search for: rel_reduction_of_f

...used the method, L-BFGS-B, in OPTIM, I've got the following message. --------------------------------------------------------------------- $par [1] 0.176166426835580 $value [1] 1322.17600079332 $counts function gradient 8 8 $convergence [1] 0 $message [1] "CONVERGENCE: REL_REDUCTION_OF_F <= FACTR*EPSMCH" $hessian [,1] [1,] 46300.3853279247 --------------------------------------------------------------------- First, what does that message, "CONVERGENCE: REL_REDUCTION_OF_F <= FACTR*EPSMCH", mean? and I am wondering if the estimates are relia...

hi all i dont understand the error message that is produced by the optim function. can anybody help??? ie: [[1]]$message [1] "CONVERGENCE: REL_REDUCTION_OF_F <= FACTR*EPSMCH" can anyone help? ########################################################################### SK.FIT(XDATA=a,XDATAname="a",PHI1=1,v=5,vlo=2,vhi=300,phi2lo=.01) [[1]] [[1]]$par [1] -0.01377906 0.83859445 0.34675230 300.00000000 [[1]]$value [1] 90.59185 [...

...grad, data=Data1, method="L-BFGS-B", lower=rep(0, 3), upper=rep(1, 3)) D1.unbound $par c1 c2 c3 0.004387706 0.203562156 0.300825550 $value [1] 0.07811152 $counts function gradient 8 8 $convergence [1] 0 $message [1] "CONVERGENCE: REL_REDUCTION_OF_F <= FACTR*EPSMCH" Any suggestion on how to fix the error "CONVERGENCE: REL_REDUCTION_OF_F <= FACTR*EPSMCH"? [[alternative HTML version deleted]]

...and the algorithm continues the minimisation. It stops and gives a (-log(likelihood))=6104.45, with the messages: "there are 50 or more warnings" ( warnings() = "multi-arguments returns are deprecated" in a function used by the program) $convergence=0 $message= CONVERGENCE:REL_REDUCTION_OF_F <= FACTR*EPSMCH What does it mean? Is the convergence reached? What can it be concluded from these two steps? Thank you very much for your advices and help.

...;,lower=c(0.001, 0.001) ,upper = rep(Inf, 2), hessian=TRUE, control=list(trace=1)) iter 0 value 3.011784 final value 2.802694 converged $par [1] 4.6597779 0.3860387 $value [1] 2.802694 $counts function gradient 17 17 $convergence [1] 0 $message [1] "CONVERGENCE: REL_REDUCTION_OF_F <= FACTR*EPSMCH" WHich gives an estimate of stDev = 0.38 while the empirical stDev = 1.94 Is there anything wrong above in the code? Thanks in advance

...=1)) which gives: $par Winf k t0 b sigma [1] 24.27206813 0.04679844 0.00100000 1.61760492 0.01000000 $value [1] -11.69524 $counts function gradient 143 143 $convergence [1] 0 $message [1] "CONVERGENCE: REL_REDUCTION_OF_F <= FACTR*EPSMCH" $hessian [,1] [,2] [,3] [,4] [,5] [1,] 1.867150e+00 1.262763e+03 -7.857719 -5.153276e+01 -1.492850e-05 [2,] 1.262763e+03 8.608461e+05 -5512.469266 -3.562137e+04 9.693180e-05 [3,] -7.857719e+00 -5.512469e+03 41.670...

...a previous optim() call and using these as starting values in the next function call. The final call to optim() returns the following: $par [1] 0.2272361 0.8037642 26.8591998 3.0631280 0.2224566 $value [1] -46.13906 $counts function gradient 4 4 $convergence [1] 0 $message [1] "CONVERGENCE: REL_REDUCTION_OF_F <= FACTR*EPSMCH" $hessian [,1] [,2] [,3] [,4] [,5] [1,] 1.267070e+17 1.012691e+17 1.348054e+15 625551.58724 9.359559e+07 [2,] 1.012691e+17 8.189877e+16 1.144248e+15 569562.44945 8.699072e+07 [3,] 1.348054e+15 1.144248e+15 2.457323e+05 3426.60293 -2.297009e+03 [4,] 6.255516e+05 5.695624e+05...

...experimentalPI=3.48, lambda = lambda) The output is: $par [1] 0.56350964 0.56350964 0.56350964 0.56350964 0.00000000 -0.29515957 [7] 0.00569937 0.32543297 0.18615880 $value [1] 0.2529198 $counts function gradient 31 31 $convergence [1] 0 $message [1] "CONVERGENCE: REL_REDUCTION_OF_F <= FACTR*EPSMCH" Warning messages: 1: bounds can only be used with method L-BFGS-B in: optim(par, errorFunction, gr = NULL, method = "Nelder-Mead", 2: NAs introduced by coercion If I change my "error-function" to errorFunction <- function(localShifts,globalShif...

