stepwiseregression.dat

这些程序是vc++编程时会用到的基本算法的程序

f1=1.460000e+000  f2=1.450000e+000

original x(i) and y values:
x(0)=  7.00 x(1)= 26.00 x(2)=  6.00 x(3)= 60.00 y= 78.50
x(0)=  1.00 x(1)= 29.00 x(2)= 15.00 x(3)= 52.00 y= 74.30
x(0)= 11.00 x(1)= 56.00 x(2)=  8.00 x(3)= 20.00 y=104.30
x(0)= 11.00 x(1)= 31.00 x(2)=  8.00 x(3)= 47.00 y= 87.60
x(0)=  7.00 x(1)= 52.00 x(2)=  6.00 x(3)= 33.00 y= 95.90
x(0)= 11.00 x(1)= 55.00 x(2)=  9.00 x(3)= 22.00 y=109.20
x(0)=  3.00 x(1)= 71.00 x(2)= 17.00 x(3)=  6.00 y=102.70
x(0)=  1.00 x(1)= 31.00 x(2)= 22.00 x(3)= 44.00 y= 72.50
x(0)=  2.00 x(1)= 54.00 x(2)= 18.00 x(3)= 22.00 y= 93.10
x(0)= 21.00 x(1)= 47.00 x(2)=  4.00 x(3)= 26.00 y=115.90
x(0)=  1.00 x(1)= 40.00 x(2)= 23.00 x(3)= 34.00 y= 83.80
x(0)= 11.00 x(1)= 66.00 x(2)=  9.00 x(3)= 12.00 y=113.30
x(0)= 10.00 x(1)= 68.00 x(2)=  8.00 x(3)= 12.00 y=109.40

mean of x(i) and y:
x(0)= 7.462 x(1)=48.154 x(2)=11.769 x(3)=30.000 y=95.423

regression coeffi b(i):
b(0)= 1.451938 b(1)= 0.416110 b(2)= 0.000000 b(3)=-0.236540 b(4)=71.648307 

standard partial sum of square of 
regression for x(i) and sum of 
square of residuals:
v(0)=-3.022750e-001 v(1)=-9.864403e-003 v(2)=4.016921e-005 v(3)=-3.657077e-003 
q=4.797273e+001

standard deviation of regression  
coeffi and regression equation:
s(0)=1.169976e-001 s(1)=1.856105e-001 s(2)=0.000000e+000 s(3)=1.732878e-001 
s=2.308745e+000

multi-correlation coeffi c is:9.911284e-001

the f value=1.668317e+002

estimated values and residuals:
ye(0)=7.843831e+001  yr(0)=6.168641e-002
ye(1)=7.286734e+001  yr(1)=1.432663e+000
ye(2)=1.061910e+002  yr(2)=-1.890967e+000
ye(3)=8.940164e+001  yr(3)=-1.801637e+000
ye(4)=9.564375e+001  yr(4)=2.562468e-001
ye(5)=1.053018e+002  yr(5)=3.898223e+000
ye(6)=1.041287e+002  yr(6)=-1.428673e+000
ye(7)=7.559188e+001  yr(7)=-3.091878e+000
ye(8)=9.181823e+001  yr(8)=1.281775e+000
ye(9)=1.155461e+002  yr(9)=3.538826e-001
ye(10)=8.170227e+001  yr(10)=2.097732e+000
ye(11)=1.122444e+002  yr(11)=1.055614e+000
ye(12)=1.116247e+002  yr(12)=-2.224668e+000

matrix r:
1.066330e+000  2.043901e-001  -8.936536e-001  4.605878e-001  5.677366e-001  
2.043901e-001  1.878031e+001  -2.242266e+000  1.832256e+001  4.304144e-001  
8.936536e-001  2.242266e+000  2.133634e-002  2.371430e+000  9.257775e-004  
4.605878e-001  1.832256e+001  -2.371430e+000  1.894008e+001  -2.631830e-001  
-5.677366e-001  -4.304144e-001  9.257775e-004  2.631830e-001  1.766455e-002  


