[R] Incremental Sparse Bridge PLS algorithm (iSB-PLS)

I'm reading the paper "Predictive modeling with high-dimensional data streams: an on-line variable selection approach", from McWilliams and Montana, which introduces an interesting algorithm to dynamically select variables in high dimensional data streams. Does anyone know if this (or a similar

[R] Are there equivalents to xblocks or rect that can be used with plot.xts?

I would like to add vertical shaded blocks in plot.xts graphs (like recession periods in FRED graphs) The reason I use plot.xts instead of plot.zoo is that I like the fact that the grid is automatically aligned with major ticks in plot.xts. xblocks() and rect() do not seem to work with plot.xts

[R] Filling missing days in xts time series

Hi, I have a bunch of irregularly spaced xts time series (with a POSIX index), and I'm trying to write a function that fillls the missing days. Using a solution suggested by Gabor Grothendieck for zoo, I wrote the following: # FD: Fill missing days FD<-function(ser) {rng<-range(time(ser)) > tem

Re: [R] How to do operations on zoo/xts objects with Monthly and Daily periodicities

Thanks for your suggestion Gabor, it has helped me in my developments during the last few months. I'm now trying to go further by being able to do the following: I have a collection of xts time series that are spaced in different ways (weekdays only, monthly, quarterly etc.). Is there an efficie

[R] Calculate the latest Z-score of all zoo time series

Hello, I have a population of 2000+ zoo time series (but my environment also contains objects that are not zoo time series). I'm trying to calculate the latest 90 days Z-Score of all zoo time series, using the following code: LZS<-function(ser) { temp<-window(ser,start=Sys.Date()-90) last((temp-

[R] How to do operations on zoo/xts objects with Monthly and Daily periodicities

Is there an elegant way to do operations (+/-/*/ / ) on zoo/xts objects when one serie is monthly (end of month) and the other daily (weekdays only) - typically a monthly economic indicator and a stock index price? Thanks, TDB -- View this message in context: http://r.789695.n4.nabble.com/H

[R] non-parametric regression with a convexity constraint

I would like to know if there's a package in R that enables to get a non-parametric regression (OLS, not quantile) that would have a positive (or negative) convexity constraint, as well as monotonicity. Right now, I have only found two packages (fdrtool and cir) that enable to impose only monoto

[R] R Quantreg package: "CI" constraint in qss

Hello, For a few large set of points, whenever I use a "CI" constraint in the qss term, I get the following error message: Warning message: In rq.fit.sfnc(x, y, tau = tau, ...) : tiny diagonals replaced with Inf when calling blkfct Without any constraint, these sets work well. Does anyone kn

[R] R square for Monotone regression

I'm using the monoreg function (with weights) from the fdrtool package. How can I calculate the R square for this type of regression? Thanks for your help, Thierry -- View this message in context: http://www.nabble.com/R-square-for-Monotone-regression-tp15580803p15580803.html Sent from the

[R] Function built with segments

Hello, I'm new to R. If I have a set of 10 points (X(i), Y(i)), is there an elegant way to build a function y=f(x) that would be build out of the consecutive segments of X(j),Y(j) points (with X(j) sorted)? Thank you very much TDB -- View this message in context: http://www.nabble.com/Fun

[R] Gaussian Smoothing

Hello, I'm new to R, and I would like to know if there is a way to smooth a curve using a Gaussian smoothing with R. Thank you very much, TDB -- View this message in context: http://www.nabble.com/Gaussian-Smoothing-tp14321313p14321313.html Sent from the R help mailing list archive at Nabb