Off-Campus Hollins Users:
To access this document, please click here to log in to our proxy server with your campus network user name/password (the same one you use to log into the campus network and your e-mail).
Event Type
Research Presentation
Academic Department
Mathematics and Statistics
Location
Dana Science Building, 2nd floor
Start Date
14-4-2023 1:30 PM
End Date
14-4-2023 3:00 PM
Description
Under the direction of Dr. Julie Clark
Statistics and machine learning are two methods for analyzing and modeling data. A dependent variable's relationship to one or more independent variables is described through regression. The forecasting technique is used for predicting future results based on historical data. This study compares two approaches—regression and forecasting—along with statistics and machine learning. Regression and forecasting methods have been explored in numerous studies, but the results vary depending on the problem, the data, and the technology, so it is important to continue investigating regression and forecasting algorithms. We study the statistical model of ordinary least squares (OLS) and the machine learning model of gradient boosting regression (GBR) for the linear regression technique. For forecasting utilizing the Markov chain, we investigate the statistical model of the Autoregressive Integrated Moving Average (ARIMA) and the machine learning model of the Hidden Markov Model (HHM). Although regression and forecasting are applications of both machine learning and statistical models, there are some distinctions in their algorithms and data approaches. The choice between statistics and machine learning will depend on the specific problem, data, and available resources.
Statistics and Machine Learning: Regression and Forecasting
Dana Science Building, 2nd floor
Under the direction of Dr. Julie Clark
Statistics and machine learning are two methods for analyzing and modeling data. A dependent variable's relationship to one or more independent variables is described through regression. The forecasting technique is used for predicting future results based on historical data. This study compares two approaches—regression and forecasting—along with statistics and machine learning. Regression and forecasting methods have been explored in numerous studies, but the results vary depending on the problem, the data, and the technology, so it is important to continue investigating regression and forecasting algorithms. We study the statistical model of ordinary least squares (OLS) and the machine learning model of gradient boosting regression (GBR) for the linear regression technique. For forecasting utilizing the Markov chain, we investigate the statistical model of the Autoregressive Integrated Moving Average (ARIMA) and the machine learning model of the Hidden Markov Model (HHM). Although regression and forecasting are applications of both machine learning and statistical models, there are some distinctions in their algorithms and data approaches. The choice between statistics and machine learning will depend on the specific problem, data, and available resources.