Generalization: EMS

Adding a kernel smoother into the EM algorithm to become EMS. The good: faster convergence by reducing dimension of parameter space; robustness; etc. the bad: introducing systematic bias. By control the bandwidth and the shape of the kernel, one may strike a balance.

RELATED ARTICLESExplain
Controlling Infectious Diseases
Research Questions
Open mathematical/computational problems?
Statistical Methods for model selection and parameter estimation
Parametric approaches
Methods incorporating both process and observation error
Expectation-maximization (EM)
Generalization: EMS
Convergence; problem with large number of parameters
Point estimation only, if converge
Graph of this discussion
Enter the title of your article


Enter a short (max 500 characters) summation of your article
Enter the main body of your article
Lock
+Comments (0)
+Citations (0)
+About
Enter comment

Select article text to quote
welcome text

First name   Last name 

Email

Skip