Wagner Kamakura | Rice University (original) (raw)

Papers by Wagner Kamakura

Research paper thumbnail of Long-term forecasting with innovation diffusion models: The impact of replacement purchases

Journal of Forecasting, 1987

... Period (x 10-1) (x 10-5) (FIT) (FOR.) Rifrigerators Vacuum cleaners Toasters Electric blanket... more ... Period (x 10-1) (x 10-5) (FIT) (FOR.) Rifrigerators Vacuum cleaners Toasters Electric blankets Refrigerators Vacuum cleaners Toasters Electric blankets 1925-59 1922-56 1922-56 1948-72 1925-59 19 22-5 6 1922-56 1948-72 1.75 1.75 1.75 1.75 15.8 16.1 13.3 15.5 0.190 ...

Research paper thumbnail of Statistical Data Fusion for Cross-Tabulation

Journal of Marketing Research, Nov 1, 1997

Take-down policy If you believe that this document breaches copyright please contact us providing... more Take-down policy If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.

Research paper thumbnail of Research Note Heterogeneous and Nonproportional Effects of Marketing Variables on Brand Switching: An Application of a Discrete Time Duration Model

RePEc: Research Papers in Economics, 1993

Research paper thumbnail of Reviewing the Reviewers: The Impact of Individual Film Critics on Box Office Performance

Social Science Research Network, Feb 1, 2006

Research paper thumbnail of Chain-Wide and Store-Level Analysis for Cross-Category Management

Social Science Research Network, Feb 1, 2006

When planning and implementing their price-promotions strategy, retail chain managers face the ty... more When planning and implementing their price-promotions strategy, retail chain managers face the typical dilemma of "thinking globally, but acting locally." In other words, they must plan their strategy, keeping in mind the global chain-level impact of their promotions, to deliver on the commitments made to manufacturers. At the same time, managers need to make sure that the implementation of such strategy takes into account the fact that each store caters to a different market with different needs and responses to marketing programs. Moreover, the retail chain manager must consider not only how the promotion of a brand affects competing brands and total category sales, but also how it could affect sales in other categories. Our proposed model addresses these two important aspects of chain-wide and store-level cross-category analysis. First, our proposed factor regression model takes store differences and longitudinal market shifts into account, thereby providing the retail chain manager with unbiased global, chain-level estimates. It also provides stable local estimates of cross-category promotion effects at the store level. Second, while allowing this flexibility, our proposed model is parsimonious enough over existing alternatives, making it particularly useful for chain-wide and store-level cross-category analysis. We apply the proposed model to store-level data from one retail chain, comparing it with several competing approaches, and demonstrate that it provides the best balance between flexibility and parsimony. Most importantly, we show that the proposed model provides useful insights regarding cross-category effects at the chain-level, for individual stores, and their patterns across stores.

Research paper thumbnail of Applications of Multivariate Latent Variable Models in Marketing

Research paper thumbnail of Concomitant Variable Latent Class Models for the External Analysis of Choice Data

RePEc: Research Papers in Economics, 1992

Research paper thumbnail of Tailored Interviewing: An Application of Item Response Theory for Personality Measurement

Journal of Personality Assessment, Sep 1, 1989

Research paper thumbnail of Sequential market basket analysis

Marketing Letters, May 22, 2012

Research paper thumbnail of Productivity assessment of multiple retail outlets

Journal of Retailing, Dec 1, 1996

v of u particular retail store depends both on the seller's und the buyers' &ciency. While there ... more v of u particular retail store depends both on the seller's und the buyers' &ciency. While there is often data on euch store's inputs to the production of retail services, the contribution of each store's customers to this process is d#cult to measure, and often goes unmeasured. In the absence of dutu on variation in customer efficient?, across stores. it is difficult to make comparisons of the relative efficiencv of the retailer's operation across stores. In this paper, we propose to solve the problem of missing duta on customer inputs by treating stores as member.7 of dlerent latent classes, where the classes are defined by d$ferences in customer inputs and other market characteristics. We consider the clusterwise estimution of multiple translog costfunctions, which identifio sets of retail outlets operuting under similar conditions und simultaneously estimutes multiple cost jtinctions for these classes. The ef$ciency of each outlet would then be evaluated relative to other.7 in its cluss. which allows.for a more equitable evaluation @'each retail outlet, in comparison to other unirs operating under similar conditions. We apply this upprouch in the evuluation of multiple branches from u commercial bank in Lutin America, and cornpure the eficienc:y measUres obtained,from it with measures obtained from other methods, using the bank's central munager.s' classificution of markets as a benchmurk. Our results indicute that the clustenvise estimation of trun.slog cost functions 1ead.y to u more equituble assessment oj'the brunches, more in tune +vith the market diflerences perceived by the bank managers .

