Stochastic Approximation Algorithm for Estimating Mixing Distribution for Dependent Observations
Links to Fileshttps://arxiv.org/abs/2006.14734
MetadataShow full item record
Type of Work42 pages
journal articles preprints
Citation of Original PublicationNilabja Guha and Anindya Roy, Stochastic Approximation Algorithm for Estimating Mixing Distribution for Dependent Observations, https://arxiv.org/abs/2006.14734
RightsThis item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
Estimating the mixing density of a mixture distribution remains an interesting problem in statistics literature. Using a stochastic approximation method, Newton and Zhang (1999) introduced a fast recursive algorithm for estimating the mixing density of a mixture. Under suitably chosen weights the stochastic approximation estimator converges to the true solution. In Tokdar et. al. (2009) the consistency of this recursive estimation method was established. However, the proof of consistency of the resulting estimator used independence among observations as an assumption. Here, we extend the investigation of performance of Newton's algorithm to several dependent scenarios. We first prove that the original algorithm under certain conditions remains consistent when the observations are arising form a weakly dependent process with fixed marginal with the target mixture as the marginal density. For some of the common dependent structures where the original algorithm is no longer consistent, we provide a modification of the algorithm that generates a consistent estimator.