similar to: do_optimhess vs. fdHess ...

Your question is better addressed to the R-help@R-project.org mailing list, which I am copying on this reply. You are confusing a statistical concept, the Fisher Information matrix, with a numerical concept, the Hessian matrix of a scalar function of a vector argument. The Fisher information matrix is the Hessian matrix of a particular function at its optimum and I have forgotten whether that

I have constructed the function mml2 (below) based on the likelihood function described in the minimal latex I have pasted below for anyone who wants to look at it. This function finds parameter estimates for a basic Rasch (IRT) model. Using the function without the gradient, using either nlminb or optim returns the correct parameter estimates and, in the case of optim, the correct standard

GENERAL REFERENCE ON NONLINEAR OPTIMIZATION? What are your favorite references on nonlinear optimization? I like Bates and Watts (1988) Nonlinear Regression Analysis and Its Applications (Wiley), especially for its key insights regarding parameter effects vs. intrinsic curvature. Before I spent time and money on several of the refences cited on the help pages for "optim",

Hello splus-users, I am trying to fit a regression model for an ordered response factor. So I am using the function polr in library(MASS). My data is a matrix of 1665 rows and 63 columns (one of the column is the dependent variable). The code I use is polr(as.ordered(q23p)~.,data=newdatap) but I am getting the following warning message singularity encountered in: nlminb.1(temp, p, liv, lv,

Hi all, I would like to use optim() to estimate the equation by the log-likelihood function and gradient function which I had written. I try to use OPG(Out Product of Gradient) to calculate the Hessian matrix since sometime Hessian matrix is difficult to calculate. Thus I want to pick the Gradient matrix from the gradient function. Moreover, could R show the process of calculation on gradient

Dear all, There appears to be a bug in how constrOptim handles ... arguments that are suppose to be passed to optim, according to the documentation. This means you can't get the hessian to be returned, for example (so this is a real problem, and not just a question of mistaken documentation). Looking at the code, it appears that a call to the user-defined f includes the ..., when the ...

In the course of revising a paper I have had occasion to attempt to maximize a rather complicated log likelihood using the function nlm(). This is at the demand of a referee who claims that this will work better than my proposed use of a home- grown implementation of the Levenberg-Marquardt algorithm. I have run into serious hiccups in attempting to apply nlm(). If I provide gradient and

I've been working on a new package and I have a few questions regarding the behaviour of the nlm function. I've been (for better or worse) using the nlm function to fit a linear model without suppling the hessian or gradient attributes in the objective function. I'm curious as to why the nlm requires 31 iterations (for the linear model), and then it doesn't work when I try to add

Hello, I'm fitting a series of ARIMA models to a data set to compare fits. After taking the logs of the data and then differencing them to induce stationarity, I execute arima( y, order=c( p, 0, q ), seasonal=list( order=c( P, 0, Q ), period=7 ) ) for various values of p, q, P and Q. For one set of these values, I get Error in optim(init[mask], armafn, method = "BFGS", hessian

Hi, All: What tools exist for diagnosing singular gradient problems with 'nls'? Consider the following toy example: DF1 <- data.frame(y=1:9, one=rep(1,9)) nlsToyProblem <- nls(y~(a+2*b)*one, DF1, start=list(a=1, b=1), control=nls.control(warnOnly=TRUE)) Error in nlsModel(formula, mf, start, wts) : singular gradient matrix at initial

I've been trying to figure out how to build a list of terms from a nonlinear model (terms() returns a error). I need to compute and evaluate the partial derivatives (Jacobian) for each equaiton in a set of equations. For example: > eqn <- q ~ s0 + s1 * p + s2 * f + s3 * a > sv2 <- c(d0=3,d1=4.234,d2=4,s0=-2.123,s1=0.234,s2=2.123,s3=4.234) > names( sv2 ) [1] "d0"

Dear All, I am running a simulation to obtain coverage probability of Wald type confidence intervals for my parameter d in a function of two parameters (mu,d). I am optimizing it using "optim" method "L-BFGS-B" to obtain MLE. As, I want to invert the Hessian matrix to get Standard errors of the two parameter estimates. However, my Hessian matrix at times becomes

I have a function that I am currently using very inefficiently. The following are needed to illustrate the problem: set.seed(12345) dat <- matrix(sample(c(0,1), 110, replace = TRUE), nrow = 11, ncol=10) mis <- sample(1:110, 5) dat[mis] <- NA theta <- rnorm(11) b_vector <- runif(10, -4,4) empty <- which(is.na(t(dat))) So, I have a matrix (dat) with some values within the matrix

Hello RUser! I try to use ace for an ancestral state reconstruction but got back an error message. ace(FacVar,Tree, type="discrete") Warning messages: 1: In nlm(function(p) dev(p), p = rep(ip, length.out = np), hessian = TRUE) : NA/Inf durch gr??te positive Zahl ersetzt (NA/Inf replaced by positive number) 2: In nlm(function(p) dev(p), p = rep(ip, length.out = np), hessian

Dear R users, I have looked in the reference Schnabel, R. B., Koontz, J. E. and Weiss, B. E. (1985) A modular system of algorithms for unconstrained minimization. _ACM Trans. Math. Software_, *11*, 419-440. cited in the nlm help. This article says that the algorithm permits the use of step selection (line search, dogleg and optimal step), analytic or finite diference gradient

Dear all I want to compute Monte Carlo p-values in lmer-models based on sampled data sets. To speed up calculations, I've tried to use internal functions from the Matrix package (as suggested ealier on the list by Doug Bates). So I did: fm2 <- lmer(resistance ~ ET + position + (1|Grp), Semiconductor,method='ML') simdata<-simulate(fm2,nsim=1) ynew <- simdata[,1] mer

Out of curiosity, I have tried, without success, to use the new facility in nlm to specify the gradient and hessian. (It is many years since I had a problem simple enough to make analytic derivation of these worthwhile.) The help now says that the function must have attributes with these names but gives no indication as to what should be in the attributes. The online example and demo do not use

Hello: Below is a toy logistic regression problem. When I wrote my own code, Newton-Raphson converged in three iterations using both the gradient and the Hessian and the starting values given below. But I can't get nlm() to work! I would much appreciate any help. > x [1] 10.2 7.7 5.1 3.8 2.6 > y [1] 9 8 3 2 1 > n [1] 10 9 6 8 10 derfs4=function(b,x,y,n) {

Hi all, I'm adjusting a nonlinear regression model for data that has a categorigal variable present. So, I can use nls() to do this considering the categorical variable, like this #------------------------------------------------------------ da <- expand.grid(tr=gl(2,1,la=c("tr")), x=1:12) da$y <- 10*da$x/(3+da$x)+rnorm(da$x,0,0.1) plot(y~x, da) n0 <-

Hi, I have a scalar valued function with several variables. One of the variables is restricted to be non-negative. For example, f(x,y)=sqrt(x)*exp(y), then x should be non-negative. I need the gradient and hessian for some vector (0,y), i.e., I need the gradient and hessian at the boudary of parameter space. The "numderiv" package does not work, even for f(x)=sqrt(x), if you do