The plotting is easy: it was done with ggplot2. The data frame contains columns for x1, x2, dataset, choice and so the code is something like:

`ggplot(data, aes(x=x1, y=x2)) + geom_point(aes(colour=choice, size=dataset))`

I saw your coding for How to: Multinomial regression models in R”. This is a new technique which I am trying. You mentioned the above coding may not be adequate for more complex models. What would you suggest in stead? Also how did you go about plotting the data. I’ve used a confusion matrix to validate my model but I would like to visualize it if possible.

My optimal five level multinomial model contains 4 continuous variables, 1 categorical (2 levels) and 2 interactions.

Many thanks

Sophie

]]>Can you please read chapter 9 and try to use the derivative of the observations in the R code. ]]>

I’d never heard of a waterfall plot as a distinct type of 3D graph, but looking at the Wiki Talk page, I’d have to agree with the comment at the bottom: “Hands up everyone who thinks that a waterfall plot looks like a waterfall. I certainly don’t.”

]]>