[R] abline in log-log power law plot

[Peter Dalgaard]

hadley wickham wrote:
> On Fri, Feb 22, 2008 at 2:38 PM, martin klein <mklein at cs.odu.edu> wrote:
>   
>>  I have a power law plot in log-log scale using plot(x,y,log="xy") but I
>>  can't get the regression line to plot correctly.
>>  abline(lm(log(y)~log(x))) plots a straight line that looks promising but
>>  the intercept with the y-axis seems to be way off.
>>  summary(lm(log(y)~log(x))) gives the values but i cant really make any
>>  sense out of it.
>>  fitted(..) just confirms the values that seem to be incorrect.
>>  any help is appreciated.
>>  thanks!
>>     
>
> You might try using ggplot2 instead:
>
> install.packages("ggplot2")
> library(ggplot2)
>
> qplot(x, y, log="xy") + geom_smooth(method = lm)
>
> Hadley
>
>   
Or just switch to base-10 logarithms:

abline(lm(log10(y)~log10(x)))

-- 
   O__  ---- Peter Dalgaard             Øster Farimagsgade 5, Entr.B
  c/ /'_ --- Dept. of Biostatistics     PO Box 2099, 1014 Cph. K
 (*) \(*) -- University of Copenhagen   Denmark          Ph:  (+45) 35327918
~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk)                  FAX: (+45) 35327907