Reputation: 137
I have fitted a Hidden Markov Model using the moveHMM
library in R.
hmm_model <- fitHMM(data = move_data, nbStates = 3, stepPar0 = stepPar0, anglePar0 = anglePar0, formula = ~1)
The result makes sense biologically speaking and I do not have any warning issued.
As indicated in the package documentation (https://cran.r-project.org/web/packages/moveHMM/vignettes/moveHMM-guide.pdf) I tried to plot the object.
I tried the following commands:
plot(hmm_model, type = "states")
plot(hmm_model)
but I always get the same error message:
> plot(hmm_model, type = "states")
Decoding states sequence... DONE
Error in if (maxdens > ymax & maxdens < 1.5 * ymax) { :
missing value where TRUE/FALSE needed
Has anyone ever encountered this issue and would have any recommendations on how to solve it?
Here is the structure of the object that should be plotted:
> str(hmm_model)
List of 7
$ data :'data.frame': 16515 obs. of 6 variables:
..$ ID : chr [1:16515] "1" "1" "1" "1" ...
..$ step : num [1:16515] 0.327 0.346 0.346 0.346 0.346 ...
..$ angle : num [1:16515] NA -0.156381 -0.004527 -0.001887 -0.000926 ...
..$ x : num [1:16515] 582629 582629 582628 582628 582628 ...
..$ y : num [1:16515] -2195359 -2195359 -2195358 -2195358 -2195358 ...
..$ (Intercept): num [1:16515] 1 1 1 1 1 1 1 1 1 1 ...
$ mle :List of 5
..$ stepPar : num [1:3, 1:3] 3.43e-15 8.36e+09 1.00 8.31e-02 1.13e-01 ...
.. ..- attr(*, "dimnames")=List of 2
.. .. ..$ : chr [1:3] "mean" "sd" "zero-mass"
.. .. ..$ : chr [1:3] "state 1" "state 2" "state 3"
..$ anglePar: num [1:2, 1:3] 1.31e-03 2.83 1.32e-03 2.23e+01 -3.31e-10 ...
.. ..- attr(*, "dimnames")=List of 2
.. .. ..$ : chr [1:2] "mean" "concentration"
.. .. ..$ : chr [1:3] "state 1" "state 2" "state 3"
..$ beta : num [1, 1:6] -6.91 -37.97 -9.65 -25.74 -0.43 ...
.. ..- attr(*, "dimnames")=List of 2
.. .. ..$ : chr "intercept"
.. .. ..$ : chr [1:6] "1 -> 2" "1 -> 3" "2 -> 1" "2 -> 3" ...
..$ delta : num [1:3] 2.67e-10 1.00 1.32e-14
..$ gamma : num [1:3, 1:3] 9.99e-01 6.44e-05 3.38e-01 9.93e-04 1.00 ...
$ mod :List of 6
..$ minimum : num -27526
..$ estimate : num [1:23] -33.31 -2.49 1.61 22.85 -2.18 ...
..$ gradient : num [1:23] 0 -0.00268 0 0 0.00216 ...
..$ hessian : num [1:23, 1:23] 0 0 0 0 0 0 0 0 0 0 ...
..$ code : int 1
..$ iterations: int 73
$ conditions :List of 6
..$ stepDist : chr "gamma"
..$ angleDist : chr "vm"
..$ zeroInflation: logi TRUE
..$ estAngleMean : logi TRUE
..$ stationary : logi FALSE
..$ formula :Class 'formula' language ~1
.. .. ..- attr(*, ".Environment")=<environment: R_GlobalEnv>
$ rawCovs :'data.frame': 16515 obs. of 0 variables
$ knownStates: NULL
$ nlmTime : 'proc_time' Named num [1:5] 66.16 0.72 66.88 NA NA
..- attr(*, "names")= chr [1:5] "user.self" "sys.self" "elapsed" "user.child" ...
- attr(*, "class")= chr [1:2] "moveHMM" "list"
Many thanks (I do not really know how to make this issue reproducible, so I am asking about the error message to get a first idea).
Upvotes: 0
Views: 75