search for: validmu

...burn suggested using the variance function mu^2(1-mu)^2. This variance function isn't readily available in R's `quasi' family object, but it seems to me that the following definition could be used: }, "mu^2(1-mu)^2" = { variance <- function(mu) mu^2 * (1 - mu)^2 validmu <- function(mu) all(mu > 0) && all(mu < 1) dev.resids <- function(y, mu, wt) 2 * wt * ((2 * y - 1) * (log(ifelse(y == 0, 1, y/mu)) - log(ifelse(y == 1, 1, (1 - y)/(1 - mu)))) - 2 + y/mu + (1 - y)/(1 - mu)) I've modified the `quasi' function accord...

...gt;]) it says: valid.mu: logical function. Returns ?TRUE? if a mean vector ?mu? is within the domain of ?variance?. valid.eta: logical function. Returns ?TRUE? if a linear predictor ?eta? is within the domain of ?linkinv?. However, the real names of these elements are "validmu" and "valideta" (no dots); try names(poisson()) or names(binomial()) and see ... Can someone on R-core fix this and save me the trouble of filing a bug report ... ? Or have I misunderstood something? cheers Ben Bolker

...env <- new.env(parent = .GlobalEnv) assign(".nziek", nziek, envir = env) famname<-"Addhaza" link="addlink" linkfun<-function(mu) -log(1-mu) linkinv<-function(eta) 1-exp(-eta) variance<-function(mu) mu*(1-mu) validmu<-function(mu) all(mu > 0) && all(mu < 1) mu.eta<-function(mu) 1/(1-mu) dev.resids <- function(y, mu, wt) 2 * wt * (y * log(ifelse(y == 0, 1, y/mu)) + (1 - y) * log(ifelse(y == 1, 1, (1 - y)/(1 - mu)))) aic <- function(y, n, mu...

...ly$linkinv 25 mu.eta <- family$mu.eta 26 if (!is.function(variance) || !is.function(linkinv)) 27 stop("illegal `family' argument") 28 valideta <- family$valideta 29 if (is.null(valideta)) 30 valideta <- function(eta) TRUE 31 validmu <- family$validmu 32 if (is.null(validmu)) 33 validmu <- function(mu) TRUE 34 if (is.null(mustart)) { 35 eval(family$initialize) 36 } 37 else { 38 mukeep <- mustart 39 eval(family$initialize) 40 mustart <- mukeep...

In a glm() call using a quasi() family, one may define a custom variance function in the form of a "list containing components varfun, validmu, dev.resids, initialize and name" (quoting the help page for family). In trying to do so, I run into the following issue that I have not seen discussed previously: x <- runif(1000, min=0, max=1) y <- x + rnorm(1000, mean=0, sd=1)*x^(3/4) vf <- function(mu) { abs(mu)^(3/4) } vm <...

...v = linkinv, mu.eta = mu.eta, valideta = valideta, name = link), class = "link-glm") } # Modified binomial family function (that allows logexp link function) logexposure<-function (link="logexp",ExposureDays) { variance <- function(mu) mu * (1 - mu) validmu <- function(mu) all(mu > 0) && all(mu < 1) dev.resids <- function(y, mu, wt) .Call("binomial_dev_resids", y, mu, wt, PACKAGE = "stats") aic <- function(y, n, mu, wt, dev) { m <- if (any(n > 1)) n else wt...

This is not so much a bug as an infelicity in the code that can easily be fixed. The initialize expression in the quasi family function is, (uniformly for all links and all variance functions): initialize <- expression({ n <- rep.int(1, nobs) mustart <- y + 0.1 * (y == 0) }) This is inappropriate (and often fails) for variance function "mu(1-mu)".

...git.deriv=function(eta) .5*(exp(eta/2)+exp(-eta/2))^-2 half.logit.inv.indicator=function(eta) TRUE half.logit.indicator=function(mu) mu>.5 & mu<1 link <- "half.logit" structure(list(linkfun = half.logit, linkinv = half.logit.inv, mu.eta = half.logit.deriv, validmu = half.logit.indicator ,valideta = half.logit.inv.indicator, name = link), class = "link-glm") } binomial(halflogit()) Family: binomial Link function: half.logit ############################# I based this off the help for the family() function. So I try to call glmmPQL...

