similar to: Hurwicz Bias Correction

dear R experts---now I have a case where I want to estimate very large regression models with many fixed effects---not just the mean type, but cross-fixed effects---years, months, locations, firms. Many millions of observations, a few thousand variables (most of these variables are interaction fixed effects). could someone please point me to packages, if any, that would help me estimate such

Hi, Way back in 2004, an update to randomForest added an option 'corr.bias'. The explanation was a bit vague, but it turns out it improves RF's predictive fit with my data substantially. But I am having trouble understanding it. Does anyone know what this 'bias correction' actually does? Or what the justification for it is? Or when it would be necessary? Is there a paper

Dear R-Help List, I'm trying to implement Firth's (1993) bias correction for log-linear models. Firth (1993) states that such a correction can be implemented by supplementing the data with a function of h_i, the diagonals from the hat matrix, but doesn't provide further details. I can see that for a saturated log-linear model, h_i=1 for all i, hence one just adds 1/2 to each count,

Dear R wizards: is there a clean way to assign to elements in a list? what I would like to do, in pseudo R+perl notation is f <- function(a,b) list(a+b,a-b) (c,d) <- f(1,2) and have c be assigned 1+2 and d be assigned 1-2. right now, I use the clunky x <- f(1,2) c <- x[[1]] d <- x[[2]] rm(x) which seems awful. is there a nicer syntax? regards, /iaw ---- Ivo Welch

Hey there, I was wondering if someone could tell me if there's a package or command that allows me to compute a GINI coefficient using a vector of weights. Also the coefficient should be bias corrected. Diego Rojas [[alternative HTML version deleted]]

dear R experts---I am using the coef() function to pick off the coefficients from an lm() object. alas, I also need the standard errors and I need them fast. I know I can do a "summary()" on the object and pick them off this way, but this computes other stuff I do not need. Or, I can compute (X' X)^(-1) s^2 myself. Has someone written a fast se() function? incidentally, I think

this is not an important question, but I wonder why lm returns an error, and whether this can be shut off. it would seem to me that returning NA's would make more sense in some cases---after all, the problem is clearly that coefficients cannot be computed. I know that I can trap the lm.fit() error---although I have always found this to be quite inconvenient---and this is easy if I have only

As an end-user, I wonder about Revolution R. Is the relationship between Revolution R and the R community at-large a positive one? Do the former contribute to the development efforts of the latter? Is there a competitive aspect? is their forum competitive with r-help? any other thoughts? (most of all, I simply hope that they help some of the many helpful experts on this forum, who have

I cleaned up my old benchmarking code and added checks for missing data to compare various ways of finding OLS regression coefficients. I thought I would share this for others. the long and short of it is that I would recommend ols.crossprod = function (y, x) { x <- as.matrix(x) ok <- (!is.na(y))&(!is.na(rowSums(x))) y <- y[ok]; x

dear R community: i have been looking but failed to find the following: is there a function in R that updates a plain OLS lm() model with one additional observation, so that I can write a function that computes recursive residuals *quickly*? PS: (I looked at package strucchange, but if I am not mistaken, the recresid function there takes longer than iterating over the models fresh from

dear R wizards:? I am wrestling with reshape.? I have a long data set that I want to convert into a wide data set, in which rows are firms and columns are years. > summary(rin) firm fyear sim1 Min. :1004.00 Min. :1964.0 Min. : -1.00000 1st Qu.:1010.00 1st Qu.:1979.0 1st Qu.: -0.14334 Median :1016.00 Median :1986.0 Median : 0.00116 Mean

dear R experts: does R have "static" variables that are local to functions? I know that they are usually better avoided (although they are better than globals). However, I would like to have a function print how often it was invoked when it is invoked, or at least print its name only once to STDOUT when it is invoked many times. possible without <<- ? sincerely, /iaw

dear R experts--- t <- 1:30 f <- function(t) { cat("f for", t, "\n"); return(2*t) } g <- function(t) { cat("g for", t, "\n"); return(3*t) } s <- ifelse( t%%2==0, g(t), f(t)) shows that the ifelse function actually evaluates both f() and g() for all values first, and presumably then just picks left or right results based on t%%2.

dear R wizards: here is the strange question for the day. It seems to me that nrow() is very slow. Let me explain what I mean: ds= data.frame( NA, x=rnorm(10000) ) ## a sample data set > system.time( { for (i in 1:10000) NA } ) ## doing nothing takes virtually no time user system elapsed 0.000 0.000 0.001 ## this is something that should take time; we need to add 10,000

Hi folks, I'm trying to estimate bias-corrected percentile (BCP) confidence intervals on a vector from a simple for loop used for resampling. I am attempting to follow steps in Manly, B. 1998. Randomization, bootstrap and monte carlo methods in biology. 2nd edition., p. 48. PDF of the approach/steps should be available here: https://wyocoopunit.box.com/s/9vm4vgmbx5h7um809bvg6u7wr392v6i9 If

Dear R experts--- after many years, I am planning to give in and write my first R package. I want to combine my collection of collected useful utility routines. as my guide, I am planning to use Friedrich Leisch's "Creating R Packages: A Tutorial" from Sep 2009. Is there a newer or better tutorial? this one is 4 years old. I also plan on one change---given that the

Dear R Users, My question is overall and not necessarily related to R. Suppose we face to a situation in which MSE( Mean Squared Error) shows desired results but Bias shows undesired ones, Or in advers. How can we evaluate the results. And suppose, Both MSE and Bias are important for us. The ecact question is that, whether there is any combined measure of two above metrics. Thank you so

Dear R wizards---I read Brian Ripley's post from 2004 which said that it was not possible to print to STDERR. Alas, I have more modest needs. I was wondering if it was possible to just send a string to STDERR with cat() while in CMD BATCH mode. Is it not possible to open STDERR in R? (Or does R use STDERR for itself and redirect it into the output stream?) This would be on a standard Unix

Dear R users: In Prof. Harrell's library rms, calibrate.rms plot the Bias-corrected Probability and Apparent Probability. The latter one can be retrieved from class calibrate.default. But how to retrieve the former one. BW *Yao Zhu* *Department of Urology Fudan University Shanghai Cancer Center Shanghai, China* [[alternative HTML version deleted]]

just a short beg for the next R 2.3 version: I know it is easy to add the sd into summary() in the source bowels of R---but everytime R is updated, my change disappears. :-(. I do not believe that R has an easy extension mechanism for univariate summaries, short of a function rewrite here. Could this please be added into R 2.3? Aside, a logical ordering might also be: mean sd min q1 med q3