[R] Package ‘orcutt’ bug?

[王柏元]

Hello~
 
Did any one have used the package 'orcutt' ? 
 
I find that it can not work smoothly in a single variable regression. I use the 
example following, it function very well.
 
But when I regress "cons" on "price" (use the 
"reg1<-lm(cons~price+income+temp)") , then  use "reg11<-cochrane.orcutt(reg1)
". There is an error message “Error in X[, -1] %*% regCO$coeff[-1] : 
non-conformable arguments”.
 
Is this a bug for this function?
 
> price<-c(  0.27,  0.28,  0.28,  0.28,  0.27,  0.26,  0.28  ,0.27  
> ,0.26  ,0.28,  0.28  ,0.27,  0.27,  0.29,  0.28,0.29,  0.28,  0.28,  
> 0.28,  0.28,  0.29,  0.29,  0.28,  0.28,  0.28,  0.26,  0.26  
> ,0.26,  0.27  ,0.26)
> cons<-c(0.39,  0.37,  0.39,  0.42,  0.41,  0.34,  0.33,  0.29,  
> 0.27,  0.26,  0.29  ,0.30,  0.33,  0.32,  0.38,0.38,  0.47,  0.44,  
> 0.39,  0.34,  0.32,  0.31,  0.28,  0.33,  0.31,  0.36,  0.38  
> ,0.42,  0.44  ,0.55)
> income<-c(78,  79,  81,  80  ,76  ,78,  82,  79,  76,  79,  82,  
> 85,  86,  83,  84,  82,  80,  78,  84,  86,  85,  87,  94,  92,  
> 95,  96,  94,  96,  91,  90)
> temp<-c(41,56,63,68,69,65,61,47,32,24,28,26,32,40,55,63,72,72,67,60,44,40,32,27,28,33,41,52,64,71)
> reg<-lm(cons~price+income+temp)
> library(orcutt)
Warning message:
package ‘orcutt’ was built under R version 2.14.2 
> reg2<-cochrane.orcutt(reg)
> reg2
$Cochrane.Orcutt
Call:
lm(formula = YB ~ XB - 1)
Residuals:
      Min        1Q    Median        3Q       Max 
-0.072610 -0.012760  0.000906  0.015209  0.077841 
Coefficients:
                Estimate Std. Error t value Pr(>|t|)    
XB(Intercept)  0.2424113  0.2531469   0.958   0.3474    
XBprice       -1.1927018  0.6873988  -1.735   0.0950 .  
XBincome       0.0031820  0.0014969   2.126   0.0436 *  
XBtemp         0.0035572  0.0005339   6.662 5.56e-07 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ 
’ 1 
Residual standard error: 0.0317 on 25 degrees of freedom
Multiple R-squared: 0.9837,     Adjusted R-squared: 0.9811 
F-statistic: 378.3 on 4 and 25 DF,  p-value: < 2.2e-16 

$rho
[1] 0.3788941
$number.interaction
[1] 12
 
> reg1<-lm(cons~price)
> reg11<-cochrane.orcutt(reg1)
Error in X[, -1] %*% regCO$coeff[-1] : non-conformable arguments
  
Paul Wang
pywan...@yahoo.com.tw
        [[alternative HTML version deleted]]


______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.