DocumentCode :
1731059
Title :
Nonlinear analysis of retail performance
Author :
Vaccari, David A.
Author_Institution :
Stevens Inst. of Technol., Hoboken, NJ, USA
fYear :
1996
Firstpage :
252
Lastpage :
258
Abstract :
A new class of models is proposed for use in economic correlation and forecasting. The new model, termed the multivariable polynomial regression (MPR) model, is essentially a multiple regression model with polynomial and cross-product (interaction) terms. For example, if Y is a function of Q, R, and S, terms can be included such as QR2S or Q3S. MPR models can be fitted using conventional multiple regression software, although an automated program facilitates the analysis. Only terms which are statistically significant are retained in the model. MPR models are likely to be applicable to low-to-moderate dimensionality problems as are encountered in economics. If the number of independent variables is not too great, MPR models compare favorably to artificial neural network (ANN) models: MPR models can provide a better fit with fewer coefficients; as a result there is less overfitting of “memorizing” of data; the fitting procedure converges absolutely; MPR models result in a simple explicit equation for prediction or analysis; standard statistical tests can be applied to all coefficients and forecast predictions. The technique was applied to correlation of the performance of retail stores to a set of thirteen potential causative variables. An MPR model was developed which was able to explain 82% of the variation in the gross margin of the stores under study
Keywords :
financial data processing; forecasting theory; marketing; retail data processing; statistical analysis; artificial neural network models; automated program; causative variables; cross-product terms; economic correlation; economic forecasting; economics; fitting; independent variables; low-to-moderate dimensionality problems; multiple regression model; multiple regression software; multivariable polynomial regression model; nonlinear analysis; polynomial terms; retail performance; retail store performance; statistical tests; statistically significant terms; Artificial neural networks; Economic forecasting; Equations; Performance analysis; Polynomials; Predictive models; Robustness; Statistical analysis; Technology forecasting; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computational Intelligence for Financial Engineering, 1996., Proceedings of the IEEE/IAFE 1996 Conference on
Conference_Location :
New York City, NY
Print_ISBN :
0-7803-3236-9
Type :
conf
DOI :
10.1109/CIFER.1996.501849
Filename :
501849
Link To Document :
بازگشت