252y0641s1 12/6/06

Computer Output for Question 1

Regression A

Data description

C1 Price - Price of property in $thousands

C2 Livsqft – Living area in thousands of square feet

C3 Lotsqft – Lot size in thousands of square feet.

C4 Loc1 – A dummy variable, 1 if property is in Area 1 of 3

C5 Loc2 – A dummy variable, 1 if property is in Area 2 of 3

C6 Baths – Number of baths in house.

C7 Lot 1 – An interaction variable, the product of Lotsqft and Loc1.

C8 Lot 2 - An interaction variable, the product of Lotsqft and Loc2.

C9 Liv 1 – An interaction variable, the product of Livsqft and Loc1.

C10 Liv 2 - An interaction variable, the product of Livsqft and Loc2.

C11 Libsqsq – The living area squared.

This is a regression suggested by Leonard J Kazmier.The dependent variable is the price of the property. The remainder of the variables listed above are candidates for explanatory variables. Since there are only 30 observations the number of independent variables needed to explain the values of the price variable should be relatively small. The data set and descriptive statistics appear at the end.

————— 12/4/2006 8:36:27 PM ————————————————————

Welcome to Minitab, press F1 for help.

MTB > WOpen "C:\Documents and Settings\RBOVE\My Documents\Minitab\252x06041-021.MTW".

Retrieving worksheet from file: 'C:\Documents and Settings\RBOVE\My

Documents\Minitab\252x06041-021.MTW'

Worksheet was saved on Mon Dec 04 2006

Results for: 252x06041-021.MTW

MTB > regress c1 10 c2 c3 c4 c5 c6 c7 c8 c9 c10 c11;

SUBC> vif.

1)Regression Analysis: price versus livsqft, lotsqft, ...

The regression equation is

price = - 783 + 705 livsqft - 2.90 lotsqft + 569 loc1 + 423 loc 2 + 18.1 baths

+ 5.78 lot1 - 1.07 lot2 - 349 liv1 - 197 liv2 - 125 livsqsq

Predictor Coef SE Coef T P VIF

Constant -782.8 265.1 -2.95 0.008

livsqft 704.6 213.8 3.30 0.004 8142.7

lotsqft -2.900 3.283 -0.88 0.388 76.1

loc1 569.4 190.3 2.99 0.007 5725.1

loc 2 423.3 139.0 3.05 0.007 3054.2

baths 18.121 4.392 4.13 0.001 2.3

lot1 5.775 4.709 1.23 0.235 520.6

lot2 -1.071 5.196 -0.21 0.839 997.7

liv1 -349.3 117.8 -2.96 0.008 4382.0

liv2 -196.54 79.91 -2.46 0.024 3414.8

livsqsq -125.48 39.56 -3.17 0.005 4606.9

S = 6.49288 R-Sq = 97.5% R-Sq(adj) = 96.2%

Analysis of Variance

Source DF SS MS F P

Regression 10 31197.6 3119.8 74.00 0.000

Residual Error 19 801.0 42.2

Total 29 31998.6

Source DF Seq SS

livsqft 1 29642.7

lotsqft 1 126.4

loc1 1 2.9

loc 2 1 492.5

baths 1 472.4

lot1 1 4.2

lot2 1 27.5

liv1 1 0.0

liv2 1 4.7

livsqsq 1 424.2

Unusual Observations

Obs livsqft price Fit SE Fit Residual St Resid

29 2.50 199.40 190.70 5.36 8.70 2.37R

R denotes an observation with a large standardized residual.

MTB > regress c1 9 c3 c4 c5 c6 c7 c8 c9 c10 c11;

SUBC> vif.

2)Regression Analysis: price versus lotsqft, loc1, ...

The regression equation is

price = 85.2 + 2.12 lotsqft - 48.5 loc1 - 20.4 loc 2 + 11.0 baths - 1.73 lot1

- 4.13 lot2 + 23.3 liv1 + 29.2 liv2 + 4.16 livsqsq

Predictor Coef SE Coef T P VIF

Constant 85.16 36.25 2.35 0.029

lotsqft 2.121 3.552 0.60 0.557 59.7

loc1 -48.47 39.41 -1.23 0.233 164.5

loc 2 -20.39 41.96 -0.49 0.632 186.5

baths 11.012 4.675 2.36 0.029 1.7

lot1 -1.728 5.036 -0.34 0.735 398.9

lot2 -4.127 6.247 -0.66 0.516 965.9

liv1 23.32 40.44 0.58 0.571 345.9

liv2 29.22 50.24 0.58 0.567 904.3

livsqsq 4.156 5.025 0.83 0.418 49.8

S = 7.93322 R-Sq = 96.1% R-Sq(adj) = 94.3%

Analysis of Variance

Source DF SS MS F P

Regression 9 30739.9 3415.5 54.27 0.000

Residual Error 20 1258.7 62.9

Total 29 31998.6

Source DF Seq SS

lotsqft 1 26347.5

loc1 1 61.3

loc 2 1 3609.1

baths 1 509.1

lot1 1 8.0

lot2 1 47.0

liv1 1 59.8

liv2 1 55.1

livsqsq 1 43.0

Unusual Observations

Obs lotsqft price Fit SE Fit Residual St Resid

29 20.0 199.40 186.60 6.37 12.80 2.71R

R denotes an observation with a large standardized residual.

MTB > regress c1 7 c3 c4 c5 c6 c9 c10 c11;

SUBC> vif.

