Optimum smoothing parameter in Parzen density estimation.
H = PARZENML(A)
Maximum likelihood estimation for the smoothing parameter H in the Parzen denstity estimation of the data in A. A leave-one out maximum likelihood estimation is used.
The optimisation of H may be stopped prematurely by PRTIME.
The dataset A can either be crisp or soft labeled. In case of crisp labeling the class information is not used and a single smoothing parameter is estimated. In case of soft labels a smoothing parameter for every class is estimated and objects are weighted in relation to their class weigthts (soft label value). It may be profitable to scale the data before calling it. eg. WS = SCALEM(A,'variance'); A = A*WS.