Problem with LM

Richard,

It is now working.

Thank you very much.

Bob
On 12/18/2018 7:10 PM, Richard M. Heiberger wrote:

## This example, with your variable names, works correctly.

z2 <- data.frame(y=1:5, x=c(1,5,2,3,5), x2=c(1,5,2,3,5)^2)
z2
class(z2)
length(z2)
dim(z2)

lm(y ~ x + x2, data=z2)

## note that that variable names y, x, x2 are column names of the
## data.frame z2

## please review the definitions and examples of data.frame in

?data.frame

## also the argument requirements for lm in ?lm

On Tue, Dec 18, 2018 at 6:32 PM rsherry8 <rsherry8 at comcast.net> wrote:

The values read into z2 came from a CSV file. Please consider this R
session:

  > length(x2)

[1] 1632

  > length(x)

[1] 1632

  > length(z2)

[1] 1632

  > head(z2)

[1] 28914.0 28960.5 28994.5 29083.0 29083.0 29083.0

  > tail(z2)

[1] 32729.65 32751.85 32386.05 32379.75 32379.15 31977.15

  > lm ( y ~ x2 + x, z2 )

Error in eval(predvars, data, env) :
    numeric 'envir' arg not of length one

  > lm ( y ~ x2 + x, as.data.frme(z2) )

Error in as.data.frme(z2) : could not find function "as.data.frme"

  > lm ( y ~ x2 + x, as.data.frame(z2) )

Error in eval(predvars, data, env) :
    numeric 'envir' arg not of length one
lm(formula = y ~ x2 + x, data = as.data.frame(z2))

Coefficients:
(Intercept)           x2            x
   -1.475e-09    1.000e+00    6.044e-13

  > min(z2)

[1] 24420

  > max(z2)

[1] 35524.85

  > class(z2)

[1] "numeric"

  >

where x is set to x = seq(1:1632)
and x2 is set to x^2

I am looking for an interpolating polynomial of the form:
      Ax^2 + Bx + C
I do not think the results I got make sense. I believe that I have a
data type error.  I do not understand why
I need to convert z2 to a data frame if it is already numeric.

Thanks,
Bob