3)Regression Analysis: price versus lotsqft, loc1, ...

The regression equation is

price = 99.0 + 0.67 lotsqft - 58.7 loc1 - 28.3 loc 2 + 11.4 baths + 15.1 liv1

- 0.2 liv2 + 6.04 livsqsq

Predictor Coef SE Coef T P VIF

Constant 99.01 24.22 4.09 0.000

lotsqft 0.671 2.072 0.32 0.749 21.9

loc1 -58.68 33.91 -1.73 0.098 131.1

loc 2 -28.32 37.49 -0.76 0.458 160.2

baths 11.441 4.105 2.79 0.011 1.4

liv1 15.12 21.04 0.72 0.480 100.7

liv2 -0.22 19.15 -0.01 0.991 141.4

livsqsq 6.044 3.435 1.76 0.092 25.0

S = 7.64800 R-Sq = 96.0% R-Sq(adj) = 94.7%

Analysis of Variance

Source DF SS MS F P

Regression 7 30711.8 4387.4 75.01 0.000

Residual Error 22 1286.8 58.5

Total 29 31998.6

Source DF Seq SS

lotsqft 1 26347.5

loc1 1 61.3

loc 2 1 3609.1

baths 1 509.1

liv1 1 2.4

liv2 1 1.3

livsqsq 1 181.1

Unusual Observations

Obs lotsqft price Fit SE Fit Residual St Resid

29 20.0 199.40 184.53 5.16 14.87 2.63R

R denotes an observation with a large standardized residual.

MTB > regress c1 5 c3 c6 c9 c10 c11;

SUBC> vif.

4)Regression Analysis: price versus lotsqft, baths, liv1, liv2, livsqsq

The regression equation is

price = 68.4 + 2.73 lotsqft + 10.6 baths - 19.9 liv1 - 13.3 liv2 + 5.10 livsqsq

Predictor Coef SE Coef T P VIF

Constant 68.38 15.84 4.32 0.000

lotsqft 2.731 1.726 1.58 0.127 14.6

baths 10.568 4.157 2.54 0.018 1.4

liv1 -19.906 5.390 -3.69 0.001 6.3

liv2 -13.334 3.662 -3.64 0.001 5.0

livsqsq 5.105 3.425 1.49 0.149 23.9

S = 7.80489 R-Sq = 95.4% R-Sq(adj) = 94.5%

Analysis of Variance

Source DF SS MS F P

Regression 5 30536.6 6107.3 100.26 0.000

Residual Error 24 1462.0 60.9

Total 29 31998.6

Source DF Seq SS

lotsqft 1 26347.5

baths 1 168.4

liv1 1 123.9

liv2 1 3761.5

livsqsq 1 135.3

Unusual Observations

Obs lotsqft price Fit SE Fit Residual St Resid

29 20.0 199.40 186.61 5.12 12.79 2.17R

R denotes an observation with a large standardized residual.

MTB > regress c1 4 c6 c9 c10 c11;

SUBC> vif.

5)Regression Analysis: price versus baths, liv1, liv2, livsqsq

The regression equation is

price = 86.8 + 11.1 baths - 17.0 liv1 - 10.1 liv2 + 9.92 livsqsq

Predictor Coef SE Coef T P VIF

Constant 86.77 11.08 7.83 0.000

baths 11.090 4.267 2.60 0.015 1.4

liv1 -16.988 5.214 -3.26 0.003 5.6

liv2 -10.148 3.149 -3.22 0.004 3.5

livsqsq 9.915 1.622 6.11 0.000 5.1

S = 8.03608 R-Sq = 95.0% R-Sq(adj) = 94.1%

Analysis of Variance

Source DF SS MS F P

Regression 4 30384.2 7596.0 117.62 0.000

Residual Error 25 1614.5 64.6

Total 29 31998.6

Source DF Seq SS

baths 1 8914.5

liv1 1 8231.0

liv2 1 10825.9

livsqsq 1 2412.9

Unusual Observations

Obs baths price Fit SE Fit Residual St Resid

3 2.00 87.90 102.84 3.19 -14.94 -2.03R

27 3.00 195.85 209.28 5.08 -13.43 -2.16R

29 3.00 199.40 182.01 4.34 17.39 2.57R

R denotes an observation with a large standardized residual.

MTB > BReg c1 c6 c9 c10 c11 ;

SUBC> NVars 1 4;

SUBC> Best 2;

SUBC> Constant.

6)Best Subsets Regression: price versus baths, liv1, liv2, livsqsq

Response is price

l

i

b v

a l l s

t i i q

Mallows h v v s

Vars R-Sq R-Sq(adj) C-p S s 1 2 q

1 91.9 91.6 14.3 9.6448 X

1 45.3 43.3 245.3 25.013 X

2 92.6 92.1 12.5 9.3441 X X

2 92.2 91.6 14.7 9.6171 X X

3 93.6 92.9 9.8 8.8812 X X X

3 92.9 92.0 13.4 9.3746 X X X

4 95.0 94.1 5.0 8.0361 X X X X

MTB > regress c1 10 c2 c3 c4 c5 c6 c7 c8 c9 c10 c11

7)Regression Analysis: price versus livsqft, lotsqft, ...