Research paper thumbnail of Clustering Methods

Research paper thumbnail of Profiling Segments

Research paper thumbnail of Segmentation Based on Product Dissimilarity Judgements

Springer eBooks, 2000

Dissimilarity judgements have been represented in the marketing and psychometric literatures as e... more Dissimilarity judgements have been represented in the marketing and psychometric literatures as either spaces or trees. The dominant tree representations have been the ultrametric and the additive trees. We describe an extension of those approaches to accommodate differential points of view of consumer segments, by allowing for different segments that have different perceptions of the stimuli, represented as mixtures of spaces, or mixtures of trees, or mixtures of both.

Research paper thumbnail of Using Voter-Choice Modeling to Plan the Final Campaign in Runoff Elections

Social Science Research Network, 2014

Research paper thumbnail of Legal Services Marketing: An Empirical Investigation of the Forecastability and Possible Interrelationship between Marriage Dissolutions, Personal Bankruptcies, and Unemployment

Developments in marketing science: proceedings of the Academy of Marketing Science, 2015

The following paper examines the longitudinal demand for two legal services, divorces and persona... more The following paper examines the longitudinal demand for two legal services, divorces and personal bankruptcies. For each service this paper presents the appropriate univariate model for forecasting. A causal relationship was suggested by a number of local attorneys in which bankruptcies were the result of untenable divorce settlements. Based upon this theory, the relationship between divorces, personal bankruptcies and an economic variable unemployment is examined.

Research paper thumbnail of Household Life Cycles and Lifestyles in the

Social Science Research Network, 2006

Research paper thumbnail of What Happened to the American 'Middle Class'? Class and Consumption in America

Social Science Research Network, 2014

Research paper thumbnail of A New Framework for Time-Use Analysis

Social Science Research Network, 2012

Research paper thumbnail of General Unobservable Bases: Values and Lifestyles

International series in quantitative marketing, 2000

This article describes selected family values among a national sample of 483 social workers holdi... more This article describes selected family values among a national sample of 483 social workers holding membership in the National Association of Social Workers (NASW). The family values chosen were identified in questions contained in the General Social Survey (GSS) administered to a national sample of United States adults. When compared with this sample (n = 1,974), social workers were more supportive of diverse family forms, more accepting of suicide and abortion, more likely to affirm the effectiveness of same-sex parenting couples, but less likely to affirm hard spanking of children. Controlling for socio-demographic variables, however, differences for a question concerning working mothers with children having warm relationships with their children disappeared, as did other questions about parent/children relationships. Similarly, differences on questions related to suicide and abortion were diminished with controls. Addressed are implications for practice considering family values which differ in most cases from the families' in the general population that social workers will potentially serve.

Research paper thumbnail of Segmentation Methods

International series in quantitative marketing, 2000

Research paper thumbnail of Long-term forecasting with innovation diffusion models: The impact of replacement purchases

Journal of Forecasting, 1987

... Period (x 10-1) (x 10-5) (FIT) (FOR.) Rifrigerators Vacuum cleaners Toasters Electric blanket... more ... Period (x 10-1) (x 10-5) (FIT) (FOR.) Rifrigerators Vacuum cleaners Toasters Electric blankets Refrigerators Vacuum cleaners Toasters Electric blankets 1925-59 1922-56 1922-56 1948-72 1925-59 19 22-5 6 1922-56 1948-72 1.75 1.75 1.75 1.75 15.8 16.1 13.3 15.5 0.190 ...

Research paper thumbnail of Statistical Data Fusion for Cross-Tabulation

Journal of Marketing Research, Nov 1, 1997

Take-down policy If you believe that this document breaches copyright please contact us providing... more Take-down policy If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.

