Details

The following basic settings can be used:
Automatic automatically choose the estimator to use

"MaximumLikelihood" maximize the log‐likelihood function
The maximum likelihood method will maximize the log-likelihood function , where is the process parameters and is the PDF for the joint SliceDistribution of the path.
ProcessEstimator->{"estimator",Method->"solver"} specifies what underlying optimization solver to use.
Possible solver settings for "MaximumLikelihood" include:

	Automatic	automatically chosen solver
	"FindMaximum"	use FindMaximum to maximize log-likelihood
	"NMaximize"	use NMaximize to maximize log-likelihood

With the setting ProcessEstimator->{"estimator",Method->{"solver",opts}}, additional options can be given for the solver.
Solver methods such as NMaximize that do not rely on starting values will not make use of starting values given to EstimatedProcess or FindProcessParameters.
Special settings for ProcessEstimator are documented under the individual random process reference pages.

Examples

Construct a process model from data using automatic methods:

Wolfram Language code: SeedRandom[2];data = RandomFunction[PoissonProcess[10], {0, 10}];

Wolfram Language code: auto = EstimatedProcess[data, PoissonProcess[μ]]

Use maximum likelihood estimates:

Wolfram Language code: ml = EstimatedProcess[data, PoissonProcess[μ], ProcessEstimator -> "MaximumLikelihood"]

Compare the first-order probability density functions at :

Wolfram Language code: DiscretePlot[Evaluate@Table[PDF[proc[5], x], {proc, {auto, ml}}], {x, 20, 80, 5}]

Top