Contains household characteristics Variables: hh id household identifier hh income household inco... more Contains household characteristics Variables: hh id household identifier hh income household income category hhsize number of household members insample 0/1 variable indicating whether this household was used for the in sample data outofsample 0/1 variable indicating whether this household was used for the out of sample data
International Series in Quantitative Marketing, 2017
Decisions of individuals are central to almost all marketing questions. In some cases, it is most... more Decisions of individuals are central to almost all marketing questions. In some cases, it is most sensible to model these decisions at an aggregate level, for example, using models for sales or market shares (see, for example, Chap. 7 in Vol. I). In many other cases, it is the behavior of the individuals themselves that are the key object of interest. For example, we can think of modeling the decisions of customers at a retailer (Mela etal. 1997; Zhang and Wedel 2009), modeling the behavior of website visitors (Montgomery etal. 2004), or modeling choices made by customers of an insurance firm (Donkers etal. 2007).
markdownabstract__Abstract__ Pretty much every modern organisation collects a mountain of data on... more markdownabstract__Abstract__ Pretty much every modern organisation collects a mountain of data on a daily basis as it goes about its business. But all that data is of little real value unless it is properly analysed and used to anticipate client behaviour and needs.
Misspecification tests for Multinomial Logit [MNL] models are known to have low power or large si... more Misspecification tests for Multinomial Logit [MNL] models are known to have low power or large size distortion. We propose two new misspecification tests. Both use that preferences across binary pairs of alternatives can be described by independent binary logit models when MNL is true. The first test compares Composite Likelihood parameter estimates based on choice pairs with standard Maximum Likelihood estimates using a Hausman (1978) test. The second tests for overidentification in a GMM framework using more pairs than necessary. A Monte Carlo study shows that the GMM test is in general superior with respect to power and has correct size
Contains household level purchase histories Variables: id household identifier date date of purch... more Contains household level purchase histories Variables: id household identifier date date of purchase vol purchased volume in ounces brand brand number The data we use are based on the so-called ERIM database, which is collected by A.C.Nielsen. The data span the years 1986 to 1988, and the particular subset we use concerns purchases of detergent by households in Sioux Falls (South Dakota, USA). For our purposes, the data are aggregated to the brand level. Brand coding: 1=Cheer 2=Oxidol 3=Surf 4=Tide 5=Wisk 6=Rest
Uncertainty pervades most aspects of life. From selecting a new technology to choosing a career, ... more Uncertainty pervades most aspects of life. From selecting a new technology to choosing a career, decision makers often ignore the outcomes of their decisions. In the last decade a new paradigm has emerged in behavioral decision research in which decisions are “experienced” rather than “described”, as in standard decision theory. The dominant finding from studies using the experience-based paradigm is that decisions from experience exhibit "black swan effect", i.e. the tendency to neglect rare events. Under prospect theory, this results in an experience-description gap. We show that several tentative conclusions can be drawn from our interdisciplinary examination of the putative experience-description gap in decision under uncertainty. Several insights are discussed. First, while the major source of under-weighting of rare events may be sampling error, it is argued that a robust experience-description gap remains when these factors are not at play. Second, the residual expe...
To comprehend the competitive structure of a market, it is important to understand the short-run ... more To comprehend the competitive structure of a market, it is important to understand the short-run and long-run effects of the marketing mix on market shares. A useful model to link market shares with marketing-mix variables, like price and promotion, is the market share attraction model. In this paper we put forward a representation of the attraction model, which allows for explicitly disentangling long-run from short-run effects. Our model also contains a second level, in which these dynamic effects are correlated with various brand and product category characteristics. Based on the findings in for example Nijs et al. (2001), we postulate the expected signs of these correlations. We fit our resultant Hierarchical Bayes attraction model to data on seven categories in two geographical areas. This data set spans a total of 50 brands. Our main finding is that, in absolute sense, the short-run price elasticity usually exceeds the long-run effect. Moreover, we find that the longrun price ...
