Mathematics Colloquium

Add to Calendar 04/26/2018 15:35:0004/26/2018 16:30:0015Mathematics ColloquiumSpeaker One: Amal Alsomali, University of Dayton Advisor: Maher Qumsiyeh Title: Forecasting Using Logistic Regression and Box–Jenkins (ARIMA) Models Abstract: Prediction and forecasting using a logistic regression or a Box–Jenkins (ARIMA) model have exploded during the past few years. Both models are now used in almost all kinds of knowledge. In a climate system, rainfall is one of the most important events. It is well known that the intensity of rainfall, or whether it rains or not act on natural, agricultural, human and even total biological system. In this project, we show how logistic regression and the Box–Jenkins (ARIMA) model can be used in predicting rainfall. We developed two models and used them on two different data sets. One model uses logistic regression and the other one uses a Box–Jenkins (ARIMA) model. All programming was done using the statistical software package SAS. Speaker Two: Ashley Mailloux, University of Dayton Advisor: Maher Qumsiyeh Title: Bootstrapping a Moving Average Time Series Data Abstract: The bootstrap method introduced by Efron (1979) is applicable under the hypothesis of independence or under specific model assumptions. The general ARIMA models are highly dependent on time, and so the residuals are also highly correlated. Due to this, a different bootstrap approach must be used to deal with the dependency. We present two types of approaches: the non-overlapping and then the overlapping bootstrap method. We will show how these methods can be used for parameter estimation and for forecasting in a Moving Average model, for simulated data. These methods will be compared with the Box-Jenkins methodology on parameter estimation and forecasts. We will also compare the length of the confidence intervals for the parameters and the forecasts using the traditional methods and the non- overlapping and overlapping block bootstrap. All programming for this research project was completed using the statistical software package SAS. Refreshments are available at 3:00 PM in SC 313F. The department colloquia are held every Thursday (excluding holidays) at 3:35 pm in room SC 323 unless otherwise noted. All are invited to attend. Science Center Room 323Paul Eloepeloe1@udayton.eduNo04/26/2018

Thursday, April 26

Time: 3:35 p.m. — 4:30 p.m.

Location: Science Center Room 323

Tags:  Colloquia, Mathematics, Sciences

Cost:  Free

Speaker One: Amal Alsomali, University of Dayton

Advisor: Maher Qumsiyeh

Title: Forecasting Using Logistic Regression and Box–Jenkins (ARIMA) Models

Abstract: Prediction and forecasting using a logistic regression or a Box–Jenkins (ARIMA) model have exploded during the past few years. Both models are now used in almost all kinds of knowledge. In a climate system, rainfall is one of the most important events. It is well known that the intensity of rainfall, or whether it rains or not act on natural, agricultural, human and even total biological system. In this project, we show how logistic regression and the Box–Jenkins (ARIMA) model can be used in predicting rainfall. We developed two models and used them on two different data sets. One model uses logistic regression and the other one uses a Box–Jenkins (ARIMA) model. All programming was done using the statistical software package SAS.

Speaker Two: Ashley Mailloux, University of Dayton

Advisor: Maher Qumsiyeh

Title: Bootstrapping a Moving Average Time Series Data

Abstract: The bootstrap method introduced by Efron (1979) is applicable under the hypothesis of independence or under specific model assumptions. The general ARIMA models are highly dependent on time, and so the residuals are also highly correlated. Due to this, a different bootstrap approach must be used to deal with the dependency. We present two types of approaches: the non-overlapping and then the overlapping bootstrap method. We will show how these methods can be used for parameter estimation and for forecasting in a Moving Average model, for simulated data. These methods will be compared with the Box-Jenkins methodology on parameter estimation and forecasts. We will also compare the length of the confidence intervals for the parameters and the forecasts using the traditional methods and the non- overlapping and overlapping block bootstrap. All programming for this research project was completed using the statistical software package SAS.

Refreshments are available at 3:00 PM in SC 313F.

The department colloquia are held every Thursday (excluding holidays) at 3:35 pm in room SC 323 unless otherwise noted. All are invited to attend. 

Contact Information:

Name:  Paul Eloe
Email:  peloe1@udayton.edu