The regression equation is

price = - 783 + 705 livsqft - 2.90 lotsqft + 569 loc1 + 423 loc 2 + 18.1 baths

+ 5.78 lot1 - 1.07 lot2 - 349 liv1 - 197 liv2 - 125 livsqsq

Predictor Coef SE Coef T P

Constant -782.8 265.1 -2.95 0.008

livsqft 704.6 213.8 3.30 0.004

lotsqft -2.900 3.283 -0.88 0.388

loc1 569.4 190.3 2.99 0.007

loc 2 423.3 139.0 3.05 0.007

baths 18.121 4.392 4.13 0.001

lot1 5.775 4.709 1.23 0.235

lot2 -1.071 5.196 -0.21 0.839

liv1 -349.3 117.8 -2.96 0.008

liv2 -196.54 79.91 -2.46 0.024

livsqsq -125.48 39.56 -3.17 0.005

S = 6.49288 R-Sq = 97.5% R-Sq(adj) = 96.2%

Analysis of Variance

Source DF SS MS F P

Regression 10 31197.6 3119.8 74.00 0.000

Residual Error 19 801.0 42.2

Total 29 31998.6

Source DF Seq SS

livsqft 1 29642.7

lotsqft 1 126.4

loc1 1 2.9

loc 2 1 492.5

baths 1 472.4

lot1 1 4.2

lot2 1 27.5

liv1 1 0.0

liv2 1 4.7

livsqsq 1 424.2

Unusual Observations

Obs livsqft price Fit SE Fit Residual St Resid

29 2.50 199.40 190.70 5.36 8.70 2.37R

R denotes an observation with a large standardized residual.

MTB > regress c1 8 c2 c3 c4 c5 c6 c9 c10 c11

8)Regression Analysis: price versus livsqft, lotsqft, ...

The regression equation is

price = - 637 + 574 livsqft - 0.24 lotsqft + 463 loc1 + 351 loc 2 + 14.9 baths

- 247 liv1 - 174 liv2 - 103 livsqsq

Predictor Coef SE Coef T P

Constant -636.8 241.4 -2.64 0.015

livsqft 573.8 187.6 3.06 0.006

lotsqft -0.241 1.789 -0.13 0.894

loc1 462.9 173.0 2.68 0.014

loc 2 350.9 128.0 2.74 0.012

baths 14.910 3.674 4.06 0.001

liv1 -247.23 87.63 -2.82 0.010

liv2 -173.97 59.10 -2.94 0.008

livsqsq -103.43 35.91 -2.88 0.009

S = 6.51098 R-Sq = 97.2% R-Sq(adj) = 96.2%

Analysis of Variance

Source DF SS MS F P

Regression 8 31108.4 3888.5 91.73 0.000

Residual Error 21 890.3 42.4

Total 29 31998.6

Source DF Seq SS

livsqft 1 29642.7

lotsqft 1 126.4

loc1 1 2.9

loc 2 1 492.5

baths 1 472.4

liv1 1 2.5

liv2 1 17.3

livsqsq 1 351.6

MTB > regress c1 7 c2 c4 c5 c6 c9 c10 c11

9)Regression Analysis: price versus livsqft, loc1, ...

The regression equation is

price = - 634 + 570 livsqft + 461 loc1 + 349 loc 2 + 14.8 baths - 247 liv1

- 173 liv2 - 103 livsqsq

Predictor Coef SE Coef T P

Constant -633.6 234.9 -2.70 0.013

livsqft 569.6 180.8 3.15 0.005

loc1 461.3 168.7 2.74 0.012

loc 2 349.5 124.7 2.80 0.010

baths 14.822 3.534 4.19 0.000

liv1 -246.77 85.58 -2.88 0.009

liv2 -173.49 57.66 -3.01 0.006

livsqsq -102.93 34.92 -2.95 0.007

S = 6.36403 R-Sq = 97.2% R-Sq(adj) = 96.3%

Analysis of Variance

Source DF SS MS F P

Regression 7 31107.6 4443.9 109.72 0.000

Residual Error 22 891.0 40.5

Total 29 31998.6

Source DF Seq SS

livsqft 1 29642.7

loc1 1 10.8

loc 2 1 597.7

baths 1 484.7

liv1 1 3.3

liv2 1 16.4

livsqsq 1 352.0

MTB > regress c1 7 c2 c4 c5 c6 c9 c10 c11;

SUBC> vif.

10)Regression Analysis: price versus livsqft, loc1, ...

The regression equation is

price = - 634 + 570 livsqft + 461 loc1 + 349 loc 2 + 14.8 baths - 247 liv1

- 173 liv2 - 103 livsqsq

Predictor Coef SE Coef T P VIF

Constant -633.6 234.9 -2.70 0.013

livsqft 569.6 180.8 3.15 0.005 6060.8

loc1 461.3 168.7 2.74 0.012 4682.2

loc 2 349.5 124.7 2.80 0.010 2559.1

baths 14.822 3.534 4.19 0.000 1.5

liv1 -246.77 85.58 -2.88 0.009 2406.6

liv2 -173.49 57.66 -3.01 0.006 1851.0

livsqsq -102.93 34.92 -2.95 0.007 3736.4

S = 6.36403 R-Sq = 97.2% R-Sq(adj) = 96.3%

Analysis of Variance

Source DF SS MS F P

Regression 7 31107.6 4443.9 109.72 0.000

Residual Error 22 891.0 40.5

Total 29 31998.6

Source DF Seq SS

livsqft 1 29642.7

loc1 1 10.8

loc 2 1 597.7

baths 1 484.7

liv1 1 3.3

liv2 1 16.4

livsqsq 1 352.0

MTB > Stepwise c1 c2 c3 c4 c5 c6 c7 c8 c9 c10 c11;

SUBC> AEnter 0.15;

SUBC> ARemove 0.15;

SUBC> Best 0;

SUBC> Constant.

