Comparative performance of ARIMA and kernel estimation of the conditional mean : time series of traffic violations in Gaza Strip
Other Title(s)
الأداء المقارن لنماذج آريما و تقدير النواة للمتوسط الشرطي : السلاسل الزمنية للمخالفات المرورية في قطاع غزة
Dissertant
Thesis advisor
University
Islamic University
Faculty
Faculty of Science
Department
Department of Mathematics
University Country
Palestine (Gaza Strip)
Degree
Master
Degree Date
2019
English Abstract
In this thesis, we introuced the basic concepts and technique related to the area of forecasting of the time series, using two different methods.
The first one, was Autoregressive integrated moving average ARIMA model from Box and Jenknis and the second method was the Reweighted Nadaraya-Watson RNW which is one of the nonparametris estimation methods to estimate the conditional mean.The two methods were implemented on 82 from data of monthly data of the traffic violations in the Gaza Strip from January 2010 to October 2016.
This study is of great importance due to the frequent excesses of drivers and ordinary citizens of the traffic laws, and the consequent obstruction of traffic, material losses, injury or death of citizens.
This study aims to obtain a more accurate forecast of the number of traffic violations in the Gaza Strip using two different methods, ARIMA and RNW.
87.8% of the data were considered as a training group, to make prediction more efficient and less erroneous, the missing values were processed, finding the first differences of data in method ARIMA and finding the natural logarithm of the data in RNW method.
The study showed that ARIMA (1,1,2) is the best model of ARIMA models for model construction prediction, a comparison was made between the results obtained from the application of both ARIMA and RNW methods.
The results clearly showed that the results of the ARIMA model were better than the RNW model .
We recommend that you use more than one model to predict the futur.
Main Topic
No. of Pages
73
Table of Contents
Table of contents.
Abstract.
Abstract in Arabic.
Chapter One : Introduction.
Chapter Two : Time series models.
Chapter Three : Kernel estimator.
Chapter Four : Data analysis.
Chapter Five : Discussions AND conclusions.
References.
American Psychological Association (APA)
Ulwan, Taha Farid Ahmad. (2019). Comparative performance of ARIMA and kernel estimation of the conditional mean : time series of traffic violations in Gaza Strip. (Master's theses Theses and Dissertations Master). Islamic University, Palestine (Gaza Strip)
https://search.emarefa.net/detail/BIM-901391
Modern Language Association (MLA)
Ulwan, Taha Farid Ahmad. Comparative performance of ARIMA and kernel estimation of the conditional mean : time series of traffic violations in Gaza Strip. (Master's theses Theses and Dissertations Master). Islamic University. (2019).
https://search.emarefa.net/detail/BIM-901391
American Medical Association (AMA)
Ulwan, Taha Farid Ahmad. (2019). Comparative performance of ARIMA and kernel estimation of the conditional mean : time series of traffic violations in Gaza Strip. (Master's theses Theses and Dissertations Master). Islamic University, Palestine (Gaza Strip)
https://search.emarefa.net/detail/BIM-901391
Language
English
Data Type
Arab Theses
Record ID
BIM-901391
Advertisement