Research paper thumbnail of Research Note Heterogeneous and Nonproportional Effects of Marketing Variables on Brand Switching: An Application of a Discrete Time Duration Model

RePEc: Research Papers in Economics, 1993

Research paper thumbnail of Reviewing the Reviewers: The Impact of Individual Film Critics on Box Office Performance

Social Science Research Network, Feb 1, 2006

Research paper thumbnail of Chain-Wide and Store-Level Analysis for Cross-Category Management

Social Science Research Network, Feb 1, 2006

When planning and implementing their price-promotions strategy, retail chain managers face the ty... more When planning and implementing their price-promotions strategy, retail chain managers face the typical dilemma of "thinking globally, but acting locally." In other words, they must plan their strategy, keeping in mind the global chain-level impact of their promotions, to deliver on the commitments made to manufacturers. At the same time, managers need to make sure that the implementation of such strategy takes into account the fact that each store caters to a different market with different needs and responses to marketing programs. Moreover, the retail chain manager must consider not only how the promotion of a brand affects competing brands and total category sales, but also how it could affect sales in other categories. Our proposed model addresses these two important aspects of chain-wide and store-level cross-category analysis. First, our proposed factor regression model takes store differences and longitudinal market shifts into account, thereby providing the retail chain manager with unbiased global, chain-level estimates. It also provides stable local estimates of cross-category promotion effects at the store level. Second, while allowing this flexibility, our proposed model is parsimonious enough over existing alternatives, making it particularly useful for chain-wide and store-level cross-category analysis. We apply the proposed model to store-level data from one retail chain, comparing it with several competing approaches, and demonstrate that it provides the best balance between flexibility and parsimony. Most importantly, we show that the proposed model provides useful insights regarding cross-category effects at the chain-level, for individual stores, and their patterns across stores.

Research paper thumbnail of Applications of Multivariate Latent Variable Models in Marketing

Research paper thumbnail of Concomitant Variable Latent Class Models for the External Analysis of Choice Data

RePEc: Research Papers in Economics, 1992

Research paper thumbnail of Tailored Interviewing: An Application of Item Response Theory for Personality Measurement

Journal of Personality Assessment, Sep 1, 1989

Research paper thumbnail of Sequential market basket analysis

Marketing Letters, May 22, 2012

Research paper thumbnail of Productivity assessment of multiple retail outlets

Journal of Retailing, Dec 1, 1996

v of u particular retail store depends both on the seller's und the buyers' &ciency. While there ... more v of u particular retail store depends both on the seller's und the buyers' &ciency. While there is often data on euch store's inputs to the production of retail services, the contribution of each store's customers to this process is d#cult to measure, and often goes unmeasured. In the absence of dutu on variation in customer efficient?, across stores. it is difficult to make comparisons of the relative efficiencv of the retailer's operation across stores. In this paper, we propose to solve the problem of missing duta on customer inputs by treating stores as member.7 of dlerent latent classes, where the classes are defined by d$ferences in customer inputs and other market characteristics. We consider the clusterwise estimution of multiple translog costfunctions, which identifio sets of retail outlets operuting under similar conditions und simultaneously estimutes multiple cost jtinctions for these classes. The ef$ciency of each outlet would then be evaluated relative to other.7 in its cluss. which allows.for a more equitable evaluation @'each retail outlet, in comparison to other unirs operating under similar conditions. We apply this upprouch in the evuluation of multiple branches from u commercial bank in Lutin America, and cornpure the eficienc:y measUres obtained,from it with measures obtained from other methods, using the bank's central munager.s' classificution of markets as a benchmurk. Our results indicute that the clustenvise estimation of trun.slog cost functions 1ead.y to u more equituble assessment oj'the brunches, more in tune +vith the market diflerences perceived by the bank managers .

Research paper thumbnail of Clustering Methods

Research paper thumbnail of Profiling Segments

Research paper thumbnail of Segmentation Based on Product Dissimilarity Judgements

Springer eBooks, 2000

Dissimilarity judgements have been represented in the marketing and psychometric literatures as e... more Dissimilarity judgements have been represented in the marketing and psychometric literatures as either spaces or trees. The dominant tree representations have been the ultrametric and the additive trees. We describe an extension of those approaches to accommodate differential points of view of consumer segments, by allowing for different segments that have different perceptions of the stimuli, represented as mixtures of spaces, or mixtures of trees, or mixtures of both.