11)Stepwise Regression: price versus livsqft, lotsqft, ...

Alpha-to-Enter: 0.15 Alpha-to-Remove: 0.15

Response is price on 10 predictors, with N = 30

Step 1 2 3 4

Constant 13.59 16.80 59.44 53.49

livsqft 62.8 62.2 45.9 38.0

T-Value 18.77 19.15 6.17 5.53

P-Value 0.000 0.000 0.000 0.000

lot2 -0.40 -1.22 -1.51

T-Value -1.76 -3.03 -4.21

P-Value 0.090 0.005 0.000

loc1 -21.6 -25.8

T-Value -2.39 -3.27

P-Value 0.024 0.003

baths 11.8

T-Value 3.18

P-Value 0.004

S 9.17 8.85 8.17 7.03

R-Sq 92.64 93.39 94.58 96.14

R-Sq(adj) 92.37 92.90 93.96 95.53

Mallows C-p 29.9 26.1 19.1 9.3

More? (Yes, No, Subcommand, or Help)

SUBC> y

No variables entered or removed

More? (Yes, No, Subcommand, or Help)

SUBC> n

Correlations: livsqft, lot2, loc1, baths

livsqft lot2 loc1

lot2 -0.109

0.565

loc1 -0.735 -0.497

0.000 0.005

baths 0.472 0.136 -0.405

0.009 0.475 0.026

Cell Contents: Pearson correlation

P-Value

MTB > Save "C:\Documents and Settings\RBOVE\My Documents\Minitab\252x06041-021.MTW";

SUBC> Replace.

Saving file as: 'C:\Documents and Settings\RBOVE\My

Documents\Minitab\252x06041-021.MTW'

Existing file replaced.

MTB> describe c1-c11

Descriptive Statistics: price, livsqft, lotsqft, loc1, loc 2, baths, lot1, ...

