Title :
Deconvolving multivariate kernel density estimates from contaminated associated observations
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of California, La Jolla, CA, USA
Abstract :
We consider the estimation of the multivariate probability density function f(x1,...,xp) of X1,...,Xp of a stationary positively or negatively associated (PA or NA) random process {Xi}i=1∞ from noisy observations. Both ordinary smooth and super smooth noise are considered. Quadratic mean and asymptotic normality results are established.
Keywords :
convergence of numerical methods; deconvolution; noise; optimisation; probability; random processes; asymptotic normality; contaminated associated observations; deconvolution; multivariate kernel density estimates; multivariate probability density function; negatively associated random process; noisy observations; quadratic mean; smooth noise; stationary positively associated process; super smooth noise; Additive noise; Convergence; Data analysis; Deconvolution; Kernel; Multidimensional systems; Pattern recognition; Probability density function; Random processes; Random variables;
Journal_Title :
Information Theory, IEEE Transactions on
DOI :
10.1109/TIT.2003.818415