...distribution. However, I want to use an overdispersion parameter that varies (dependent on the length of a stretch of road) so glm.nb will not do. >From what I've read I should be able to do this using GLM by specifying my own quasi family and describing the variance function using varfun, validmu, dev.resids and initiate. However I cannot find any detailed discussion of this method. Any help would be appreciated. ps I've done this in SAS so I know it should be possible! Craig

Dear R users I have been looking for functions that can deal with overdispersed poisson models. Some (one) of the observations are negative. According to actuarial literature (England & Verall, Stochastic Claims Reserving in General Insurance , Institute of Actiuaries 2002) this can be handled through the use of quasi likelihoods instead of normal likelihoods. The presence of negatives is not

...git.deriv=function(eta) .5*(exp(eta/2)+exp(-eta/2))^-2 half.logit.inv.indicator=function(eta) TRUE half.logit.indicator=function(mu) mu>.5 & mu<1 link <- "half.logit" structure(list(linkfun = half.logit, linkinv = half.logit.inv, ??????????????????? mu.eta = half.logit.deriv, validmu = half.logit.indicator ,valideta = half.logit.inv.indicator, name = link), ?????????????? class = "link-glm") } # submit halflogit function to lmer rcNrPSrcNxPSxP<-lmer(Correct~-1+cNoise*f_Pos+f_Shape_con+f_Shape_con:f_Pos+(-1+cNoise*f_Pos|f_Subject), data=dens_data, family=binomial(ha...

...and R have many different features, for example: In R: > names(Gamma()) [1] "family" "link" "linkfun" "linkinv" "variance" [6] "dev.resids" "aic" "mu.eta" "initialize" "validmu" [11] "valideta" In S-Plus: > names(Gamma()) [1] "family" "names" "link" "inverse" "deriv" [6] "initialize" "variance" "deviance" "weight" > My question concerns...

I apologize for my earlier posting that, unbeknownst to me before, apparently was not in the correct format for this list. Hopefully this attempt will go through, and no-one will hold the newbie mistake against me. I could really use some help in writing a new glm link function in order to run an analysis of daily nest survival rates. I've struggled with this for weeks now, and can at least

...ferentiation data based on quasi-likelihoods" between variance = phi*mu (quasi-Poisson), variance = phi*mu^2 (quasi-exponential), and variance = mu+theta*mu^2. The "quasi" function accepted for the family argument in "glm" generates functions "variance", "validmu", and "dev.resids". I can probably write functions to mimic the "quasi" function. However, I have two questions in regard to this: (1) I don't know what to use for "dev.resids". This may not matter for fitting. I can try a couple of different thing...

Hi, I'm tying to fit a glm using quasi with variance=mu(1-mu) (to try and get "well behaved" residuals). I get an error message: "cannot find valid starting values, please specify some". I have tried using start= and specifying coefficients from a previous fit (with different error structure) but get the same message. What would be valid starting values? I am using a

...uasi family will accept the literal character string (or unquoted as a name/expression) specifications "constant", "mu(1-mu)", "mu", "mu^2" and "mu^3", a length-one character vector taking one of those values, or a list containing components varfun, validmu, dev.resids, initialize and name. Thanks very much. -- With Kind Regards, oooO::::::::: (..)::::::::: :\.(:::Oooo:: ::\_)::(..):: :::::::)./::: ::::::(_/:::: ::::::::::::: [***********************************************************************] Zhi Jie,Zhang ,PHD Tel:86-21-54237149 Dept. of Epi...

Dear list, I have recently encountered an odd error when running glm(dep~indep, quasipoisson): while, with a subset of my data, I could get a perfectly reasonable model, once I include all of my data (17K+ observations, 29 variables), I get the following error: Error in if (any(y < 0)) stop("negative values not allowed for the quasiPoisson family") : missing value where

...0, 0, y[, 1]/n) weights <- weights * n mustart <- (n * y + 0.5)/(n + 1) } else stop("for the binomial family, y must be a vector of 0 and 1's\n", "or a 2 column matrix where col 1 is no. successes and col 2 is no. failures") }) .. ..$ validmu :function (mu) .. ..$ valideta :function (eta) .. ..$ simulate :function (object, nsim) .. ..- attr(*, "class")= chr "family" ..$ linear.predictors: Named num [1:1615] -2.162 -0.87 -1.485 -2.656 -0.818 ... .. ..- attr(*, "names")= chr [1:1615] &quot...