Variable N N* Mean SE Mean StDev Minimum Q1 Median Q3

price 30 0 134.23 6.06 33.22 87.90 109.45 124.20 164.25

livsqft 30 0 1.9200 0.0929 0.5088 1.2000 1.5000 1.8500 2.4000

lotsqft 30 0 15.267 0.585 3.205 10.000 12.000 15.000 18.000

loc1 30 0 0.3333 0.0875 0.4795 0.0000 0.0000 0.0000 1.0000

loc 2 30 0 0.3333 0.0875 0.4795 0.0000 0.0000 0.0000 1.0000

baths 30 0 2.0333 0.0756 0.4138 1.0000 2.0000 2.0000 2.0000

lot1 30 0 4.00 1.07 5.84 0.00 0.00 0.00 10.50

lot2 30 0 5.07 1.34 7.33 0.00 0.00 0.00 15.00

liv1 30 0 0.467 0.124 0.677 0.000 0.000 0.000 1.225

liv2 30 0 0.610 0.161 0.882 0.000 0.000 0.000 1.725

livsqsq 30 0 3.937 0.378 2.069 1.440 2.250 3.425 5.760

Variable Maximum

price 199.40

livsqft 3.0000

lotsqft 22.000

loc1 1.0000

loc 2 1.0000

baths 3.0000

lot1 15.00

lot2 17.00

liv1 1.600

liv2 2.000

livsqsq 9.000

MTB > print c1 - c11

Data Display

Row price livsqft lotsqft loc1 loc 2 baths lot1 lot2 liv1 liv2

1 102.20 1.5 12 1 0 2 12 0 1.5 0.0

2 103.95 1.2 10 1 0 2 10 0 1.2 0.0

3 87.90 1.2 10 1 0 2 10 0 1.2 0.0

4 110.00 1.6 15 1 0 2 15 0 1.6 0.0

5 97.00 1.4 12 1 0 1 12 0 1.4 0.0

6 95.70 1.2 10 1 0 2 10 0 1.2 0.0

7 113.60 1.6 15 1 0 2 15 0 1.6 0.0

8 109.60 1.5 12 1 0 2 12 0 1.5 0.0

9 110.80 1.5 12 1 0 2 12 0 1.5 0.0

10 90.60 1.3 12 1 0 1 12 0 1.3 0.0

11 109.00 1.6 13 0 1 2 0 13 0.0 1.6

12 133.00 1.9 15 0 1 2 0 15 0.0 1.9

13 134.00 1.8 15 0 1 2 0 15 0.0 1.8

14 120.30 2.0 17 0 1 2 0 17 0.0 2.0

15 137.00 2.0 17 0 1 3 0 17 0.0 2.0

16 122.40 1.7 15 0 1 2 0 15 0.0 1.7

17 121.70 1.8 15 0 1 2 0 15 0.0 1.8

18 126.00 1.9 16 0 1 2 0 16 0.0 1.9

19 128.00 2.0 16 0 1 2 0 16 0.0 2.0

20 117.50 1.6 13 0 1 2 0 13 0.0 1.6

21 158.70 2.4 18 0 0 2 0 0 0.0 0.0

22 186.80 2.6 18 0 0 2 0 0 0.0 0.0

23 172.40 2.3 16 0 0 2 0 0 0.0 0.0

24 151.20 2.2 16 0 0 2 0 0 0.0 0.0

25 179.10 2.8 20 0 0 2 0 0 0.0 0.0

26 182.30 2.7 20 0 0 2 0 0 0.0 0.0

27 195.85 3.0 22 0 0 3 0 0 0.0 0.0

28 168.00 2.4 18 0 0 2 0 0 0.0 0.0

29 199.40 2.5 20 0 0 3 0 0 0.0 0.0

30 163.00 2.4 18 0 0 2 0 0 0.0 0.0

Row livsqsq

1 2.25

2 1.44

3 1.44

4 2.56

5 1.96

6 1.44

7 2.56

8 2.25

9 2.25

10 1.69

11 2.56

12 3.61

13 3.24

14 4.00

15 4.00

16 2.89

17 3.24

18 3.61

19 4.00

20 2.56

21 5.76

22 6.76

23 5.29

24 4.84

25 7.84

26 7.29

27 9.00

28 5.76

29 6.25

30 5.76

Regression B

Data description

C1 Sq.ft – Number of square feet

C2 Sqftsq – The square of the previous variable.

C3 Assessed – Assessed value in $1000s

C4 Market – Market value in $1000s – The dependent variable.

C5 Low – A dummy variable; indicates an inferior property.

C6 Med - A dummy variable; indicates a normal property.

C7 High - A dummy variable; indicates a superior property.

C9 AL – An interaction variable; the product of Assessed and Low.

C10 AM – An interaction variable; the product of Assessed and Med.

C11 AH – An interaction variable; the product of Assessed and High.

This is a regression mentioned in the Minitab handbook and the data comes from the Minitab website maintained by the publisher. The dependent variable is the market price of the property. The remainder of the variables listed above are candidates for explanatory variables. Since there are only 60 observations the number of independent variables needed to explain the values of the price variable should be relatively small. The data and some descriptive statistics appear at the end.

————— 12/4/2006 10:28:02 PM ————————————————————

Welcome to Minitab, press F1 for help.

MTB > WOpen "C:\Documents and Settings\RBOVE\My Documents\Minitab\252x06041-022.MTW".

Retrieving worksheet from file: 'C:\Documents and Settings\RBOVE\My

Documents\Minitab\252x06041-022.MTW'

Worksheet was saved on Mon Dec 04 2006

Results for: 252x06041-022.MTW

MTB > regress c4 7 c1 c2 c3 c5 c6 c9 c10;

SUBC> vif.

12)Regression Analysis: Market versus Sq.ft, Sqftsq, ...

The regression equation is

Market = 9.9 + 0.0438 Sq.ft - 0.000015 Sqftsq + 0.129 Assessed - 6.2 Low

- 5.9 Med - 0.012 AL + 0.176 AM

Predictor Coef SE Coef T P VIF

Constant 9.87 15.05 0.66 0.515

Sq.ft 0.043807 0.008169 5.36 0.000 31.3

Sqftsq -0.00001476 0.00000370 -3.99 0.000 29.6

Assessed 0.1289 0.4909 0.26 0.794 64.9

Low -6.16 14.12 -0.44 0.664 257.6

Med -5.87 14.11 -0.42 0.679 314.7

AL -0.0122 0.5023 -0.02 0.981 133.8

AM 0.1762 0.4985 0.35 0.725 265.9

S = 2.72518 R-Sq = 81.5% R-Sq(adj) = 79.1%

Analysis of Variance

Source DF SS MS F P

Regression 7 1706.22 243.75 32.82 0.000

Residual Error 52 386.18 7.43

Total 59 2092.40

Source DF Seq SS

Sq.ft 1 1173.10

Sqftsq 1 231.97

Assessed 1 177.38

Low 1 107.14

Med 1 3.57

AL 1 12.13

AM 1 0.93

Unusual Observations

Obs Sq.ft Market Fit SE Fit Residual St Resid

2 538 19.400 26.297 1.433 -6.897 -2.98R

3 544 25.200 30.544 1.188 -5.344 -2.18R

10 712 42.400 34.179 0.696 8.221 3.12R

30 923 30.000 32.106 1.752 -2.106 -1.01 X

57 1298 45.200 44.904 2.670 0.296 0.54 X

59 1602 47.400 46.162 2.032 1.238 0.68 X

60 1804 45.400 44.330 2.309 1.070 0.74 X

R denotes an observation with a large standardized residual.

X denotes an observation whose X value gives it large influence.

MTB > regress c4 5 c1 c2 c3 c9 c10;

SUBC> vif.

13)Regression Analysis: Market versus Sq.ft, Sqftsq, Assessed, AL, AM

The regression equation is

Market = 3.69 + 0.0443 Sq.ft - 0.000015 Sqftsq + 0.337 Assessed - 0.230 AL

- 0.0289 AM

Predictor Coef SE Coef T P VIF

Constant 3.691 4.390 0.84 0.404

Sq.ft 0.044273 0.007962 5.56 0.000 30.7

Sqftsq -0.00001498 0.00000360 -4.16 0.000 29.1

Assessed 0.33686 0.07850 4.29 0.000 1.7

AL -0.22961 0.07316 -3.14 0.003 2.9

AM -0.02893 0.05321 -0.54 0.589 3.1

S = 2.67918 R-Sq = 81.5% R-Sq(adj) = 79.8%

Analysis of Variance

Source DF SS MS F P

Regression 5 1704.79 340.96 47.50 0.000

Residual Error 54 387.61 7.18

Total 59 2092.40

Source DF Seq SS

Sq.ft 1 1173.10

Sqftsq 1 231.97

Assessed 1 177.38

AL 1 120.21

AM 1 2.12

Unusual Observations

Obs Sq.ft Market Fit SE Fit Residual St Resid

2 538 19.400 26.200 1.322 -6.800 -2.92R

3 544 25.200 30.488 1.156 -5.288 -2.19R

10 712 42.400 34.150 0.636 8.250 3.17R

45 1060 44.800 43.631 1.471 1.169 0.52 X

59 1602 47.400 46.627 1.681 0.773 0.37 X

60 1804 45.400 44.247 2.253 1.153 0.80 X

R denotes an observation with a large standardized residual.

