[prev in list] [next in list] [prev in thread] [next in thread] 

List:       r-sig-mac
Subject:    Re: [R-SIG-Mac] Dependent variable of left and right hand sides
From:       Rolf Turner <r.turner () auckland ! ac ! nz>
Date:       2011-05-10 3:59:53
Message-ID: 4DC8B839.7010709 () auckland ! ac ! nz
[Download RAW message or body]

(a) What has this question to do with R-SIG-Mac???  It should have
been sent to r-help.

(b) I don't understand what your problem is.  Please provide a
a commented, minimal, self-contained, reproducible example.
//
//(c) It's bad policy to use ``df'' as the name of a data frame,
since ``df'' is the name of a built-in object (the F density
function).  Why not ``CanNrgData'' or something evocative
like that?

     cheers,

             Rolf Turner

On 10/05/11 01:56, Thor Jensen wrote:
> Hello all,
> 
> An R squared novice with a trouble regression.  Some brief background:
> I am looking for a relationship between energy efficiency (based on
> certification level) against various independent variables - including
> heating and cooling days, region (11 Canadian provinces), and soon
> energy prices.
> 
> Writing out all the variables into my equation using "monkey$Level" or
> renaming them all using "Level=monkey$Level" seemed too much so I just
> represented the equation side using "lm(monkey$Level~."  The trouble
> is my dependent variable  is listed among the other independent
> variables on the right hand side.  Is this because I am using
> "monkey$level~." instead of renaming the variables via Y=monkey$Level
> and then writing Y~X1..Xn?
> 
> > summary(fm<-lm(monkey$Level~., data=df))   # monkey is a csv2 read file, and df \
> > is my data frame with ten dummy variables and two ordinary integer variables
> Call:
> lm(formula = monkey$Level ~ ., data = df)
> 
> Residuals:
> Min         1Q     Median         3Q        Max
> -1.514e-14 -1.048e-15 -1.660e-16  2.960e-16  3.118e-13
> 
> Coefficients:
> Estimate Std. Error    t value Pr(>|t|)
> (Intercept)   3.040e-14  1.170e-14  2.599e+00  0.00951 **
> monkey.Level  1.000e+00  4.571e-16  2.188e+15<  2e-16 ***
> monkey.AB     3.785e-15  1.876e-15  2.018e+00  0.04394 *
> monkey.BC    -2.550e-15  3.669e-15 -6.950e-01  0.48733
> monkey.MB     1.708e-15  2.937e-15  5.820e-01  0.56095
> monkey.NL     1.476e-15  5.022e-15  2.940e-01  0.76887
> monkey.NS     1.214e-16  2.843e-15  4.300e-02  0.96596
> monkey.NT     6.692e-15  1.155e-14  5.790e-01  0.56247
> monkey.ON    -9.637e-16  1.160e-15 -8.310e-01  0.40637
> monkey.PE     1.818e-16  6.240e-15  2.900e-02  0.97677
> monkey.SK     2.087e-15  2.539e-15  8.220e-01  0.41130
> monkey.HDD   -1.487e-18  1.657e-18 -8.980e-01  0.36958
> monkey.CDD    2.572e-18  4.551e-18  5.650e-01  0.57206
> ---
> Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
> 
> Residual standard error: 1.057e-14 on 882 degrees of freedom
> Multiple R-squared:     1,	Adjusted R-squared:     1
> F-statistic: 4.637e+29 on 12 and 882 DF,  p-value:<  2.2e-16
> 
> I hope this wasn't too much information, thanks for any help or tips
> how to do this more effectively.
> 
> Best regards,
> 
> Thor Jensen

	[[alternative HTML version deleted]]



_______________________________________________
R-SIG-Mac mailing list
R-SIG-Mac@r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-mac


[prev in list] [next in list] [prev in thread] [next in thread]