Impact of Missing Data on Parameter Estimation Algorithm of Normal Distribution

被引：0

作者：

Wang Feng ^{[1
]}

Wang Shaotong ^{[2
]}

机构：

[1] Lanzhou Univ Finance & Econ, Sch Informat Engn, Lanzhou, Peoples R China

[2] Lanzhou Univ, Sch Pastoral Agr Sci & Technol, Lanzhou 730000, Peoples R China

来源：

2013 2ND INTERNATIONAL SYMPOSIUM ON INSTRUMENTATION AND MEASUREMENT, SENSOR NETWORK AND AUTOMATION (IMSNA) | 2013年

关键词：

Parameter estimation of normal distribution; EM algorithm; Missing data; CONVERGENCE PROPERTIES;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper propose a simulation approach for the parameter estimation of normal distribution, to analyze the EM algorithm with missing data under different missing rates and complete data maximum likelihood estimation. The simulation result shows that the EM algorithm and the maximum likelihood estimates are almost unanimously when the missing rate is less than 0.25, but the effect of parameter estimation of the EM algorithm gradually deteriorates when the missing rate increases. The result also shows that the EM algorithm is more sensitive to the initial value. In addition, this paper also analyzes the evaluation of the selection of initial value for EM algorithm.

引用

页码：574 / 578

页数：5

共 50 条

[1] Impact of Missing Data on Parameter Estimation of EM Algorithm under Rayleigh Distribution
Li, Zhendong
Li, Mengmeng
SENSORS, MEASUREMENT AND INTELLIGENT MATERIALS II, PTS 1 AND 2, 2014, 475-476 : 278 - +
[2] On the use of the selection matrix in the maximum likelihood estimation of normal distribution models with missing data
Takai, Keiji
COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2018, 47 (14) : 3392 - 3407
[3] The Impact of Missing Data on Parameter Estimation: Three Examples in Computerized Adaptive Testing
Liu, Xiaowen
Loken, Eric
EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT, 2025,
[4] Parameter Estimation and Hypothesis Testing of Two Negative Binomial Distribution Population with Missing Data
Zhao, Zhiwen
2012 INTERNATIONAL CONFERENCE ON MEDICAL PHYSICS AND BIOMEDICAL ENGINEERING (ICMPBE2012), 2012, 33 : 1475 - 1480
[5] Least-squares parameter estimation for systems with irregularly missing data
Ding, Feng
Ding, Jie
INTERNATIONAL JOURNAL OF ADAPTIVE CONTROL AND SIGNAL PROCESSING, 2010, 24 (07) : 540 - 553
[6] Time series AR model parameter estimation with missing observation data
Ding, Jie
Chen, Xiaoming
Ding, Feng
2008 7TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-23, 2008, : 5632 - 5636
[7] PARAMETER ESTIMATION FOR WEIBULL DISTRIBUTION WITH RIGHT CENSORED DATA USING EM ALGORITHM
Ferreira, Luis Andrade
Silva, Jose Luis
EKSPLOATACJA I NIEZAWODNOSC-MAINTENANCE AND RELIABILITY, 2017, 19 (02): : 310 - 315
[8] Distribution estimation with auxiliary information for missing data
Liu, Xu
Liu, Peixin
Zhou, Yong
JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 2011, 141 (02) : 711 - 724
[9] Estimation with missing data
Goodwin, GC
Feuer, A
MATHEMATICAL AND COMPUTER MODELLING OF DYNAMICAL SYSTEMS, 1999, 5 (03) : 220 - 244
[10] The Impact of Missing Data on Species Tree Estimation
Xi, Zhenxiang
Liu, Liang
Davis, Charles C.
MOLECULAR BIOLOGY AND EVOLUTION, 2016, 33 (03) : 838 - 860

← 1 2 3 4 5 →