similar to: pointwise confidence bands or interval values for a non parametric sm.regression

Hi all. I hope I have my terminology right here... For a simple lm, one can add ?pointwise confidence bounds? to a fitted line using something like >predict(results.lm, newdata = something, interval = "confidence") (I'm following DAAG page 154-155 for this) I would like to do the same thing for a glm of the logistic regression type, for instance, the example in MASS pg

To my understanding, a confidence interval typically covers a single valued parameter. In contrast, a confidence band covers an entire line with a band. In regression, it is quite common to construct confidence and prediction bands. I have found that many people are connecting individual confidence/prediction interval values produced with predict(object,sd.fit=T,type="conf/pred") and

Just trying to create returns from prices, and do something like: returns.z = tail(prices.z,-1)/head(prices.z,-1) - 1 # should be equivalent to returns = exp(diff(log(prices.z))) - 1 Curiously, I get a zoo object back with zeros everywhere and also with the index having one fewer element than it should. Does anyone know how to pointwise divide zoo objects, and what exactly "/" is

I'm trying to find a bootstrap based confidence band for a linear model. I have created a data set with X and Y X=runif(n,-1.25,1.25) e=rnorm(n,0,1) Y=exp(3*X)+5*sin((30*X)/(2*pi))+2*e fit=lm(Y~X) summary(fit)   I define a bootstrap function named PairedBootstrap which is not listed here. Than I try many ways to find the confidence band. One way is to predict Y using the model I get above for

Hi all, I just uploaded a new version of the bpcp package. It calculates confidence intervals for a survival distribution for right-censored data using the newly developed beta product confidence procedure. Previously developed methods can have substantial error rate inflation for the lower limit, especially at the right end of the curves when there are small numbers of events. The bpcp method

Dear all, Is there any package or function can do the pointwise confidence interval and confidence band for the local polynomial regression? Maybe the local linear regression is enough. Thanks. Regards, Zhen

Dear expeRts, I somehow don't see why the following does not work: integrand <- function(x, vec, mat, val) 1 # dummy return value A <- matrix(runif(16), ncol = 4) u <- c(0.4, 0.1, 0.2, 0.3) integrand(0.3, u, A, 4) integrate(integrand, lower = 0, upper = 1, vec = u, mat = A, val = 4) I would like to integrate a function ("integrand") which gets an "x" value (the

Dear all, I've now spent a couple of days trying to learn R and, in particular, the gam() function, and I now have a few questions and reflections regarding the latter. Maybe these things are implemented in some way that I'm not yet aware of or have perhaps been decided by the R community to not be what's wanted. Of course, my lack of complete theoretical understanding of what

I'm using nonparametric regression (packeges ksmooth and ks). My question: is there any way to compute confidence bands (or variability bands) with R. Confidence bands for functions are intervals [CLO(x);CUP(x)] such that with probability 1-alpha the true curve is covered by the band [CLO(x);CUP(x)]. Thanks very much for any help you can offer. Michael G??lger

Good morning, I am Marta Colombo,student at Politecnico,Milan. I am studying local regression models and I am using loess function. My problem is that when I have a loess object I don't know how to display the fitted surface; in fact, while in S when you have a loess object you can see it writing plot(object), in R this dosen't work. Also I'd like to know if there is something like the

Hello, Is there any other bivariate pointwise interpolation command besides akima's interpp? I tried to search through the J. Baron's page without luck. The problem is that I have got regularly spaced data (in x and y) what is not acceptable for interpp. I am not very much interested in the method of interpolation as the data are dense and the error would not be to high. Thanks in

Dear R-Users, I have problems with the cobs library. When doing the cobs example, I get the folling error message: example(cobs) cobs> x <- seq(-1, 3, , 150) cobs> y <- (f.true <- pnorm(2 * x)) + rnorm(150)/10 cobs> con <- rbind(c(1, min(x), 0), c(-1, max(x), 1), c(0, 0, 0.5)) cobs> Rbs <- cobs(x, y, constraint = "increase", pointwise = con)

I would like to apply a function 'f' to the lagged version of a vector and the vector itself. This is easy to do explicitly: mapply( f, v[-1], v[-length(v)] ) or in the case of a pointwise vector function, simply f( v[-1], v[-length(v)] ) This is essentially the same as 'diff' but with an arbitrary function, not '-'. Is there a standard way to do this? Is

Hi there, I'm plotting some glass RI values just by plotting plot(x) then I put on my lowess smoother lines(lowess(x)) now I want to put on some 95% Confidence Interval bands of the lowess smoother, but don't know how?? Thanks -- Gareth Campbell PhD Candidate The University of Auckland P +649 815 3670 M +6421 256 3511 E gareth.campbell@esr.cri.nz gcam032@gmail.com [[alternative

Greetings. For R gurus this may be a no brainer, but I could not find pointers to efficient computation of this beast in past help files. Background - I wish to implement a Cramer-von Mises type test statistic which involves double sums of max(X_i,Y_j) where X and Y are vectors of differing length. I am currently using ifelse pointwise in a vector, but have a nagging suspicion that there is a

Dear List, I would greatly appreciate help on the following matter: The RuleFit program of Professor Friedman uses partial dependence plots to explore the effect of an explanatory variable on the response variable, after accounting for the average effects of the other variables. The plot method [plot(summary(rq(y ~ x1 + x2, t=seq(.1,.9,.05))))] of Professor Koenker's quantreg program

Morning, This weekend I attempted an upgrade of my primary samba server from 3.0.24 to 3.3.3. When testing this primary server after the upgrade I had a few issues, so rolled back the upgrade until I can find solutions. This server also has the OpenLDAP server local to and co-located with samba. The two things that initially didn't seem right are that each time I logged into a windows XP box

Dear R users, The package 'mfp' that fits fractional polynomial terms to predictors. Example: data(GBSG) f <- mfp(Surv(rfst, cens) ~ fp(age, df = 4, select = 0.05) + fp(prm, df = 4, select = 0.05), family = cox, data = GBSG) print(f) To describe the association between the original predictor, eg. age and risk for different values of age I can plot it the polynomials

Dear R-core/development-team, The problem noted in the subject-line has been a problem in the last three development versions of R for Windows that I have downloaded and tested, the most recent of them being a version I downloaded this morning. Update.packages() using the graphical option, i.e. called as update.packages(ask='graphics', checkBuilt=TRUE) does not work as it should, but

Dear List, I would appreciate help on the following matter: I am aware that higher dimensional contingency tables can be analysed using either log-linear models or as a poisson regression using a generalized linear model: log-linear: loglm(~Age+Site, data=xtabs(~Age+Site, data=SSites.Rev, drop.unused.levels=T)) GLM: glm.table <- as.data.frame(xtabs(~Age+Site, data=SSites.Rev,