New method to estimate missing data by using the asymmetrical winsorized mean in a time series

Ahmad Mahir Razali, A. M H Al-Khazaleh

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In this paper we consider the problem of missing data in a time series analysis. We propose asymmetrical r ≠ s winsorized mean to handle the problem of missing data. Beside that we suggested the Neyman allocation method to choose the values of r and s in asymmetric winsorized mean. We used the a absolute mean error and mean square error to compare the result of estimation missing data with other methods, such as trends, average of the whole data, naive forecast and average bound of the holes and simultaneous filling in the missing data. An example had been presented.

Original languageEnglish
Pages (from-to)1715-1726
Number of pages12
JournalApplied Mathematical Sciences
Volume3
Issue number33-36
Publication statusPublished - 2009

Fingerprint

Time series analysis
Missing Data
Mean square error
Time series
Estimate
Neyman Allocation
Time Series Analysis
Forecast
Choose

Keywords

  • Missing data
  • Neyman allocation
  • Winsorized mean

ASJC Scopus subject areas

  • Applied Mathematics

Cite this

New method to estimate missing data by using the asymmetrical winsorized mean in a time series. / Razali, Ahmad Mahir; Al-Khazaleh, A. M H.

In: Applied Mathematical Sciences, Vol. 3, No. 33-36, 2009, p. 1715-1726.

Research output: Contribution to journalArticle

@article{4e6847ef8e4a4d31be569dbeb351e9ff,
title = "New method to estimate missing data by using the asymmetrical winsorized mean in a time series",
abstract = "In this paper we consider the problem of missing data in a time series analysis. We propose asymmetrical r ≠ s winsorized mean to handle the problem of missing data. Beside that we suggested the Neyman allocation method to choose the values of r and s in asymmetric winsorized mean. We used the a absolute mean error and mean square error to compare the result of estimation missing data with other methods, such as trends, average of the whole data, naive forecast and average bound of the holes and simultaneous filling in the missing data. An example had been presented.",
keywords = "Missing data, Neyman allocation, Winsorized mean",
author = "Razali, {Ahmad Mahir} and Al-Khazaleh, {A. M H}",
year = "2009",
language = "English",
volume = "3",
pages = "1715--1726",
journal = "Applied Mathematical Sciences",
issn = "1312-885X",
publisher = "Hikari Ltd.",
number = "33-36",

}

TY - JOUR

T1 - New method to estimate missing data by using the asymmetrical winsorized mean in a time series

AU - Razali, Ahmad Mahir

AU - Al-Khazaleh, A. M H

PY - 2009

Y1 - 2009

N2 - In this paper we consider the problem of missing data in a time series analysis. We propose asymmetrical r ≠ s winsorized mean to handle the problem of missing data. Beside that we suggested the Neyman allocation method to choose the values of r and s in asymmetric winsorized mean. We used the a absolute mean error and mean square error to compare the result of estimation missing data with other methods, such as trends, average of the whole data, naive forecast and average bound of the holes and simultaneous filling in the missing data. An example had been presented.

AB - In this paper we consider the problem of missing data in a time series analysis. We propose asymmetrical r ≠ s winsorized mean to handle the problem of missing data. Beside that we suggested the Neyman allocation method to choose the values of r and s in asymmetric winsorized mean. We used the a absolute mean error and mean square error to compare the result of estimation missing data with other methods, such as trends, average of the whole data, naive forecast and average bound of the holes and simultaneous filling in the missing data. An example had been presented.

KW - Missing data

KW - Neyman allocation

KW - Winsorized mean

UR - http://www.scopus.com/inward/record.url?scp=77950940507&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77950940507&partnerID=8YFLogxK

M3 - Article

VL - 3

SP - 1715

EP - 1726

JO - Applied Mathematical Sciences

JF - Applied Mathematical Sciences

SN - 1312-885X

IS - 33-36

ER -