A categorical modeling approach to analyzing new product adoption and usage in the context of the building-materials industry

Abstract A high proportion of non-adopters is prevalent in any market where the product under consideration is relatively new or has a low acceptance rate. This results in a low proportion of adopters in a representative sample. In adoption or product usage modeling such high proportion of zeros in the dependent variable may be addressed by zero-inflated models, by modeling the product adoption and usage as a function of two latent processes. This paper considers a zero-inflated ordinal-probit model for investigating adoption and usage of innovative wall-cavity insulation materials among residential homebuilders in the US. This study assumes a three-step adoption process of innovative housing materials, namely, trial adoption, intermediate adoption and complete adoption. The study uses 5757 responses from a combined ‘Annual Builder Practices Survey’ dataset comprising ten cross-sectional yearly surveys, undertaken by the NAHB Research Center, from 1996 to 2005. The research results indicate that though a higher proportion of large firms are more likely to adopt innovative insulation material, they continue using established products while slowly increasing their use of the innovative material over time. However, when smaller homebuilders adopt an innovative insulation material, it replaces the existing product from their material usage portfolio at a faster rate.

[1]  L. Fourt,et al.  Early Prediction of Market Success for New Grocery Products , 1960 .

[2]  Siva Balasubramanian,et al.  Long-Term View of the Diffusion of Durables: A Study of the Role of Price and Adoption Influence Processes via Tests of Nested Models , 1988 .

[3]  Diane Lambert,et al.  Zero-inflacted Poisson regression, with an application to defects in manufacturing , 1992 .

[4]  D. Gann,et al.  Innovation in project-based, service-enhanced firms: the construction of complex products and systems , 2000 .

[5]  Graham Winch,et al.  Zephyrs of creative destruction: understanding the management of innovation in construction , 1998 .

[6]  Steven T. Sonka,et al.  Managerial Performance and Income Variability for a Sample of Illinois Cash Grain Producers , 1986 .

[7]  J. Hinde,et al.  A Score Test for Testing a Zero‐Inflated Poisson Regression Model Against Zero‐Inflated Negative Binomial Alternatives , 2001, Biometrics.

[8]  D. Jain,et al.  Effect of Price on the Demand for Durables: Modeling, Estimation, and Findings , 1990 .

[9]  M. Aldenderfer,et al.  Cluster Analysis. Sage University Paper Series On Quantitative Applications in the Social Sciences 07-044 , 1984 .

[10]  D. Hall.  Zero‐Inflated Poisson and Binomial Regression with Random Effects: A Case Study , 2000, Biometrics.

[11]  Edward M. Shepard,et al.  The Diffusion of Innovation in Home Building , 1996 .

[12]  F. Bass.  The Relationship between Diffusion Rates, Experience Curves, and Demand Elasticities for Consumer Durable Technological Innovations , 1980 .

[13]  Robert A. Peterson,et al.  Innovation Diffusion in a Dynamic Potential Adopter Population , 1978 .

[14]  Mark N. Harris,et al.  Modelling Tobacco Consumption with a Zero-Inflated Ordered Probit Model ∗ , 2004 .

[15]  John M. Quigley,et al.  Regulatory Barriers to the Diffusion of Innovation: Some Evidence from Building Codes , 1977 .

[16]  A. Raftery.  Bayes Factors and BIC , 1999 .

[17]  S. Kalish.  A New Product Adoption Model with Price, Advertising, and Uncertainty , 1985 .

[18]  David R. Cox,et al.  On test statistics calculated from residuals , 1971 .

[19]  Christopher Winship,et al.  REGRESSION MODELS WITH ORDINAL VARIABLES , 1984 .

[20]  R. McKelvey,et al.  A statistical model for the analysis of ordinal level dependent variables , 1975 .

[21]  Andy H. Lee,et al.  Multi-level zero-inflated Poisson regression modelling of correlated count data with excess zeros , 2006, Statistical methods in medical research.

[22]  John Hinde,et al.  Zero-inflated proportion data models applied to a biological control assay , 2000 .

[23]  Lars-Erik Gadde,et al.  The construction industry as a loosely coupled system: implications for productivity and innovation , 2002 .

[24]  K. Zimmermann,et al.  PSEUDO‐R2 MEASURES FOR SOME COMMON LIMITED DEPENDENT VARIABLE MODELS , 1996 .

[25]  P. Schmidt,et al.  Limited-Dependent and Qualitative Variables in Econometrics. , 1984 .

[26]  D. Weakliem.  A Critique of the Bayesian Information Criterion for Model Selection , 1999 .

[27]  N. Nagelkerke,et al.  A note on a general definition of the coefficient of determination , 1991 .

[28]  J. Pratt.  Concavity of the Log Likelihood , 1981 .

[29]  Q. Vuong.  Likelihood Ratio Tests for Model Selection and Non-Nested Hypotheses , 1989 .

[30]  James E. Bartlett,et al.  Organizational research: Determining appropriate sample size in survey research , 2001 .

[31]  Bruce R. Robinson,et al.  Dynamic Price Models for New-Product Planning , 1975 .

[32]  M. Atkins,et al.  Sizing up the Small Firm: UK and Australian Experience , 1997 .

[33]  Daniel B. Hall,et al.  Marginal models for zero inflated clustered data , 2004 .

[34]  J. S. Long,et al.  Regression Models for Categorical and Limited Dependent Variables , 1997 .

[35]  K. Burnham,et al.  Model selection: An integral part of inference , 1997 .

[36]  Dipak C. Jain,et al.  Why the Bass Model Fits without Decision Variables , 1994 .

[37]  David Gann,et al.  Do regulations encourage innovation? The case of energy efficiency in housing. , 1998 .