similar to: Using MLE Method to Estimate Regression Coefficients

Hello, I'm using optim to program a set of mle regression procedures for non-normal disturbances. This is for teaching and expository purposes only. I've successfully programmed the normal, generalized gamma, gamma, weibull, exponential, and lognormal regression functions. And optim returns reasonable answers for all of these compared with the identical optimization problems in STATA and

I have had some weird results using the optim() function. I wrote a probit likelihood and wanted to run it with optim() with simulated data. I did not include a gradient at first and found that optim() would not even iterate using BFGS and would only occasionally work using SANN. I programmed in the gradient and it iterates fine but the estimates it returns are wrong. The simulated data work

Hello, I am having trouble using "optim". I want to maximalise a function to its parameters [kind of like: univariate maximum likelihood estimation, but i wrote the likelihood function myself because of data issues ] When I try to optimize a function for only one parameter there is no problem: llik.expo<-function(x,lam){(length(x)*log(lam))-(length(x)*log(1-exp(-1*lam*

Hi May you help me correct my loop function. I want optim to estimates al_j; au_j; sigma_j; b_j by looking at 0 to 20, 21 to 40, 41 to 60 data points. The final result should have 4 columns of each of the estimates AND 4 rows of each of 0 to 20, 21 to 40, 41 to 60. ###MY code is n=20 runs=4 out=matrix(0,nrow=runs) llik = function(x) { al_j=x[1]; au_j=x[2]; sigma_j=x[3]; b_j=x[4]

Hi I am estimating the following coxph function with stratification and frailty?where each person had multiple events. m<-coxph(Surv(dtime1,status1)~gender+cage+uplf+strata(enum)+frailty(id),xmodel) ? > head(xmodel) id enum dtime status gender cage uplf 1 1008666 1 2259.1412037 1 MA 0.000 0 2 1008666 2 36.7495023 1 MA 2259.141 0 3 1008666

I wrote this: # Setup problem x <- runif(100) y <- 2 + 3*x + rnorm(100) X <- cbind(1, x) # True OLS -- lm(y ~ x) # OLS likelihood function -- ols.lf <- function(theta, K, y, X) { beta <- theta[1:K] sigma <- exp(theta[K+1]) e <- (y - X%*%beta)/sigma logl <- sum(log(dnorm(e))) return(logl) } optim(c(2,3,0), ols.lf, gr=NULL, method="BFGS",

Hi I need help figure out how to fix my code. When I call into R >optimize(llik,init.params=F) I get this error message ####Error in optimize(llik, init.params = F) : element 1 is empty; the part of the args list of 'min' being evaluated was: (interval)#### My data and my code looks like below. R_j R_m 0.002 0.026567296 0.01 0.003194435 . . . . . . . . 0.0006

As part of carrying out a complicated maximum likelihood estimation, I am trying to learn to program likelihoods in R. I started with a simple probit model but am unable to get the code to work. Any help or suggestions are most welcome. I give my code below: ************************************ mlogl <- function(mu, y, X) { n <- nrow(X) zeta <- X%*%mu llik <- 0 for (i in 1:n) { if

Thanks to Gabor for setting me right. My code is as follows. I found it useful for learning optim(), and you might find it similarly useful. I will be most grateful if you can guide me on how to do this better. Should one be using optim() or stats4::mle? set.seed(101) # For replicability # Setup problem X <- cbind(1, runif(100)) theta.true <- c(2,3,1) y <- X

Dear Friends, My problem is related to how to measure probabilities from a probit model by changing one independent variable keeping the others constant. A simple toy example is like this Range for my variables is defined as follows y=0 or 1, x1 = -10 to 10, x2=-40 to 100, x3 = -5 to 5 Model output <- glim(y ~ x1+x2+x3 -1, family=binomial(link="probit")) outcoef <-

Hi I have developed the code below. I am worried that the parameters I want to be estimated are "not being found" when I ran my code. Is there a way I can code them so that R recognize that they should be estimated. This is the error I am getting. > out1=optim(llik,par=start.par) Error in pnorm(au_j, mean = b_j * R_m, sd = sigma_j) : object 'au_j' not found #Yet

Dear R-help, I'm using the 'optim' functions to minimise functions, and have read the documentation, but I'm still not sure how to determine sensible values to use for the 'fnscale' and 'parscale' options. If I have understood everything correctly, 'fnscale' should be used to scale the objective function, so that for example if the default is

Hi I have a code that calculate maximisation using optimx and it is working just fine. I want to extend the code to run several colomns of R_j where j runs from 1 to 200. If I am to run the code in its current state, it means I will have to run it 200 times manually. May you help me adjust it to accomodate several rows of R_j and print the 200 results. ***Please do not get intimidated by the

Dear R users, I am trying to figure out the control parameter in "optim," especially, "fnscale" and "parscale." In the R docu., ------------------------------------------------------ fnscale An overall scaling to be applied to the value of fn and gr during optimization. If negative, turns the problem into a maximization problem. Optimization is performed on

Hello, the more general thing I'd like to learn here is how to compute Function of Data on the basis of grouping determiend by n variables. In terms of the reason why I am interested in this, I need to compute the average of my data based on the value of the month and day across years. I have come up withy the code below which, as far as I can see, does what I need but getting either a more

?optim says, in describing the control parameter, 'fnscale' An overall scaling to be applied to the value of 'fn' and 'gr' during optimization. If negative, turns the problem into a maximization problem. Optimization is performed on 'fn(par)/fnscale'. 'parscale' A vector of scaling values for the parameters.

Hello, I've just a little problem using the function optim. Here is the function I want to optimize : test_function(x){(exp(-0.06751 + 0.25473*((x[1]-350)/150) + 0.04455*((x[2]-40)/20) + 0.09399*((x[3]-400)/100) - 0.17238*((x[4]-250)/50)- 0.45984*((x[5]-550)/150)-0.39508*((x[1]-350)/150)* ((x[1]-350)/150) - 0.05116*((x[2]-40)/20)* ((x[2]-40)/20) - 0.27735*((x[3]-400)/100)*((x[3]-400)/100) -

In trying to streamline various optimization functions, I would like to have a scratch pad of working data that is shared across a number of functions. These can be called from different levels within some wrapper functions for maximum likelihood and other such computations. I'm sure there are other applications that could benefit from this. Below are two approaches. One uses the <<-

I am trying to figure out how to run maximum likelihood in R. Here is my situation: I have the following equation: equation<-(1/LR-(exp(-k*T)*LM)*(1-exp(-k))) LR, T, and LM are vectors of data. I want to R to change the value of k to maximize the value of equation. My attempts at optim and optimize have been unsuccessful. Are these the recommended functions that I should use to maximize

I'm trying to calculate the maximum likelihood estimate for a binomial distribution. Here is my code: y <- c(2, 4, 2, 4, 5, 3) n <- length(y) binomial.ll <- function (pi, y, n) { ## define log-likelihood output <- y*log(pi)+(n-y)*(log(1-pi)) return(output) } binomial.mle <- optim(0.01, ## starting value binomial.ll,