Re: [R] cdplot error
On 03/08/11 05:52, wildernessness wrote: Fairly new at this. Trying to create a conditional density plot. cdplot(status~harvd.l,data=phy) Error in cdplot.formula(status~harvd.l,data=phy): dependent variable should be a factor What does this error mean? Status is a binary response of infestation (0/1) Probably status is a numerical variable rather than a factor**. Try print(is.factor(phy$status)) and if that is FALSE then phy$status - factor(phy$status, labels=c(N, Y)) cdplot(status~harvd.l,data=phy) Hope this helps a little. Allan and harvd.l is the log of timber harvest density per catchment. Thanks. -- View this message in context: http://r.789695.n4.nabble.com/cdplot-error-tp3714454p3714454.html Sent from the R help mailing list archive at Nabble.com. __ 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. __ 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.
Re: [R] cdplot error
On 2011-08-02 21:52, wildernessness wrote: Fairly new at this. Trying to create a conditional density plot. cdplot(status~harvd.l,data=phy) Error in cdplot.formula(status~harvd.l,data=phy): dependent variable should be a factor What does this error mean? Status is a binary response of infestation (0/1) and harvd.l is the log of timber harvest density per catchment. Your question suggests that have not looked at help(cdplot) which clearly says just what the error message says and/or you aren't aware that 'factor' has a specific meaning in R in which case a look at chapter 4 of 'An Introduction to R' likely would be profitable. Peter Ehlers Thanks. -- View this message in context: http://r.789695.n4.nabble.com/cdplot-error-tp3714454p3714454.html Sent from the R help mailing list archive at Nabble.com. __ 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. __ 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.
Re: [R] cdplot????
On Thu, 1 Oct 2009, kayj wrote: I am having difficulties interpreting a cdplot, I have a binary variable y that I want to cdplot against a continuous variable x,below is the R command cdplot(y~x, data=mydata) you get a plot with a dark shaded area and a light shaded area. what do these areas mean? and how to interpret the plot? you help is greatly appreciated See ?cdplot. It's a display that graphs (an approximation of) P(y | x) against x. The areas above and below the line are simply shaded in different levels of gray. To obtain P(y | x), the idea is to use f(y | x) = f(x | y) * f(x)/f(y) where for f(x) and f(x | y) are obtained by (unconditional and conditional, respectively) kernel density smoothers from density(). f(y) is simply the unconditional proportion of the category y. hth, Z -- View this message in context: http://www.nabble.com/cdplot-tp25696905p25696905.html Sent from the R help mailing list archive at Nabble.com. __ 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. __ 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.