X denotes an observation whose X value gives it large influence.

MTB > BReg c4 5 c1 c2 c3 c9 c10;

SUBC> NVars 1 4;

SUBC> Best 2;

SUBC> Constant.

14)Best Subsets Regression: Market versus Sq.ft, Sqftsq, Assessed, AL, AM

Response is Market

A

s

S s

S q e

q f s

. t s

Mallows f s e A A

Vars R-Sq R-Sq(adj) C-p S t q d L M

1 56.1 55.3 72.1 3.9812 X

1 44.9 44.0 104.6 4.4582 X

2 67.9 66.7 39.7 3.4347 X X

2 67.2 66.0 41.8 3.4725 X X

3 75.6 74.3 19.0 3.0176 X X X

3 75.5 74.2 19.4 3.0242 X X X

4 81.4 80.0 4.3 2.6620 X X X X

4 78.1 76.5 13.9 2.8867 X X X X

5 81.5 79.8 6.0 2.6792 X X X X X

MTB > regress c4 7 c1 c2 c3 c5 c6 c9 c10

15)Regression Analysis: Market versus Sq.ft, Sqftsq, ...

The regression equation is

Market = 9.9 + 0.0438 Sq.ft - 0.000015 Sqftsq + 0.129 Assessed - 6.2 Low

- 5.9 Med - 0.012 AL + 0.176 AM

Predictor Coef SE Coef T P

Constant 9.87 15.05 0.66 0.515

Sq.ft 0.043807 0.008169 5.36 0.000

Sqftsq -0.00001476 0.00000370 -3.99 0.000

Assessed 0.1289 0.4909 0.26 0.794

Low -6.16 14.12 -0.44 0.664

Med -5.87 14.11 -0.42 0.679

AL -0.0122 0.5023 -0.02 0.981

AM 0.1762 0.4985 0.35 0.725

S = 2.72518 R-Sq = 81.5% R-Sq(adj) = 79.1%

Analysis of Variance

Source DF SS MS F P

Regression 7 1706.22 243.75 32.82 0.000

Residual Error 52 386.18 7.43

Total 59 2092.40

Source DF Seq SS

Sq.ft 1 1173.10

Sqftsq 1 231.97

Assessed 1 177.38

Low 1 107.14

Med 1 3.57

AL 1 12.13

AM 1 0.93

Unusual Observations

Obs Sq.ft Market Fit SE Fit Residual St Resid

2 538 19.400 26.297 1.433 -6.897 -2.98R

3 544 25.200 30.544 1.188 -5.344 -2.18R

10 712 42.400 34.179 0.696 8.221 3.12R

30 923 30.000 32.106 1.752 -2.106 -1.01 X

57 1298 45.200 44.904 2.670 0.296 0.54 X

59 1602 47.400 46.162 2.032 1.238 0.68 X

60 1804 45.400 44.330 2.309 1.070 0.74 X

R denotes an observation with a large standardized residual.

X denotes an observation whose X value gives it large influence.

MTB > let c11 = c3 - c9 -c10

MTB > regress c4 7 c1 c2 c5 c6 c9 c10 c11

16)Regression Analysis: Market versus Sq.ft, Sqftsq, Low, Med, AL, AM, AH

The regression equation is

Market = 9.9 + 0.0438 Sq.ft - 0.000015 Sqftsq - 6.2 Low - 5.9 Med + 0.117 AL

+ 0.305 AM + 0.129 AH

Predictor Coef SE Coef T P

Constant 9.87 15.05 0.66 0.515

Sq.ft 0.043807 0.008169 5.36 0.000

Sqftsq -0.00001476 0.00000370 -3.99 0.000

Low -6.16 14.12 -0.44 0.664

Med -5.87 14.11 -0.42 0.679

AL 0.1167 0.1085 1.08 0.287

AM 0.30502 0.09290 3.28 0.002

AH 0.1289 0.4909 0.26 0.794

S = 2.72518 R-Sq = 81.5% R-Sq(adj) = 79.1%

Analysis of Variance

Source DF SS MS F P

Regression 7 1706.22 243.75 32.82 0.000

Residual Error 52 386.18 7.43

Total 59 2092.40

Source DF Seq SS

Sq.ft 1 1173.10

Sqftsq 1 231.97

Low 1 202.81

Med 1 8.68

AL 1 9.22

AM 1 79.92

AH 1 0.51

Unusual Observations

Obs Sq.ft Market Fit SE Fit Residual St Resid

2 538 19.400 26.297 1.433 -6.897 -2.98R

3 544 25.200 30.544 1.188 -5.344 -2.18R

10 712 42.400 34.179 0.696 8.221 3.12R

30 923 30.000 32.106 1.752 -2.106 -1.01 X

57 1298 45.200 44.904 2.670 0.296 0.54 X

59 1602 47.400 46.162 2.032 1.238 0.68 X

60 1804 45.400 44.330 2.309 1.070 0.74 X

R denotes an observation with a large standardized residual.