Research paper thumbnail of Using Voter-Choice Modeling to Plan the Final Campaign in Runoff Elections

Social Science Research Network, 2014

Research paper thumbnail of Legal Services Marketing: An Empirical Investigation of the Forecastability and Possible Interrelationship between Marriage Dissolutions, Personal Bankruptcies, and Unemployment

Developments in marketing science: proceedings of the Academy of Marketing Science, 2015

The following paper examines the longitudinal demand for two legal services, divorces and persona... more The following paper examines the longitudinal demand for two legal services, divorces and personal bankruptcies. For each service this paper presents the appropriate univariate model for forecasting. A causal relationship was suggested by a number of local attorneys in which bankruptcies were the result of untenable divorce settlements. Based upon this theory, the relationship between divorces, personal bankruptcies and an economic variable unemployment is examined.

Research paper thumbnail of Household Life Cycles and Lifestyles in the

Social Science Research Network, 2006

Research paper thumbnail of What Happened to the American 'Middle Class'? Class and Consumption in America

Social Science Research Network, 2014

Research paper thumbnail of A New Framework for Time-Use Analysis

Social Science Research Network, 2012

Research paper thumbnail of General Unobservable Bases: Values and Lifestyles

International series in quantitative marketing, 2000

This article describes selected family values among a national sample of 483 social workers holdi... more This article describes selected family values among a national sample of 483 social workers holding membership in the National Association of Social Workers (NASW). The family values chosen were identified in questions contained in the General Social Survey (GSS) administered to a national sample of United States adults. When compared with this sample (n = 1,974), social workers were more supportive of diverse family forms, more accepting of suicide and abortion, more likely to affirm the effectiveness of same-sex parenting couples, but less likely to affirm hard spanking of children. Controlling for socio-demographic variables, however, differences for a question concerning working mothers with children having warm relationships with their children disappeared, as did other questions about parent/children relationships. Similarly, differences on questions related to suicide and abortion were diminished with controls. Addressed are implications for practice considering family values which differ in most cases from the families' in the general population that social workers will potentially serve.

Research paper thumbnail of Segmentation Methods

International series in quantitative marketing, 2000

Research paper thumbnail of Kamakura's Analytic Tools for Excel

This short document describes a suite of business-analytics tools for Excel I developed for educa... more This short document describes a suite of business-analytics tools for Excel I developed for educational purposes. This suite is free for academic use. Excel is in fact used only as an interface to grab data and display results; all the number crunching is done by a collection of reasonably optimized libraries. The suite contains a wide range of analytical tools for text-mining, data manipulation, data display and data analysis.

Research paper thumbnail of Preferences revealed by votes are more useful than those declared in polls

Much has been said in the media about the validity of stated preferences in second-round intentio... more Much has been said in the media about the validity of stated preferences in second-round intention polls. However, stated preferences are less important in the second round because: 1) stated preferences are essential in the first round due to the lack because of other information, but in the second round one can use revealed preferences from first-round votes; 2) revealed preferences were formed during a long campaign and are less susceptible to changes in the short campaign for the second round; 3) revealed preferences are obtained for each precinct, allowing candidates to plan their campaigns at a level unimaginable for stated preference.

Research paper thumbnail of Preferences revealed by votes are more useful than those declared in polls

Much has been said in the media about the validity of stated preferences in second-round intentio... more Much has been said in the media about the validity of stated preferences in second-round intention polls. However, stated preferences are less important in the second round because: 1) stated preferences are essential in the first round due to the lack because of other information, but in the second round one can use revealed preferences from first-round votes; 2) revealed preferences were formed during a long campaign and are less susceptible to changes in the short campaign for the second round; 3) revealed preferences are obtained for each precinct, allowing candidates to plan their campaigns at a level unimaginable for stated preference.

Research paper thumbnail of A longitudinal cross-product analysis of media-budget allocations: How economic and technological disruptions affected media choices across industries

The advertising and communications literature has already provided multiple frameworks to help ad... more The advertising and communications literature has already provided multiple frameworks to help advertisers choose the proper media for the types of products and services they wish to promote. We attempt to consolidate these competing (but consistent) frameworks into a common set of media prescriptions, and utilize longitudinal media-budget data for 143 products/services in a major media market (Spain) to verify whether advertisers have conformed to the advice provided by the literature. We also use this long cross-product history of media-budget allocations to study how advertisers reacted to economic (the Great Recession of 2008) and technological (the emergence of the Internet as an advertising medium) shifts in their media allocations.