We propose a simulation-based technique to calculate impulse-response functions and their confide... more We propose a simulation-based technique to calculate impulse-response functions and their confidence intervals in a market share attraction model [MCI]. As an MCI model implies a reduced form model for the logs of relative market shares, simulation techniques have to be used to obtain the impulse-responses for the levels of the market shares. We apply the technique to an MCI
Scanner data for fast moving consumer goods typically amount to panels of time series where both ... more Scanner data for fast moving consumer goods typically amount to panels of time series where both N and T are large. To reduce the number of parameters and to shrink parameters towards plausible and interpretable values, multi-level models turn out to be useful. Such models contain in the second level a stochastic model to describe the parameters in the first
Contains household characteristics Variables: hh id household identifier hh income household inco... more Contains household characteristics Variables: hh id household identifier hh income household income category hhsize number of household members insample 0/1 variable indicating whether this household was used for the in sample data outofsample 0/1 variable indicating whether this household was used for the out of sample data
International Series in Quantitative Marketing, 2017
Decisions of individuals are central to almost all marketing questions. In some cases, it is most... more Decisions of individuals are central to almost all marketing questions. In some cases, it is most sensible to model these decisions at an aggregate level, for example, using models for sales or market shares (see, for example, Chap. 7 in Vol. I). In many other cases, it is the behavior of the individuals themselves that are the key object of interest. For example, we can think of modeling the decisions of customers at a retailer (Mela etal. 1997; Zhang and Wedel 2009), modeling the behavior of website visitors (Montgomery etal. 2004), or modeling choices made by customers of an insurance firm (Donkers etal. 2007).
markdownabstract__Abstract__ Pretty much every modern organisation collects a mountain of data on... more markdownabstract__Abstract__ Pretty much every modern organisation collects a mountain of data on a daily basis as it goes about its business. But all that data is of little real value unless it is properly analysed and used to anticipate client behaviour and needs.
Misspecification tests for Multinomial Logit [MNL] models are known to have low power or large si... more Misspecification tests for Multinomial Logit [MNL] models are known to have low power or large size distortion. We propose two new misspecification tests. Both use that preferences across binary pairs of alternatives can be described by independent binary logit models when MNL is true. The first test compares Composite Likelihood parameter estimates based on choice pairs with standard Maximum Likelihood estimates using a Hausman (1978) test. The second tests for overidentification in a GMM framework using more pairs than necessary. A Monte Carlo study shows that the GMM test is in general superior with respect to power and has correct size
Contains household level purchase histories Variables: id household identifier date date of purch... more Contains household level purchase histories Variables: id household identifier date date of purchase vol purchased volume in ounces brand brand number The data we use are based on the so-called ERIM database, which is collected by A.C.Nielsen. The data span the years 1986 to 1988, and the particular subset we use concerns purchases of detergent by households in Sioux Falls (South Dakota, USA). For our purposes, the data are aggregated to the brand level. Brand coding: 1=Cheer 2=Oxidol 3=Surf 4=Tide 5=Wisk 6=Rest
Uncertainty pervades most aspects of life. From selecting a new technology to choosing a career, ... more Uncertainty pervades most aspects of life. From selecting a new technology to choosing a career, decision makers often ignore the outcomes of their decisions. In the last decade a new paradigm has emerged in behavioral decision research in which decisions are “experienced” rather than “described”, as in standard decision theory. The dominant finding from studies using the experience-based paradigm is that decisions from experience exhibit "black swan effect", i.e. the tendency to neglect rare events. Under prospect theory, this results in an experience-description gap. We show that several tentative conclusions can be drawn from our interdisciplinary examination of the putative experience-description gap in decision under uncertainty. Several insights are discussed. First, while the major source of under-weighting of rare events may be sampling error, it is argued that a robust experience-description gap remains when these factors are not at play. Second, the residual expe...
To comprehend the competitive structure of a market, it is important to understand the short-run ... more To comprehend the competitive structure of a market, it is important to understand the short-run and long-run effects of the marketing mix on market shares. A useful model to link market shares with marketing-mix variables, like price and promotion, is the market share attraction model. In this paper we put forward a representation of the attraction model, which allows for explicitly disentangling long-run from short-run effects. Our model also contains a second level, in which these dynamic effects are correlated with various brand and product category characteristics. Based on the findings in for example Nijs et al. (2001), we postulate the expected signs of these correlations. We fit our resultant Hierarchical Bayes attraction model to data on seven categories in two geographical areas. This data set spans a total of 50 brands. Our main finding is that, in absolute sense, the short-run price elasticity usually exceeds the long-run effect. Moreover, we find that the longrun price ...
We propose a simulation-based technique to calculate impulse-response functions and their confide... more We propose a simulation-based technique to calculate impulse-response functions and their confidence intervals in a market share attraction model [MCI]. As an MCI model implies a reduced form model for the logs of relative market shares, simulation techniques have to be used to obtain the impulse-responses for the levels of the market shares. We apply the technique to an MCI
Scanner data for fast moving consumer goods typically amount to panels of time series where both ... more Scanner data for fast moving consumer goods typically amount to panels of time series where both N and T are large. To reduce the number of parameters and to shrink parameters towards plausible and interpretable values, multi-level models turn out to be useful. Such models contain in the second level a stochastic model to describe the parameters in the first
Uploads
Papers