mif {pomp} | R Documentation |
The MIF algorithm for estimating the parameters of a partially-observed Markov process.
mif(object, ...) ## S4 method for signature 'pomp': mif(object, Nmif = 1, start, pars, ivps = character(0), particles, rw.sd, alg.pars, Np, ic.lag, var.factor, cooling.factor, weighted = TRUE, tol = 1e-17, warn = TRUE, max.fail = 0, verbose = FALSE) ## S4 method for signature 'mif': mif(object, Nmif, ...) ## S4 method for signature 'mif': continue(object, Nmif = 1, ...)
object |
An object of class pomp .
|
Nmif |
The number of MIF iterations to perform. |
start |
The initial guess of the parameters. This must be a named vector. |
pars |
optional character vector naming the ordinary parameters to be estimated.
Every parameter named in pars must have a positive random-walk standard deviation specified in rw.sd .
Leaving pars unspecified is equivalent to setting it equal to the names of all parameters with a positive value of rw.sd that are not ivps .
|
ivps |
optional character vector naming the initial-value parameters to be estimated.
Every parameter named in ivps must have a positive random-walk standard deviation specified in rw.sd .
|
particles |
Function of prototype particles(Np,center,sd,...) which sets up the initial particle matrix by drawing a sample of size Np from the initial particle distribution centered at center and of width sd .
If particles is not supplied by the user, the default behavior is to draw the particles from a multivariate normal distribution with mean center and standard deviation sd .
|
rw.sd |
numeric vector with names; the intensity of the random walk to be applied to parameters.
The random walk is only applied to parameters named in pars (i.e., not to those named in ivps ).
The algorithm requires that the random walk be nontrivial, so each element in rw.sd[pars] must be positive.
rw.sd is also used to scale the initial-value parameters (via the particles function).
Therefore, each element of rw.sd[ivps] must be positive.
The following must be satisfied:
names(rw.sd) must be a subset of names(start) ,
rw.sd must be non-negative (zeros are simply ignored),
the name of every positive element of rw.sd must be in either pars or ivps .
|
alg.pars |
optional; a named list of the algorithm parameters Np , cooling.factor , var.factor , ic.lag .
The use of alg.pars is now deprecated and generates a warning.
It will be removed in the near future.
|
Np |
a positive integer; the number of particles to use in filtering |
ic.lag |
a positive integer; the timepoint for fixed-lag smoothing of initial-value parameters |
var.factor |
a positive number;
the scaling coefficient relating the width of the initial particle distribution to rw.sd
The width of the initial distribution of particles will be random.walk.sd*var.factor .
|
cooling.factor |
a positive number not greater than 1;
the exponential cooling factor, alpha .
|
weighted |
Should a weighted average be used?
If weighted=F , the MIF update is not used;
instead, an unweighed average of the filtering means is used for the update.
|
tol |
Particles with log likelihood below tol are considered to be "lost".
A filtering failure occurs when, at some time point, all particles are lost.
|
warn |
Should a warning be generated when a filtering failure occurs? |
max.fail |
Maximum number of filtering failures permitted. If the number of failures exceeds this number, execution will terminate with an error. |
verbose |
logical; if TRUE, print progress reports. |
... |
Additional arguments that can be used to override the defaults. |
To re-run a sequence of MIF iterations, one can use the mif
method on a mif
object.
The call sequence is mif(object)
.
By default, the same parameters used for the original MIF run are re-used (except for weighted
, tol
, warn
, max.fail
, and verbose
, the defaults of which are shown above).
If one does specify additional arguments, these will override the defaults.
One can continue a series of MIF iterations from where one left off.
The call sequence is continue(object, Nmif)
.
This will perform Nmif
additional MIF iterations on the mif
object object
.
A call to mif
to perform Nmif=m
iterations followed by a call to continue
to perform Nmif=n
iterations will produce precisely the same effect as a single call to mif
to perform Nmif=m+n
iterations.
By default, all the algorithmic parameters are the same as used in the original call to mif
.
Additional arguments will override the defaults.
If particles
is not specified, the default behavior is to draw the particles from a multivariate normal distribution.
It is the user's responsibility to ensure that, if the optional particles
argument is given, that the particles
function satisfies the following conditions:
particles
has at least the following arguments:
Np
, center
, sd
, and ...
.
Np
may be assumed to be a positive integer;
center
and sd
will be named vectors of the same length.
Additional arguments may be specified;
these will be filled with the elements of the userdata
slot of the underlying pomp
object (see pomp-class
).
particles
returns a length(center)
x Np
matrix with rownames matching the names of center
and sd
.
Each column represents a distinct particle.
The center of the particle distribution returned by particles
should be center
.
The width of the particle distribution should vary monotonically with sd
.
In particular, when sd=0
, the particles
should return matrices with Np
identical columns, each corresponding to the parameters specified in center
.
Aaron A. King kingaa at umich dot edu
E. L. Ionides, C. Bret'o, & A. A. King, Inference for nonlinear dynamical systems, Proc. Natl. Acad. Sci. U.S.A., 103:18438–18443, 2006.
A. A. King, E. L. Ionides, M. Pascual, and M. J. Bouma, Inapparent infections and cholera dynamics, Nature, 454:877–880, 2008.
mif-class
, mif-methods
, pomp
, pomp-class
, pfilter
.
See the “intro_to_pomp” vignette for an example.