similar to: Multivariate Maximum Likelihood Estimation

Dear R experts/ users Full Information Maximum Likelihood (FIML) estimation approach is considered robust over Seemingly Unrelated Regression (SUR) approach for analysing data of multivariate sample selection problem. The zero cases in my dependent variables are resulted from three sources: Irreverent options, not choosing due to negative utility and not used in the reported time. FIML can

Hi Everyone, I am trying to do a time series regression using the lm function. However, according to the durbin watson test the errors are autocorrelated. And then I tried to use the gls function to accomodate for the autocorrelated errors. My question is how do I know what ARMA process (order) to use in the gls function? Or is there any other way to do the time series regression in R? I highly

Hi, I'm preetty new to R and seem to be having difficulties with writing a function that would change an array and keep the change after the function finishes its work. in other words I have an array of 1's X<-array(1,dim=c(2,2)) I want to add a number to X[1,1] by means of a function called addition. What I am writing is: addition<-function(a){X[1,1]=X[1,1}+a} but it

Could someone tell me how to access the log likelihood of a poisson model? I've done the following.... <BEGIN R STUFF> freq.mod <- glm(formula = nfix ~ gls.gls + pol.gls + pol.rel + rac.gls + rac.pol + rac.rac + rac.rel + white + gls.gls.w + pol.gls.w + pol.rel.w + rac.gls.w + rac.pol.w + rac.rac.w + rac.rac.w + rac.rel.w, family = poisson, data = Complex2.freq, offset = lnoffset)

Hello, I would like to get the likelihood ratio and score tests for specific variables in a multivariate coxph model. The default is Wald, so the tests for each separate variable is based on Wald's test. I have the other tests for the full model but I don't know how to get them for each variable. Any idea? David Biau. [[alternative HTML version deleted]]

Hello, I have a bigger problem in calculating the Maximum Likelihood Estimator regarding the degree of freedom of a multivariate skew-t copula. First of all I would like to describe what this is all about, so that you can understand my problem: I have 2 time series with more than 3000 entries each. I would like to calculate a multivariate skew-t Copula that fits this time series. Notice:

Hi, I have fitted a model using a glm() approach and using a gls() approach (but without correcting for spatially autocorrelated errors). I have noticed that although these models are the same (as they should be), the AIC value differs between glm() and gls(). Can anyone tell me why they differ? Thanks, Geertje ~~~~ Geertje van der Heijden PhD student Tropical Ecology School of Geography

Hi, I am using 2 times series and I want to carry out a regression of Seri1 by Serie2 using structured (autocorrelated) errors. (Equivalent to the autoreg function in SAS) I found the function gls (package nlme) and I made: gls_mens<-gls(mening_s_des~dataATB, correlation = corAR1()) My problem is that I don’t want a AR(1) structure but ARMA(n,p) but the execution fails :

Hi there, I am using gls from the nlme library to fit an AR(1) regression model. I am wondering if (and how) I can separate the auto-correlated and random components of the residuals? Id like to be able to plot the fitted values + the autocorrelated error (i.e. phi * resid(t-1)), to compare with the observed values. I am also wondering how I might go about calculating confidence (or

Dear R users, In my data, there are two variables t1 and t2. For each observation of t1 and t2, two location indicators (x, y) were provided. The data format is # x y t1 t2 Since the both t1 and t2 are depended on x and y, t1 and t2 are autocorrelated variables. My question is how to calculate the correlation between t1 and t2 by taking into account the structure of residual variance

Hi, I have two sets of data for a given set of (non-lattice) locations. I would like to know whether the two are significantly different. This would be simple enough if it wasn't for the fact that the data is spatially autocorrelated. I have come across several possible solutions (including Cliff & Ord which however appears to be for gridded data), or using gls. However, they don't

Hi, Suppose I have a multivariate response Y (n x k) obtained at a set of predictors X (n x p). I would like to perform a linear regression taking into consideration the covariance structure of Y within each unit - this would be represented by a specified matrix V (k x k), assumed to be the same across units. How do I use "lm" to do this? One approach that I was thinking of

Hello, I'm trying to calculate the Maximum likelihood estimators for a dataset which contains censored data. I started by using the function "nlm", but isn't there a separate method for doing this for e.g. the "weibull" and the "log-normal" distribution? Thanks, Olivia [[alternative HTML version deleted]]

I'm trying to estimate the parameters for GARCH(1,1) process. Here's my code: loglikelihood <-function(theta) { h=((r[1]-theta[1])^2) p=0 for (t in 2:length(r)) { h=c(h,theta[2]+theta[3]*((r[t-1]-theta[1])^2)+theta[4]*h[t-1]) p=c(p,dnorm(r[t],theta[1],sqrt(h[t]),log=TRUE)) } -sum(p) } Then I use nlminb to minimize the function loglikelihood: nlminb(

Hello, Has anyone written up code to estimate for example a simple logit using quasi-likelihood? I know that glm() already does this, but I'd like to do some tinkering with the variance function beyond what glm() allows. I've scanned online sources and everyone seems to use glm(). Will take a crack at it if necessary but have zero experience w/q-likelihood and not that much with

Have a look at ?optim. I don't think it has the BHHH algorithm as an option, though. =========================================== David Barron Jesus College University of Oxford -----Original Message----- From: r-help-bounces at stat.math.ethz.ch [mailto:r-help-bounces at stat.math.ethz.ch]On Behalf Of Harold Doran Sent: 10 July 2003 15:43 To: Fohr, Marc [AM]; R-help at stat.math.ethz.ch

Hi, I have a quick question regarding estimation of a truncation regression model (truncated above at 1) using MLE in R. I will be most grateful to you if you can help me out. The model is linear and the relationship is "dhat = bhat0+Z*bhat+e", where dhat is the dependent variable >0 and upper truncated at 1; bhat0 is the intercept; Z is the independent variable and is a uniform

Hi all, I am trying to build a copula model using the Gumbel Copula and I have two marginal distributions.I know the marginal parameters by using the fitdistr() and optim().The problem is I dont know my copula parameter. I am getting a bit confused of how shall I go about it.I read the previous threads where the query was to estimate all the parameters.How shall I define my log-likelihood

Dear R users >From what I understand, the joint maximum likelihood procedure for Rasch (availabe in the package MiscPsycho) in R can only be used on binary data. I was wondering if the code is currently being adapted for application to ordinal data? I'm trying to replicate results obtained from Winsteps in R. Best wishes denn -- View this message in context:

Hi, I want to use Maximum likelihood to estimate the parameters from my regression line. I have purchased the book "Applied linear statistical models" from Neter, Kutner, nachtsheim & Wasserman, and in one of the first chapters, they use maximum likelihood to estimate the parameters. Now I want to tried it for my self, but couldn't find the right function. In the book, they give