f1=4.750000e+000  f2=4.670000e+000

original x(i) and y values:
x(0)=  7.00 x(1)= 26.00 x(2)=  6.00 x(3)= 60.00 y= 78.50
x(0)=  1.00 x(1)= 29.00 x(2)= 15.00 x(3)= 52.00 y= 74.30
x(0)= 11.00 x(1)= 56.00 x(2)=  8.00 x(3)= 20.00 y=104.30
x(0)= 11.00 x(1)= 31.00 x(2)=  8.00 x(3)= 47.00 y= 87.60
x(0)=  7.00 x(1)= 52.00 x(2)=  6.00 x(3)= 33.00 y= 95.90
x(0)= 11.00 x(1)= 55.00 x(2)=  9.00 x(3)= 22.00 y=109.20
x(0)=  3.00 x(1)= 71.00 x(2)= 17.00 x(3)=  6.00 y=102.70
x(0)=  1.00 x(1)= 31.00 x(2)= 22.00 x(3)= 44.00 y= 72.50
x(0)=  2.00 x(1)= 54.00 x(2)= 18.00 x(3)= 22.00 y= 93.10
x(0)= 21.00 x(1)= 47.00 x(2)=  4.00 x(3)= 26.00 y=115.90
x(0)=  1.00 x(1)= 40.00 x(2)= 23.00 x(3)= 34.00 y= 83.80
x(0)= 11.00 x(1)= 66.00 x(2)=  9.00 x(3)= 12.00 y=113.30
x(0)= 10.00 x(1)= 68.00 x(2)=  8.00 x(3)= 12.00 y=109.40

mean of x(i) and y:
x(0)= 7.462 x(1)=48.154 x(2)=11.769 x(3)=30.000 y=95.423

regression coeffi b(i):
b(0)= 1.468306 b(1)= 0.662250 b(2)= 0.000000 b(3)= 0.000000 b(4)=52.577349 

standard partial sum of square of 
regression for x(i) and sum of 
square of residuals:
v(0)=-3.124101e-001 v(1)=-4.447304e-001 v(2)=3.606305e-003 v(3)=3.657077e-003 
q=5.790448e+001

standard deviation of regression  
coeffi and regression equation:
s(0)=1.213009e-001 s(1)=4.585472e-002 s(2)=0.000000e+000 s(3)=0.000000e+000 
s=2.406335e+000

multi-correlation coeffi c is:9.892817e-001

the f value=2.295037e+002

estimated values and residuals:
ye(0)=8.007400e+001  yr(0)=-1.574002e+000
ye(1)=7.325092e+001  yr(1)=1.049081e+000
ye(2)=1.058147e+002  yr(2)=-1.514740e+000
ye(3)=8.925848e+001  yr(3)=-1.658477e+000
ye(4)=9.729251e+001  yr(4)=-1.392515e+000
ye(5)=1.051525e+002  yr(5)=4.047511e+000
ye(6)=1.040021e+002  yr(6)=-1.302051e+000
ye(7)=7.457542e+001  yr(7)=-2.075420e+000
ye(8)=9.127549e+001  yr(8)=1.824513e+000
ye(9)=1.145375e+002  yr(9)=1.362457e+000
ye(10)=8.053567e+001  yr(10)=3.264326e+000
ye(11)=1.124372e+002  yr(11)=8.627555e-001
ye(12)=1.122934e+002  yr(12)=-2.893440e+000

matrix r:
1.055129e+000  -2.411808e-001  -8.359848e-001  -2.431816e-002  5.741367e-001  
-2.411808e-001  1.055129e+000  5.184659e-002  -9.673964e-001  6.850167e-001  
8.359848e-001  -5.184659e-002  3.182559e-001  -1.252070e-001  3.387813e-002  
2.431816e-002  9.673964e-001  -1.252070e-001  5.279810e-002  -1.389556e-002  
-5.741367e-001  -6.850167e-001  3.387813e-002  -1.389556e-002  2.132163e-002  


