search for: makebsm

...TS" but I failed to obtain a desirable output, in fact when I write in R Console the following lines: > x=(1,2,3,4,5,2,25,14,12,13,11,6,9,24,12,13,14,12,12,14,11,12,14,15,20,21,22,23,21,25,28) >(fit <- StructTS(x,type = "BSM")) I obtained the following message:"error in makeBSM(x, nf): the frequency has to be positif entire for BSM" I would like via this command(StrucTS) obtain estimation of seasonality and local level trend components of the time series "x". Can you help me please . Thanks. [[alternative HTML version deleted]]

...t;) Error in T[cbind(ind + 1L, ind)] <- 1 : subscript out of bounds I have looked at Prof. Ripley's 2002 RNews article but cannot see why theoretically it should not be possible to have only 2 seasons. I have also looked at the StructTS code, and the problem is with the transition matrix in makeBSM, but I am not sure whether I should overwrite this or whether my thinking is wrong. I attach code that simulates data for the basic structural model (with time-varying trend and season), the top line s determines the number of seasons in a year (3 and 4 work fine, 2 gives the above error), and at...