Errors for method = "ml"

[christophsax]

library(bdfm)
m1 <- dfm(cbind(fdeaths, mdeaths), method = "ml") #multivariate example
#> Error in dfm(cbind(fdeaths, mdeaths), method = "ml"): Mixed freqeuncy models are only supported for Bayesian estimation
m3 <- dfm(fdeaths, method = "ml") #univariate example
#> Error in dfm(fdeaths, method = "ml"): Mixed freqeuncy models are only supported for Bayesian estimation

^{Created on 2019-03-06 by the reprex package (v0.2.1)}

[christophsax]

duplicate of #38

[christophsax]

Probably not the same, but method = "ml" is not working:

library(bdfm)
dfm(mdeaths, method = 'ml')
#> Error in DSmooth(B, Jb = Jb, q, H, R, Y = Ydm, freq = rep(1, k), LD = rep(0, : Not a matrix.

^{Created on 2019-06-15 by the reprex package (v0.2.1)}

[christophsax]

Fixing this and including the test would probably bring test coverage to a satisfying level.

[SethOttoQuant]

OK... should be fine now. B was being entered as a sparse matrix in DSmooth(), needs to be a dense matrix.