automated polynomial regression

Dear all -
We perform some measurements with a machine that needs to be
recalibrated. The best calibration we get with polynomial regression.
The data might look like follows:

  

true_y <- c(1:50)*.8
# the real values
m_y <- c((1:21)*1.1, 21.1, 22.2, 23.3 ,c(25:50)*.9)/0.3-5.2
# the measured data
x <- c(1:50)
# and the x-axes

# Now I do the following:

m_y_2 <- m_y^2
m_y_3 <- m_y^3
mylm <- lm(true_y ~ m_y + m_y_2 + m_y_3) ; mylm
    

Call:
lm(formula = true_y ~ m_y + m_y_2 + m_y_3)

Coefficients:
(Intercept)          m_y        m_y_2        m_y_3
  1.646e+00    1.252e-01    2.340e-03   -9.638e-06

Now I can get the real result with
  

calibration <- 1.646e+00 + 1.252e-01*m_y + 2.340e-03*m_y_2 - 9.638e-06* m_y_3
    

But I have to put the values "by hand" into the polynom.

Isn't there an easier, more direct way, or at least , is there a way
to access the coefficients of lm() for further calculations?

Thanks
Dieter

mylm <- lm(true_y ~ m_y + m_y_2 + m_y_3) ;
  

-- but it is preferable to use the appropriate access functions:

coef(mylm)

?coef

Bert Gunter
Nonclinical Biostatistics
467-7374


## Now, what I believe you're looking for ;

mylm$coefficients ;


Cheers,

--
*Luc Villandr?*
/Biostatistician
McGill University Health Center -
Montreal Children's Hospital Research Institute/