Abstract Details
Activity Number:
|
129
|
Type:
|
Contributed
|
Date/Time:
|
Monday, August 4, 2014 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Business and Economic Statistics Section
|
Abstract #313620
|
View Presentation
|
Title:
|
ANOVA-Based Tests for Stable Seasonal Pattern, with Applications to Forecasting Economic Data
|
Author(s):
|
Stanley Sclove*+ and Fangfang Wang
|
Companies:
|
University of Illinois at Chicago and University of Illinois at Chicago
|
Keywords:
|
Seasonality ;
stable seasonal pattern ;
two-way ANOVA ;
Analysis of covariance (ANCOVA) ;
Tukey's one degree of freedom for non-additivity ;
forecasting
|
Abstract:
|
Given seasonal data, such as quarterly sales figures, a seasonal pattern is a pattern of ups or downs across the seasons. If the pattern is consistent from year to year, it is called a stable seasonal pattern. For quarterly data, the pattern is stable if the percentages attributable to the different quarters remain relatively constant over the years. Here, as two examples, stable seasonal pattern is discussed in a macroeconomic example, U.S. Gross Domestic Product (GDP), and in a microeconomic, retail example, Best Buy quarterly sales. A two-way Analysis of Variance (ANOVA) approach is applied to the logged data, with annual and quarterly effects. Instability of seasonal pattern means that quarterly effects would vary from year to year. In ANOVA terms, this is interaction, the failure of the cell entries to be adequately fitted by the row and column effects. Since there is no replication to test for interaction, the Tukey's one degree of freedom test for interaction is used to to test for stability. Forecasting is done based on the ANOVA model with ARIMA modeling of the yearly totals.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2014 program
|
2014 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Professional Development program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.