86.2 + 0.059 BIG - 0.319 PRIN - 0.417 SIZE + 0.175 LIVE + 0.656 SALE
Predictor
Constant
BIG
PRIN
SIZE
LIVE
SALE

Coef
86.25
0.0587
-0.3190
-0.41675
0.17480
0.6561

S = 8.26131

SE Coef
10.31
0.1322
0.1970
0.09030
0.07010
0.1768

R-Sq = 52.8%

T
8.37
0.44
-1.62
-4.62
2.49
3.71

P
0.000
0.659
0.112
0.000
0.016
0.001

VIF
6.945
7.138
2.372
2.013
2.547

R-Sq(adj) = 47.8%

Analysis of Variance
Source
Regression
Residual Error
Total
Source
BIG
PRIN

DF
1
1

DF
5
47
52

Seq SS
1629.27
22.85

SS
3587.12
3207.71
6794.84

MS
717.42
68.25

F
10.51

P
0.000

SIZE
LIVE
SALE

1
1
1

898.66
96.36
939.98

Unusual Observations
Obs
37
51
53

BIG
78.7
80.0
29.1

YES
56.60
90.00
63.70

Fit
73.15
72.10
86.17

SE Fit
2.15
2.49
2.13

Residual
-16.55
17.90
-22.47

St Resid
-2.07R
2.27R
-2.82R

R denotes an observation with a large standardized residual.

Residual Plots for YES


Regression Analysis: YES versus BIG, PRIN, SIZE, LIVE, SALE
The regression equation is
YES = 86.4 + 0.008 BIG - 0.286 PRIN - 0.425 SIZE + 0.184 LIVE + 0.694 SALE
Predictor
Constant
BIG
PRIN
SIZE
LIVE
SALE

Coef
86.358
0.0083
-0.2860
-0.42526
0.18363
0.6939

S = 7.61387

SE Coef
9.498
0.1229
0.1819
0.08327
0.06467
0.1634

R-Sq = 59.8%

T
9.09
0.07
-1.57
-5.11
2.84
4.25

P
0.000
0.947
0.123
0.000
0.007
0.000

VIF
6.824
7.033
2.337
2.006
2.553

R-Sq(adj) = 55.4%

Analysis of Variance
Source
Regression
Residual Error
Total
Source
BIG
PRIN
SIZE
LIVE
SALE

DF
1
1
1
1
1

DF
5
46
51

SS
3960.54
2666.67
6627.21

MS
792.11
57.97

F
13.66

P
0.000

Seq SS
1897.48
8.64
905.58
103.66
1045.18

Unusual Observations
Obs
23
37
43
51

BIG
31.7
78.7
82.6
80.0

YES
65.70
56.60
79.20
90.00

Fit
82.01
73.40
65.66
71.88

SE Fit
2.27
1.98
3.52
2.30

Residual
-16.31
-16.80
13.54
18.12

St Resid
-2.24R
-2.28R
2.01R
2.50R

R denotes an observation with a large standardized residual.

Residual Plots for YES

Regression Analysis: YES versus BIG, PRIN, SIZE, LIVE, SALE, VAL
The regression equation is
YES = 86.0 - 0.015 BIG - 0.257 PRIN - 0.402 SIZE + 0.184 LIVE + 0.827 SALE
- 0.054 VAL
Predictor
Constant
BIG
PRIN
SIZE
LIVE
SALE
VAL

Coef
85.978
-0.0150
-0.2569
-0.40218
0.18429
0.8270
-0.0539

S = 7.68004

SE Coef
9.617
0.1339
0.1941
0.09789
0.06525
0.3335
0.1174

R-Sq = 59.9%

T
8.94
-0.11
-1.32
-4.11
2.82
2.48
-0.46

P
0.000
0.911
0.192
0.000
0.007
0.017
0.648

VIF
7.963
7.876
3.174
2.007
10.451
11.690

R-Sq(adj) = 54.6%

Analysis of Variance
Source
Regression
Residual Error
Total

DF
6
45
51

SS
3972.97
2654.23
6627.21

MS
662.16
58.98

F
11.23

P
0.000

Source
BIG
PRIN
SIZE
LIVE
SALE
VAL

DF
1
1
1
1
1
1

Seq SS
1897.48
8.64
905.58
103.66
1045.18
12.43

Unusual Observations
Obs
23
37
43
51

BIG
31.7
78.7
82.6
80.0

YES
65.70
56.60
79.20
90.00

Fit
81.99
73.47
65.20
71.35

SE Fit
2.29
2.00
3.69
2.59

Residual
-16.29
-16.87
14.00
18.65

St Resid
-2.22R
-2.27R
2.08R
2.58R

R denotes an observation with a large standardized residual.

Residual Plots for YES

Вам также может понравиться