....70595 Eval fn at 0.699 10.3 8.5 --- Val = 42.70603 ... Eval fn at 0.7425713 21.12820 0.001 --- Val = 64.99 Eval fn at 0.7425713 21.12920 0.002 --- Val = 60.20449 Eval fn at 0.7425713 21.12920 0.001 --- Val = 64.99 > o$val [1] 64.99 > o$convergence [1] 0 > o$message [1] "CONVERGENCE: REL_REDUCTION_OF_F <= FACTR*EPSMCH" So optim thinks it has found an optimum (i.e. minimum). But my initial guess is better than optim's answer; and optim has visited many points which are better than its final answer. If I choose a different initial guess, like c(.7,10.3,1), optim reaches the answer I e...

....267 > > lik.t.cen.log $par [1] 0.007369536 0.032623958 1.025064715 0.315420992 0.288083186 0.008728551 [7] 1.016895527 0.978822785 0.552299864 1.016390800 0.000100000 $value [1] -1697.267 $counts function gradient 50 50 $convergence [1] 0 $message [1] "CONVERGENCE: REL_REDUCTION_OF_F <= FACTR*EPSMCH" ########### Here ``likeli.time.log'' and ``gradient.time.log'' are functions, ``temp.censor'' is a list with input variables for the two functions (data, fixed parameters, etc.), and the parameter space is of dimension 11. Note that value returne...

...h the same data, it works fine: > optRes <- optim(c(0,0), method="L-BFGS-B", fn=IRT.llZetaLambdaCorrNan, + gr=IRT.gradZL, + lower=c(-Inf, -Inf), upper=c(Inf, Inf), t=st, X=sx) > optRes $par [1] -0.6975157 0.7944972 $convergence [1] 0 $message [1] "CONVERGENCE: REL_REDUCTION_OF_F <= FACTR*EPSMCH" Does anyone have an idea what this could be, and what I could try to avoid this error? I tried bounding the parameters, with lower=c(-10, -10) and upper=... but that made no difference. Thanks, Diederik Roijers Utrecht University MSc student. ------ PS: the other funct...

...1274840 [1] 5106.236 $par: [1] 0.77012134 4.34425988 0.14248754 0.30722383 0.12748400 [6] 0.48420116 0.00000000 0.02095689 0.00000000 0.61156935 [11] 0.77179635 0.00000000 $value: [1] 5106.049 $counts: function gradient 21 21 $convergence: [1] 0 $message: [1] "CONVERGENCE: REL_REDUCTION_OF_F <= FACTR*EPSMCH" I tried the 'bad' parameters in S-plus: > likelihood(par=rep(0,12),data=data03) #It is NA. [1] NA > likelihood(data=data03) #It is normal again. [1] 5834.421 Thank you very much for your time! ########################################### This m...

...0.41936338 Agriculture 0.49205978 Examination 0.26976286 Education 0.00050000 Catholic 0.06973751 Infant.Mortality 0.96007318 $value [1] 0.5008949 $counts function gradient 22 22 $convergence [1] 0 $message [1] "CONVERGENCE: REL_REDUCTION_OF_F <= FACTR*EPSMCH" I have never seen that particular failure message from `optim` before, "NEW_X", and I cannot locate what it means. It is possible, if not probably, that it has to do with one of the functions internal to `factanal.fit.mle`, possibly the call to `eigen` as I presu...

...7 1.519658195 1.378913148 2.800328223 1.448902455 2.280837645 [15] 1.594648898 0.011581676 0.040651369 0.000000000 0.000000000 0.000000000 0.002717246 $value [1] 14535187 $counts function gradient 54 54 $convergence [1] 0 $message [1] "CONVERGENCE: REL_REDUCTION_OF_F <= FACTR*EPSMCH" $hessian [,1] [,2] [,3] [,4] [,5] [,6] [1,] 0.000000e+00 0.000000e+00 0.000000e+00 -0.0023283064 0.0000000000 2.328306e-03 [2,] 0.000000e+00 0.000000e+00 0.000000e+00 -0.0023283064 0.0000000000 2.328306e-03...

...fn2<- -length(c)*log(par[2])+sum(log(par[2]*par[2]+(c-par[1])*(c-par[1])))+ }> optim(v,fn1,NULL,method="BFGS",X)$par[1] 0.3857697 -1.3984869 2.0925084 3.2370430 -1.6269258$value[1] -6.132011$countsfunction gradient 15 15 $convergence[1] 0$message[1] "CONVERGENCE: REL_REDUCTION_OF_F <= FACTR*EPSMCH"There were 50 or more warnings (use warnings() to see the first 50)> #=====================================================================================> > c<-rn! orm(10)> v<-rnorm(10)> w<-rexp(10)> fn1<-function(v) {+ for(i ! in 1:10) {+...

...6611 # c2 and c3 are sort of okay (larger range of variation for x2 and x3) # but c1 is a bit out of whack (residual=3, we were unlucky...) $value [1] 12.87678 # keep in mind for future comparison $counts function gradient       9        9 $convergence [1] 0 $message [1] "CONVERGENCE: REL_REDUCTION_OF_F <= FACTR*EPSMCH" > > # Another rainchech : does bound optimization reach the same objective > # when the "true" value lies in the bound region ? > > system.time(D2.unbound<-optim(par=c(c1=0.5, c2=0.5, c3=0.5), +                              fn=objfun, +       ...