X denotes an observation whose X value gives it large influence.

MTB > regress c4 6 c1 c2 c5 c6 c9 c10

17)Regression Analysis: Market versus Sq.ft, Sqftsq, Low, Med, AL, AM

The regression equation is

Market = 13.6 + 0.0436 Sq.ft - 0.000015 Sqftsq - 9.80 Low - 9.49 Med + 0.117 AL

+ 0.305 AM

Predictor Coef SE Coef T P

Constant 13.615 4.740 2.87 0.006

Sq.ft 0.043570 0.008047 5.41 0.000

Sqftsq -0.00001464 0.00000364 -4.03 0.000

Low -9.796 2.671 -3.67 0.001

Med -9.494 2.818 -3.37 0.001

AL 0.1166 0.1075 1.08 0.283

AM 0.30473 0.09207 3.31 0.002

S = 2.70113 R-Sq = 81.5% R-Sq(adj) = 79.4%

Analysis of Variance

Source DF SS MS F P

Regression 6 1705.71 284.28 38.96 0.000

Residual Error 53 386.69 7.30

Total 59 2092.40

Source DF Seq SS

Sq.ft 1 1173.10

Sqftsq 1 231.97

Low 1 202.81

Med 1 8.68

AL 1 9.22

AM 1 79.92

Unusual Observations

Obs Sq.ft Market Fit SE Fit Residual St Resid

1 521 26.000 23.454 1.617 2.546 1.18 X

2 538 19.400 26.309 1.419 -6.909 -3.01R

3 544 25.200 30.561 1.176 -5.361 -2.20R

10 712 42.400 34.182 0.690 8.218 3.15R

30 923 30.000 32.099 1.737 -2.099 -1.01 X

59 1602 47.400 45.846 1.621 1.554 0.72 X

60 1804 45.400 44.406 2.271 0.994 0.68 X

R denotes an observation with a large standardized residual.

X denotes an observation whose X value gives it large influence.

MTB > regress c4 5 c1 c2 c5 c6 c10

18)Regression Analysis: Market versus Sq.ft, Sqftsq, Low, Med, AM

The regression equation is

Market = 14.0 + 0.0430 Sq.ft - 0.000014 Sqftsq - 7.70 Low - 9.55 Med + 0.306 AM

Predictor Coef SE Coef T P

Constant 13.997 4.735 2.96 0.005

Sq.ft 0.042970 0.008041 5.34 0.000

Sqftsq -0.00001441 0.00000364 -3.96 0.000

Low -7.704 1.849 -4.17 0.000

Med -9.551 2.823 -3.38 0.001

AM 0.30594 0.09221 3.32 0.002

S = 2.70550 R-Sq = 81.1% R-Sq(adj) = 79.4%

Analysis of Variance

Source DF SS MS F P

Regression 5 1697.14 339.43 46.37 0.000

Residual Error 54 395.26 7.32

Total 59 2092.40

Source DF Seq SS

Sq.ft 1 1173.10

Sqftsq 1 231.97

Low 1 202.81

Med 1 8.68

AM 1 80.57

Unusual Observations

Obs Sq.ft Market Fit SE Fit Residual St Resid

2 538 19.400 25.240 1.022 -5.840 -2.33R

3 544 25.200 30.655 1.175 -5.455 -2.24R

10 712 42.400 34.222 0.690 8.178 3.13R

59 1602 47.400 45.856 1.623 1.544 0.71 X

60 1804 45.400 44.434 2.274 0.966 0.66 X

R denotes an observation with a large standardized residual.

X denotes an observation whose X value gives it large influence.

MTB > Stepwise c4 c1 c2 c3 c5 c6 c9 c10;

SUBC> AEnter 0.15;

SUBC> ARemove 0.15;

SUBC> Best 0;

SUBC> Constant.

17)Stepwise Regression: Market versus Sq.ft, Sqftsq, ...

Alpha-to-Enter: 0.15 Alpha-to-Remove: 0.15

Response is Market on 7 predictors, with N = 60

Step 1 2 3 4

Constant 20.508 26.164 10.370 4.939

Sq.ft 0.0184 0.0137 0.0445 0.0450

T-Value 8.60 7.13 5.10 5.61

P-Value 0.000 0.000 0.000 0.000

Low -6.4 -5.3 -4.1

T-Value -5.55 -4.84 -3.82

P-Value 0.000 0.000 0.000

Sqftsq -0.00001 -0.00001

T-Value -3.60 -4.11

P-Value 0.001 0.000

Assessed 0.229

T-Value 3.34

P-Value 0.002

S 3.98 3.24 2.94 2.71

R-Sq 56.06 71.48 76.84 80.75

R-Sq(adj) 55.31 70.48 75.60 79.35

Mallows C-p 67.8 26.3 13.2 4.2

More? (Yes, No, Subcommand, or Help)

SUBC> y

No variables entered or removed

More? (Yes, No, Subcommand, or Help)

