Online Program

Return to main conference page
Friday, May 18
Computational Statistics
Time-to-Event Models
Fri, May 18, 3:30 PM - 5:00 PM
Lake Fairfax B
 

An Efficient Generalized Least Squares Algorithm for Periodic Regression With Autoregressive Errors (304601)

Anthony Dini, Boise State University 
*Jaechoul Lee, Boise State University 
William Negri, Boise State University 

Keywords: Big data, Dimension reduction, GLS estimation, Model with autocorrelated errors, Periodic time series regression

Time series data with periodic trends like daily temperatures or sales of seasonal products can be seen in periods fluctuating between highs and lows throughout the year. Generalized least squares estimators are often computed for such time series data as these estimators have minimum variance among all linear unbiased estimators. However, the generalized least squares solution can require extremely demanding computation when the data is large. We study an efficient algorithm for generalized least squares estimation in periodic regression with autoregressive errors. We develop an algorithm that can substantially simplify generalized least squares computation by manipulating large sets of data into smaller sets. This is accomplished by coining a structured matrix for dimension reduction. Simulations show that the new computation methods using our algorithm can drastically reduce computing time. Our algorithm can be easily adapted to big data that show periodic trends often pertinent to economics, environmental studies, and engineering practices.