Hello! I am a statistics graduate student and a new user of R. I am using nlm function to get estimates from a nonlinear function. I am running a simulation program. When I run the simulation with same set of starting vales then one third of the time I get bad results and I also noticed that I get good results corresponding to convergence code "2". So my question is that is there any way that I can make sure that everytime I use the nlm function, I can achieve the right convergence ie. successive iterates within tolerance, current iterate is probably solution (code=2). any help in this regard will be much appreciated. Thanks! Lovely Goyal Graduate Student Department of Statistics NCSU. --------------------------------- [[alternative HTML version deleted]]
Hello! I am a statistics graduate student and a new user of R. I am using nlm function to get estimates from a nonlinear function. I am running a simulation program. When I run the simulation with same set of starting vales then one third of the time I get bad results and I also noticed that I get good results corresponding to convergence code "2". So my question is that is there any way that I can make sure that everytime I use the nlm function, I can achieve the right convergence ie. successive iterates within tolerance, current iterate is probably solution (code=2). any help in this regard will be much appreciated. Thanks! Lovely Goyal Graduate Student Department of Statistics NCSU. --------------------------------- [[alternative HTML version deleted]]