f1=9.330000e+000  f2=9.070000e+000

original x(i) and y values:
x(0)=  7.00 x(1)= 26.00 x(2)=  6.00 x(3)= 60.00 y= 78.50
x(0)=  1.00 x(1)= 29.00 x(2)= 15.00 x(3)= 52.00 y= 74.30
x(0)= 11.00 x(1)= 56.00 x(2)=  8.00 x(3)= 20.00 y=104.30
x(0)= 11.00 x(1)= 31.00 x(2)=  8.00 x(3)= 47.00 y= 87.60
x(0)=  7.00 x(1)= 52.00 x(2)=  6.00 x(3)= 33.00 y= 95.90
x(0)= 11.00 x(1)= 55.00 x(2)=  9.00 x(3)= 22.00 y=109.20
x(0)=  3.00 x(1)= 71.00 x(2)= 17.00 x(3)=  6.00 y=102.70
x(0)=  1.00 x(1)= 31.00 x(2)= 22.00 x(3)= 44.00 y= 72.50
x(0)=  2.00 x(1)= 54.00 x(2)= 18.00 x(3)= 22.00 y= 93.10
x(0)= 21.00 x(1)= 47.00 x(2)=  4.00 x(3)= 26.00 y=115.90
x(0)=  1.00 x(1)= 40.00 x(2)= 23.00 x(3)= 34.00 y= 83.80
x(0)= 11.00 x(1)= 66.00 x(2)=  9.00 x(3)= 12.00 y=113.30
x(0)= 10.00 x(1)= 68.00 x(2)=  8.00 x(3)= 12.00 y=109.40

mean of x(i) and y:
x(0)= 7.462 x(1)=48.154 x(2)=11.769 x(3)=30.000 y=95.423

regression coeffi b(i):
b(0)= 1.439958 b(1)= 0.000000 b(2)= 0.000000 b(3)=-0.613954 b(4)=103.097382 

standard partial sum of square of 
regression for x(i) and sum of 
square of residuals:
v(0)=-2.979291e-001 v(1)=9.864403e-003 v(2)=8.810045e-003 v(3)=-4.385230e-001 
q=7.476211e+001

standard deviation of regression  
coeffi and regression equation:
s(0)=1.384166e-001 s(1)=0.000000e+000 s(2)=0.000000e+000 s(3)=4.864455e-002 
s=2.734266e+000

multi-correlation coeffi c is:9.861395e-001

the f value=1.766270e+002

estimated values and residuals:
ye(0)=7.633987e+001  yr(0)=2.160128e+000
ye(1)=7.261175e+001  yr(1)=1.688249e+000
ye(2)=1.066579e+002  yr(2)=-2.357850e+000
ye(3)=9.008110e+001  yr(3)=-2.481102e+000
ye(4)=9.291662e+001  yr(4)=2.983380e+000
ye(5)=1.054299e+002  yr(5)=3.770057e+000
ye(6)=1.037335e+002  yr(6)=-1.033535e+000
ye(7)=7.752338e+001  yr(7)=-5.023380e+000
ye(8)=9.247032e+001  yr(8)=6.296816e-001
ye(9)=1.173737e+002  yr(9)=-1.473711e+000
ye(10)=8.366292e+001  yr(10)=1.370834e-001
ye(11)=1.115695e+002  yr(11)=1.730521e+000
ye(12)=1.101295e+002  yr(12)=-7.295210e-001

matrix r:
1.064105e+000  -1.088321e-002  -8.692506e-001  2.611794e-001  5.630523e-001  
1.088321e-002  5.324726e-002  -1.193945e-001  9.756262e-001  2.291839e-002  
8.692506e-001  -1.193945e-001  2.890506e-001  1.838163e-001  -5.046334e-002  
2.611794e-001  -9.756262e-001  -1.838163e-001  1.064105e+000  -6.831066e-001  
-5.630523e-001  2.291839e-002  -5.046334e-002  6.831066e-001  2.752895e-002