search for: lambda3

...mbda1*(10^a)-lambda2*(14^a-10^a+14^a-14^a)) -exp(-lambda1*(10^a)-lambda2*(14^a-10^a+18^a-14^a))) logl<-log(s1_f1*s2_f2) return(-logl)} optim(1,L) alpha<-optim(1,L)$par } [II] for 1)-3) (making errors) alpha[1]<-1 beta0=rep(0,10) beta1=rep(0,10) lambda1=rep(0,10) lambda2=rep(0,10) lambda3=rep(0,10) lambda4=rep(0,10) verpi=rep(0,10) s1_f1=rep(0,10) s2_f2=rep(0,10) a=rep(0,10) logl=rep(0,10) beta0[1]=0 beta1[1]=0 lambda1[1]=0 lambda2[1]=0 lambda3[1]=0 lambda4[1]=0 verpi[1]=0 s1_f1[1]=0 s2_f2[1]=0 a[1]=1 logl[1]=0 for(i in 2:11){ verpi[i]<-c(5^alpha[i-1],10^alpha[i-1]-5^alpha[i-1],1...

...m likelihood based on the example given in MASS. So far I had much success in fitting two components. The problem started when I tried to extend the procedure to fit three components. More specifically, likelihood = sum( ln(c1*exp(-x/lambda1)/lambda1 + c2*exp(-x/lambda2)/lambda2 + (1-c1-c2)*exp(-x/lambda3)/lambda3) ) I've used optimizers such as ms and nlminb (SPLUS 5.0 for UNIX), and provided parameters constrains (0 <= c1, c2 <= 1) to nlminb via lower and upper. But these constrains provide no protection for (1-c1-c2) being between interval [0,1], which resulted in generating NAs in the...

Hey all, I am trying to work under a State Space form, but I didn't get the help exactly. Have anyone eles used this functions? I was used to work with S-PLUS, but I have some codes I need to adpt. Thanks alot, Bernardo [[alternative HTML version deleted]]

...e example given in >MASS. So far I had much success in fitting two components. The problem >started when I tried to extend the procedure to fit three components. >More specifically, > >likelihood = sum( ln(c1*exp(-x/lambda1)/lambda1 + >c2*exp(-x/lambda2)/lambda2 + (1-c1-c2)*exp(-x/lambda3)/lambda3) ) > >I've used optimizers such as ms and nlminb (SPLUS 5.0 for UNIX), and >provided parameters constrains (0 <= c1, c2 <= 1) to nlminb via lower and >upper. But these constrains provide no protection for (1-c1-c2) being >between interval [0,1], which resulted in g...

...2.1,3.1,100.1,1.1,2.1,3.1,100.1,1.1,2.1,3.1,100.1) b = c(1.1,1.1,1.1,100.1,1.1,1.1,1.1,100.1,1.1,1.1,1.,100.1,1.1,1.1,1.1,100.1,1.1,1.1,1.1,100.1,1.1,1.1,1.,100.1) K <-ts(cbind(a,b),start=c(1.1,1.1), names=c("a","b")) fit.bvar <- szbvar(K, p = 1, lambda0=0.6, lambda=0.1, lambda3=2, lambda4=0.25,lambda5=0,mu5=0, mu6=0, prior=0) y <- matrix(c(rep(0,8),c(1.10,1.10,1.10,100.1,1.10,1.10,1.0,100.10)),ncol=2) h <- hc.forecast(fit.bvar,y,nsteps=8,burnin=300, gibbs=500,exog=NULL)

...ead(states) #match states to tree states<-structure(states$PC, names=states$Species) names(states)<-tree$tip.label #MuSSE diversitree:::argnames.musse(NULL, 3) #number of states lik<-make.musse(tree, states, 3) argnames(lik) #contstrain lambda lik.base<-constrain(lik, lambda2~lambda1, lambda3~lambda1, mu2~mu1,mu3~mu1,q13~q12,q21~q12,q23~q12,q31~q12,q32~q12) #find ML point for this model p<-starting.point.musse(tree, 3) fit.base<-find.mle(lik.base, p[argnames(lik.base)]) #unconstrained lik.lambda<-constrain(lik,mu2~mu1,mu3~mu1,q13~q12,q21~q12,q23~q12,q31~q12,q32~q12) fit.lambda...

Hi Mehdi, > Side question on the related work because I’m curious: did you look for similar generic scheme for error handling offered by other C++ libraries? Maybe the common scheme is to use C++ exceptions but since many folks disable them (hello Google ;-) ) there has been probably many other attempts to address this. I did look around, but not very hard. Among the people I asked, everyone