search for: resvar

...(unstable) (2015-01-13 r67453) gives me the following NOTE: cbind.fsets: possible error in list(...): ... used in a situation where it does not exist The file that causes this note contains: cbind.fsets <- function(..., deparse.level = 1) { dots <- list(...) res <- NULL resVars <- NULL resSpecs <- NULL for (i in seq_along(dots)) { arg <- dots[[i]] argName <- names(dots)[i] if (!is.null(arg)) { if (!is.fsets(arg)) { stop("Function 'cbind.fsets' cannot bind arguments that are not valid &...

...t; > > cbind.fsets: possible error in list(...): ... used in a situation > where it does not exist > > > The file that causes this note contains: > > > cbind.fsets <- function(..., deparse.level = 1) { > dots <- list(...) > > res <- NULL > resVars <- NULL > resSpecs <- NULL > > for (i in seq_along(dots)) { > arg <- dots[[i]] > argName <- names(dots)[i] > > if (!is.null(arg)) { > if (!is.fsets(arg)) { > stop("Function 'cbind.fsets'...

Hi, While exploring how summary.lm generated its output I came across a section that left me puzzled. at around line 57 R <- chol2inv(Qr$qr[p1, p1, drop = FALSE]) se <- sqrt(diag(R) * resvar) I'm hoping somebody could explain the logic of these to steps or alternatively point me in the direction of a text that will explain these steps. In particular I'm puzzled what is the relationship between QR factorization and the cholesky factorization such that one can give a (sort...

...vector). I am wondering if anyone has any idea of how to speed up the computations in R. The code follows: #regression function #Linear regression code qreg <- function(y,x) { X=cbind(1,x) m<-lm.fit(y=y,x=X) p<-m$rank r <- m$residuals n <- length(r) rss <- sum(r^2) resvar <- rss/(n - p) Qr <- m$qr p1 <- 1:p R <- chol2inv(Qr$qr[p1, p1, drop = FALSE]) se <- sqrt(diag(R) * resvar) b <- m$coefficients return(c(b[2],se[2])) } #simulate a <- c(1,.63,.63,1) a <- matrix(a,2,2) c <- chol(a) C <- 0.7 theta <- 0.8 sims <-...

...or" && length(grep("effectively zero",f1))>0) options(ow) f2 <- lmer(y~treat+(1|reef),data=x) c(getranvar(f2),as.numeric(w)) } rvec <- rep(c(0.01,0.05,0.1,0.15,0.2,0.3,0.5),each=100) X <- t(sapply(rvec,estfun)) colnames(X) <- c("reefvar","resvar","warn") rfrac <- X[,"reefvar"]/(X[,"reefvar"]+X[,"resvar"]) fracwarn <- tapply(X[,"warn"],rvec,mean) est.mean <- tapply(rfrac,rvec,mean) op <- par(mfrow=c(1,2)) plot(rvec,rfrac,type="n",xlim=c(-0.02,0.55),axes=FALSE) ax...

I'm running a huge number of regressions in a loop, so I tried lm.fit for a speedup. However, I would like to be able to calculate the t-stats for the coefficients. Does anyone have some functions for calculating the regression summary stats of an lm.fit object? Thanks, Whit

Hello, I was wondering if someone knows the formula used by the function lm to compute the t-values. I am trying to implement a linear regression myself. Assuming that I have K variables, and N observations, the formula I am using is: For the k-th variable, t-value= b_k/sigma_k With b_k is the coefficient for the k-th variable, and sigma_k =(t(x) x )^(-1) _kk is its standard deviation.

...} else { if (is.null(w)) { mss <- if (attr(z$terms, "intercept")) sum((f - mean(f))^2) else sum(f^2) rss <- sum(r^2) } } resvar <- rss/(n - p) se <- sqrt(resvar * diag(z$cov.unscaled)) est <- z$coefficients tval <- est/se ans <- z[c("call", "terms")] ans$residuals <- as.numeric(r) ans$coefficients <- cbind(est, se, tval, 2 * (1 - pt(abs...

...CM.SeoTest() and HanSeo_TVECM() -new function to simulate/bootstrap a TVAR: function TVAR.sim() -new function to simulate/bootstrap a TVECM: function TVECM.sim() -new function to simulate/bootstrap a setar: function setar.sim() -new function to estimate regime-specific variance in setar: function resVar() -new function to extend a bootstrap replication in setarTest: function extendBoot() -added in selectSETAR() and setar() following args: include, common, model, trim, MM, ML, MH, model, restriction -added in selectSETAR(): criterion "SSR" (sum of squares residual) and argument max.ite...

...CM.SeoTest() and HanSeo_TVECM() -new function to simulate/bootstrap a TVAR: function TVAR.sim() -new function to simulate/bootstrap a TVECM: function TVECM.sim() -new function to simulate/bootstrap a setar: function setar.sim() -new function to estimate regime-specific variance in setar: function resVar() -new function to extend a bootstrap replication in setarTest: function extendBoot() -added in selectSETAR() and setar() following args: include, common, model, trim, MM, ML, MH, model, restriction -added in selectSETAR(): criterion "SSR" (sum of squares residual) and argument max.ite...

Hi, the standard errors of the coefficients in two regressions that I computed by hand and using lm() differ by about 1%. Can somebody help me to identify the source of this difference? The coefficient estimates are the same, but the standard errors differ. ####Simulate data happiness=0 income=0 gender=(rep(c(0,1,1,0),25)) for(i in 1:100){ happiness[i]=1000+i+rnorm(1,0,40)

I have data that looks like this: > df1 group id 1 red A 2 red B 3 red C 4 blue D 5 blue E 6 blue F I want a list of the groups containing vectors with the ids. I am avoiding subset(), as it is only recommended for interactive use. Here's what I have so far: df1 <- data.frame(group=c("red", "red", "red", "blue",

...ng lm() and summary.lm(). # Use at your own risk...untested on more complex models  :-) # 'x' is an lm.fit object calc.lm.t <- function(x) {    Qr <- x$qr    r <- x$residuals    p <- x$rank    p1 <- 1L:p    rss <- sum(r^2)    n <- NROW(Qr$qr)    rdf <- n - p    resvar <- rss/rdf    R <- chol2inv(Qr$qr[p1, p1, drop = FALSE])    se <- sqrt(diag(R) * resvar)    est <- x$coefficients[Qr$pivot[p1]]    tval <- est/se    res <- cbind(est = est, se = se, tval = tval)    res } Here is some simple example data: set.seed(1) y <- rnorm(100) x <...