Hi all,I would like to know how to predict a new y value and its confidence
interval for the prediction given a new observation x when using a linear(or
non-linear) quantile regression model.How it is possible to transform the
confidence prediction in to an interval prediction?
Is it correct to
15:03, Angel Marley wrote:
Dear R list,
I'm working with recursive tress using packages mvpart and rpart in R in
linux xubuntu (64).
The package performed with no problem under my previous R version (2.14)
I had recently updated my R version to 3.1.1 and when I try to run a mvpart
model I
Dear R list,
I'm working with recursive tress using packages mvpart and rpart in R in linux
xubuntu (64).
The package performed with no problem under my previous R version (2.14)
I had recently updated my R version to 3.1.1 and when I try to run a mvpart
model I get the following error
Hi everybody, I would like to compare using the Akaike Information Criteria
(AIC) a quadratic model and a piecewise fitted model.
Is it correct to use AIC to compare this models with such a different structure?
Thanks in advance
Angel
# A simple example
a-1
b-2
xx-seq(-15,15,length=50) #
Dear R users,
I'm trying to extract from a given matrix (GROUP) the coordinates of the
vertices of the different groups (i.e. 3, 7, 1 . . .) to plot the polygons to
delineate the area in which each group wins and colour it diferentially. I
can make a simple point plot, but I would like to add
Hi everybody,
I'm trying a multiple histogram, and I'd like to add on it a secondary axis
with a line (cumulative frequencies, or wathever lines), and the 0 intercept
doesnt coincide in y1 and y2, which dificult interpretation and makes
presentation not nice. I had seen some related answer for
Hi,
I would like to save many trees created in a loop as
different ones. I can plot them, but I can not get the
whole tree properties saved. I paste the script below
Also, How can I perform multivariate trees?, that is
predicting a vector o values, not a simple scalar
observation.
Thanks in
7 matches
Mail list logo