Alternative TitleResearch on the Gaussian Mixture distribution analysis as estimation of Probability Density Function and it's the periphery
Note (General)In statistics, Mixture distribution model is a stochastic model for a measured data set to express existence of the subpopulation in a population, without requiring that the subpopulation to whom each observational data belongs should be identified.
Formally, Mixture distribution model is equivalent to expressing the probability distributions of observational data in a population.
However, it is although it is related to the problem relevant to Mixture distribution pulling out a population's characteristic out of subpopulation.
Mixture distribution model is used without subpopulation's identity information in order to make the statistical inference about the characteristic of the subpopulation who was able to give only the observational data about a population simultaneously.
Some methods of fitting Mixture distribution model to observational data contain the step considered that subpopulation's assumed identity originates in each observational data (or gravity to such subpopulation).
This paper considered these matters from the similarity of the linear combination of an element function with the estimation problem of a Probability Density Function which used the Kernel function, and the estimation problem of the Probability Density Function using a Spline function.
How to take Translate in arrangement of knots of the estimation problem of the Probability Density Function using the method of Band width picking in the estimation problem of the Probability Density Function using a Kernel function and a Spline function and Wavelets analysis and Scale has a related thing.
At the end of this doctoral thesis, Application to an analysis of the problem of resistant bacteria and the scatter situation of the pollen and a problem of quality control is described.
identifier:https://gair.media.gunma-u.ac.jp/dspace/handle/10087/9251
Collection (particular)国立国会図書館デジタルコレクション > デジタル化資料 > 博士論文
Date Accepted (W3CDTF)2019-12-03T19:23:31+09:00
Data Provider (Database)国立国会図書館 : 国立国会図書館デジタルコレクション