Farris, Paul W.; Parry, Mark F.; Ailawadi, Kusum L.
January 1992
Marketing Science;Winter92, Vol. 11 Issue 1, p76
Academic Journal
Composite variables are those that may be mathematically decomposed into additive and/or multiplicative component variables. Several researchers have noted that the relationship between a composite variable and its components may be a mathematical artifact, but the effect of their inclusion as independent variables on the coefficients of the remaining variables in the model has not been recognized, nor has a formal expression for the resulting bias been presented. Structural analysis of composite dependent variables, as presented here, provides the key to understanding the nature and extent of this bias. It separates higher and lower level components from one another and also separates these components from other antecedent variables in the model. The advantages of this hierarchical decomposition are that (1) it reduces problems of misspecification and omitted variables, (2) by separately estimating antecedent effects on each component, it offers some insights into the underlying causal mechanisms that are not available from other techniques and (3) it ensures that regression coefficients can be interpreted in the standard way: the expected change in the dependent variable associated with a change in the independent variable, holding other independent variables in the equation constant. Moreover, hierarchical decomposition of the dependent variable can reproduce all information available from techniques that mix levels of analysis, but the converse is not true.


Related Articles

  • Reply to "A Comment on a New Measure of Predictor Variable Importance in Multiple Regression" Green, Paul E.; Carroll, J. Douglas; DeSarbo, Wayne S. // Journal of Marketing Research (JMR);Feb1980, Vol. 17 Issue 1, p116 

    The article presents a reply to comments on the predictor variables discussion in Barbara Bund Jackson's work. The primary concern is the measurement of predictor variable importance in multiple regression. In Jackson's comments describe a basic limitation of all importance measures in multiple...

  • Adaptive Variable Selection in Nonparametric Sparse Regression. Ingster, Yu.; Stepanova, N. // Journal of Mathematical Sciences;May2014, Vol. 199 Issue 2, p184 

    We study the problem of exact recovery of an unknown multivariate function f observed in the continuous regression model. It is assumed that, in addition to some smoothness constraints, f possesses an additive sparse structure determined by sparsity index β ∈ (0, 1). As a consequence of...

  • Heuristiques trompeuses et modèles de régression multiple avec variable modératrice. Irwin, Julie R.; McClelland, Gary H. // Recherche et Applications en Marketing (AFM c/o ESCP-EAP);2002, Vol. 17 Issue 2, p87 

    Moderated multiple regression models allow the simple relationship between the dependent variable and an independent variable to depend on the level of another independent variable. The moderated relationship, often referred to as the « interaction » is modeled by including a product term...

  • Forecasting the Primary Demand for a Beer Brand Using Time Series Analysis. Bratina, Danijel; Faganel, Armand // Organizacija;May/Jun2008, Vol. 41 Issue 3, p116 

    Market research often uses data (i.e. marketing mix variables) that is equally spaced over time. Time series theory is perfectly suited to study this phenomena's dependency on time. It is used for forecasting and causality analysis, but their greatest strength is in studying the impact of a...

  • Measurement Error and Regression to the Mean in Matched Samples. Althauser, Robert P.; Rubin, Donald // Social Forces;Dec71, Vol. 50 Issue 2, p206 

    This is a treatment of "regression to the mean" in matched samples produced by measurement error in matching variables. An equation expressing the respective contributions of regression and treatment effects to a difference of Y-means for two matched groups is derived, followed by an intuitive...

  • Investigación clínica XX Del juicio clínico a la regresión logística múltiple. Berea-Baltierra, Ricardo; Rivas-Ruiz, Rodolfo; Pérez-Rodríguez, Marcela; Palacios-Cruz, Lino; Moreno, Jorge; Talavera, Juan O. // Revista Medica del IMSS;mar/abr2014, Vol. 52 Issue 2, p192 

    The complexity of the causality phenomenon in clinical practice implies that the result of a maneuver is not solely caused by the maneuver, but by the interaction among the maneuver and other baseline factors or variables occurring during the maneuver. This requires methodological designs that...

  • The Relationship of Stratospheric QBO with the Difference of Measured and Calculated NmF2. Kurt, Kadri; Yeşil, Ali; Sağir, Selçuk; Atici, Ramazan // Acta Geophysica;Dec2016, Vol. 64 Issue 6, p2781 

    The relationship between stratospheric QBO and the difference (ΔNmF2) between NmF2 calculated with IRI-2012 and measured from ionosondes at the Singapore and Ascension stations in the equatorial region was statistically investigated. As statistical analysis, the regression analysis was used...

  • Complex analysis masks real meaning. Semon, Thomas T. // Marketing News;7/15/2006, Vol. 40 Issue 12, p7 

    The article discusses the use of statistical analysis programs in marketing research. It asserts that multivariate analysis programs are based on regression models. Regression models usually assume the relationships between variables as both linear and continuous. It also cites the attraction...

  • r-th mean consistency for estimators of semi-parametric regression model with a kind of mixing errors. Ren Na; Min-hong, L. V.; Pei Xiao-huan // Basic Sciences Journal of Textile Universities / Fangzhi Gaoxia;Dec2010, Vol. 23 Issue 4, p415 

    The article presents a study on use of r-th mean consistency for semi-parametric regression model estimators with mixing error variables.


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics