[R] Putting regression lines on SPLOM

[(Ted Harding)]

Yes, that's it! Well spotted (and maybe new glasses for me ...).
Thanks! Andy's solution now also works beautifully.
Ted.

On 05-Sep-03 Andrew C. Ward wrote:
> I wonder if it's as simple as the two dots ("..") in the
> splom line rather than three?
> 
> Regards,
> 
> Andrew C. Ward


>> However, there seems to be a problem with Andy Liaw's,
>> applied to the same data:
>> 
>>   df.trans <- lapply(DF, function(x) log(1+x))  ## Do the
>> transformation.
>>   splom(df.trans, panel = function(x, y, ..) {
>>         panel.xyplot(x, y, ...)
>>         fit <- lm(log(exp(y)-1) ~ log(exp(x)-1), subset =
>> x>0 & y>0)
>>                 panel.abline(fit)
>>         })
>> 
>>   Error in panel(x = as.numeric(z[subscripts, j]),
>>                  y = as.numeric(z[subscripts,  : 
>>                      ... used in an incorrect context
>> 
>> (which is the same error as I got trying an earlier
>> suggestion of Deepayan's).

--------------------------------------------------------------------
E-Mail: (Ted Harding) <Ted.Harding at nessie.mcc.ac.uk>
Fax-to-email: +44 (0)870 167 1972
Date: 05-Sep-03                                       Time: 11:49:06
------------------------------ XFMail ------------------------------