R help - Mar 2011 - linear regression in a data.frame using recast

I have a very large dataset with columns of id number, actual value,
predicted value.  This used to be a time series but I have dropped the
time component.  So I now have a data.frame where the id number is
repeated but each value in the actual and predicted columns are
unique.

I assume I need to use recast somehow but I'm at a loss... how can I
perform a simple linear regression (using lm()?) on my two variables
for each unique id number?

additionally, I need to fix the y-intercept at zero.


Thanks for your help,

Justin

On Mar 16, 2011, at 3:19 PM, Justin Haynes wrote:
> I have a very large dataset with columns of id number, actual value,
> predicted value.  This used to be a time series but I have dropped the
> time component.  So I now have a data.frame where the id number is
> repeated but each value in the actual and predicted columns are
> unique.
>
> I assume I need to use recast somehow but I'm at a loss... how can I
> perform a simple linear regression (using lm()?) on my two variables
> for each unique id number?
>
> additionally, I need to fix the y-intercept at zero.
?formula

Something like:

lm(y ~ x + factor(id) -1, data=dat)

If this is really a time series, then you will have serious validity  
problems due to auto-correlation among non-independent units. (But if  
you are just searching for a way to pull the wool over the eyes of the  
statistically uninformed, then I guess there's no stopping you.)

-- 

David Winsemius, MD
West Hartford, CT