SUBC> n

MTB > corr c1 c2 c3

Correlations: Sq.ft, Sqftsq, Assessed

Sq.ft Sqftsq

Sqftsq 0.981

0.000

Assessed 0.347 0.333

0.007 0.009

Cell Contents: Pearson correlation

P-Value

MTB > print c1 c2 c3 c4 c5 c6 c7 c9 c10

Data Display

Row Sq.ft Sqftsq Assessed Market Low Med High AL AM

1 521 271441 7.8 26.0 1 0 0 7.8 0.0

2 538 289444 28.2 19.4 1 0 0 28.2 0.0

3 544 295936 23.2 25.2 0 1 0 0.0 23.2

4 577 332929 22.2 26.2 1 0 0 22.2 0.0

5 661 436921 23.8 31.0 1 0 0 23.8 0.0

6 662 438244 19.6 34.6 0 1 0 0.0 19.6

7 677 458329 22.8 36.4 0 1 0 0.0 22.8

8 691 477481 22.6 33.0 1 0 0 22.6 0.0

9 694 481636 28.0 37.4 0 1 0 0.0 28.0

10 712 506944 21.2 42.4 0 1 0 0.0 21.2

11 721 519841 21.6 32.8 0 1 0 0.0 21.6

12 722 521284 7.4 25.6 1 0 0 7.4 0.0

13 743 552049 26.2 34.8 0 1 0 0.0 26.2

14 760 577600 26.6 35.8 0 1 0 0.0 26.6

15 767 588289 22.2 33.6 1 0 0 22.2 0.0

16 780 608400 22.6 31.0 1 0 0 22.6 0.0

17 787 619369 22.4 39.2 0 1 0 0.0 22.4

18 802 643204 25.4 36.0 0 1 0 0.0 25.4

19 814 662596 14.8 34.8 0 1 0 0.0 14.8

20 815 664225 14.4 34.4 0 1 0 0.0 14.4

21 825 680625 28.2 38.0 0 1 0 0.0 28.2

22 834 695556 18.0 34.6 1 0 0 18.0 0.0

23 838 702244 25.6 35.6 0 1 0 0.0 25.6

24 858 736164 22.4 35.8 1 0 0 22.4 0.0

25 883 779689 25.8 39.6 0 1 0 0.0 25.8

26 890 792100 20.2 35.0 0 1 0 0.0 20.2

27 899 808201 23.2 37.6 0 1 0 0.0 23.2

28 918 842724 32.2 41.2 0 1 0 0.0 32.2

29 920 846400 20.8 31.2 1 0 0 20.8 0.0

30 923 851929 4.6 30.0 1 0 0 4.6 0.0

31 926 857476 18.2 37.4 0 1 0 0.0 18.2

32 931 866761 24.6 38.0 0 1 0 0.0 24.6

33 965 931225 14.6 37.2 0 1 0 0.0 14.6

34 966 933156 30.2 44.0 0 1 0 0.0 30.2

35 967 935089 26.0 44.2 0 1 0 0.0 26.0

36 1011 1022121 28.0 43.6 0 1 0 0.0 28.0

37 1011 1022121 26.0 38.4 0 1 0 0.0 26.0

38 1024 1048576 27.0 42.2 0 1 0 0.0 27.0

39 1033 1067089 25.2 40.4 0 1 0 0.0 25.2

40 1040 1081600 22.4 40.4 0 1 0 0.0 22.4

41 1047 1096209 30.0 43.6 0 1 0 0.0 30.0

42 1051 1104601 26.4 41.4 0 1 0 0.0 26.4

43 1052 1106704 20.2 39.6 0 1 0 0.0 20.2

44 1056 1115136 25.8 41.8 0 1 0 0.0 25.8

45 1060 1123600 29.2 44.8 0 0 1 0.0 0.0

46 1060 1123600 24.0 38.4 0 1 0 0.0 24.0

47 1070 1144900 22.8 43.6 0 1 0 0.0 22.8

48 1075 1155625 30.4 42.8 0 1 0 0.0 30.4

49 1079 1164241 24.2 40.6 0 1 0 0.0 24.2

50 1100 1210000 30.0 41.6 0 1 0 0.0 30.0

51 1106 1223236 31.6 42.8 0 1 0 0.0 31.6

52 1138 1295044 25.6 39.0 0 1 0 0.0 25.6

53 1164 1354896 29.4 41.8 0 0 1 0.0 0.0

54 1171 1371241 32.2 48.4 0 1 0 0.0 32.2

55 1237 1530169 17.0 39.8 0 1 0 0.0 17.0

56 1249 1560001 22.0 47.2 0 1 0 0.0 22.0

57 1298 1684804 23.6 45.2 0 0 1 0.0 0.0

58 1435 2059225 21.4 38.8 0 1 0 0.0 21.4

59 1602 2566404 31.0 47.4 0 0 1 0.0 0.0

60 1804 3254416 30.6 45.4 0 1 0 0.0 30.6

MTB > describe c1 c2 c3 c4

Descriptive Statistics: Sq.ft, Sqftsq, Assessed, Market

Variable N N* Mean SE Mean StDev Minimum Q1 Median Q3

Sq.ft 60 0 941.7 31.4 242.8 521.0 770.3 924.5 1060.0

Sqftsq 60 0 944851 67432 522330 271441 593317 854703 1123600

Assessed 60 0 23.560 0.752 5.824 4.600 21.450 23.900 27.750

Market 60 0 37.800 0.769 5.955 19.400 34.650 38.400 42.100

Variable Maximum

Sq.ft 1804.0

Sqftsq 3254416

Assessed 32.200

Market 48.400

1