Khim Yong Goh

Beyond the Endogeneity Bias: The Effect of Unmeasured Brand Characteristics on Household-Level Brand Choice Models

We investigate the role of potential weekly brand-specific characteristics that influence consumer choices, but are unobserved or unmeasurable by the researcher. We use an empirical approach, based on the estimation methods used for standard random coefficients logit models, to account for the presence of such unobserved attributes. Using household scanner panel data, we find evidence that ignoring such time-varying latent (to the researcher) characteristics can lead to two types of problems. First, consistent with previous literature, we find that these unobserved characteristics may lead to biased estimates of the mean price response parameters. This argument is based on a form of price endogeneity. If marketing managers set prices based on consumer willingness to pay, then the observed prices will likely be correlated with the latent (to the researcher) brand characteristics. We resolve this problem by using an instrumental variables procedure. Our findings suggest that simply ignoring these attributes may also lead to larger estimates of the variance in the heterogeneity distribution of preferences and price sensitivities across households. This could overstate the benefits from marketing activities such as household-level targeting. We resolve the problem by using weekly brand intercepts, embedded in a random coefficients brand choice model, to control for weekly brand-specific characteristics, while accounting for household heterogeneity. Overall, our results extend the finding on the endogeneity bias from the mean of the heterogeneity distribution (i.e., the price effect) to include the variance of that distribution.

Newspaper Reports and Consumer Choice: Evidence from the Do Not Call Registry

Despite annual expenditures on public relations exceeding

An investigation of online group-buying institution and buyer behavior

19.42 billion, U.S. businesses lack practical guidance about the effectiveness of publicity in mass media. Here, we assemble a rich and novel data set to gauge the impact of news reports on consumer sign-ups with the U.S. Do Not Call (DNC) Registry. Using multiple identification strategies, we found robust evidence that news reports increased consumer registrations. Specifically, a 1% increase in the number of news reports increased DNC registrations by 0.018%. The impact increased with mention of the toll-free telephone number and URL, but decreased with the length of the headline and main text. Furthermore, we found evidence that reports affect behavior through persuasion as well as information---the impact on registration was higher for reports that mentioned the number of other people registering. Finally, the impact of news reports on consumer registration was stronger in national than local newspapers and in politically neutral and Democrat than Republican newspapers. This paper was accepted by Pradeep Chintagunta and Preyas Desai, special issue editors. This paper was accepted by Pradeep Chintagunta and Preyas Desai, special issue editors.

How big data and analytics reshape the wearable device market – the context of e-health

This study draws on interdependency theory to propose and assess the effects of two artifacts - conditional purchase and information cue - on decisional choice in the online group-buying context. Our results suggest that buyers presented with conditional purchase options (i.e., of not honoring the purchase when the expected discount price is not met) are more willing to make a purchase choice (i.e., deviate from an inactive inertia). Counter-intuitively, provision of information cues (i.e., information about procurement actions of the other buyers) appears to induce inaction. However, when a choice has to be made between a riskier and a less risky choice, the presence of information cues leads to a higher propensity for the riskier choice. Implications for theory and practice are further discussed.

Evaluating Longitudinal Success of Open Source Software Projects: A Social Network Perspective

The wearable device can be a key link between health care and big data and analytics (BDA). The benefits of BDA in health care have been widely acknowledged, but the uncertainty of the implementation of BDA has led some firms to hesitate in adopting this technology. In this research, we are keen to answer the key questions of whether the wearable device firms would adopt the BDA strategy, and how much effort they would put into it. We propose a competition model between the wearable device firms with and without BDA strategies, and consider the consumer’s preference towards BDA and network effects. Our model demonstrates that the investment on BDA directly affects the firm’s equilibrium price, market share and profit and at the same time, this strategy also affects the rival’s performances. When the firm with BDA strategy adopts different competition strategy: conservative or expansive, the outcomes of market are different. We also find that different market structures, fully covered and partially covered, have different impacts on the firms’ competition when the consumers have heterogeneous preference on BDA strategy.

The demand effects of product recommendation networks: an empirical analysis of network diversity and stability

To date, numerous open source projects are hosted on many online repositories. While some of these projects are active and thriving, some projects are either languishing or showing no development activities at all. This phenomenon thus begs the important question of what are the influential factors that affect the success of open source projects. In a quest to deepen our understanding of the evolution of open source projects, this research aims to analyze the success of open source projects by using the theoretical lens of social network analysis. Based on extensive analyses of data collected from online repositories, we study the impact of the communication patterns of software development teams on the demand and supply outcomes of these projects, while accounting for project-specific characteristics. Using panel data analysis of data over 13 months, we find significant impacts of communication patterns on project outcomes over the long term.

Privacy and Marketing Externalities: Evidence from Do Not Call

With the increasing popularity of product recommendation networks in e-commerce, researchers and practitioners are eager to understand how they can strategically manage product assortments through the manipulation of such networks to drive demand. We examine product recommendation networks in e-commerce to investigate how the demand of a product is influenced by product network attributes in terms of network diversity and network stability. We also examine whether the demand of a product is influenced by both the incoming network and the outgoing network, and if the effects differ between co-view and co-purchase recommendation networks. Using data from Tmall.com for four product categories, we apply linear panel data models to examine the impact of network diversity and network stability on product demand, controlling for relevant factors at the individual product, pricing, product network, product category, and time unit levels. Importantly, we account for implicit demand correlation (i.e., substitution and complementarity) and potential simultaneity of demand and network structures. We unravel several important findings. First, a 1% increase in the category diversity of the incoming (outgoing) co-purchase network of a product is associated with a 0.011% (0.012%) increase (decrease) in the products demand. Second, a 1% increase in the stability of the outgoing co-purchase network is associated with a 0.012% decrease in demand. Third, the demand effects of network diversity and stability are both stronger in the co-purchase network, compared to their insignificant effects in the co-view network. Thus, this research provides theoretical contributions in terms of the economic effects of product recommendation networks through its focus on network diversity and stability in incoming/ outgoing and co-view/co-purchase networks. We also provide notable implications for recommendation-based product marketing and recommendation systems design.

When do sellers bifurcate from Electronic Multisided Platforms? The effects of customer demand, competitive intensity, and service differentiation

If not well targeted, advertising and direct marketing inflict nuisance and inconvenience on consumers. Theoretical analyses predict that consumer actions to avoid advertising impose externalities on other consumers. We investigate the extent of such externalities in the context of the U.S. Do Not Call (DNC) registry by exploiting the exogenous timing of the enforcement of the registry. Supported by multiple robustness tests, and validation and falsification exercises, we conclude that consumer DNC registrations imposed externalities on other consumers. An increase in the first wave of registrations by 1% was associated with a 3.1% increase in subsequent registrations. This effect was stronger in larger and more educationally or racially heterogeneous markets. The externality was possibly due to unregistered consumers being more receptive to telemarketing and telemarketers increasing calls to them. Our results suggest that managers should facilitate consumer opt-out, especially in larger and more educationally or racially heterogeneous markets.Data, as supplemental material, are available at http://dx.doi.org/10.1287/mnsc.2014.2051 . This paper was accepted by J. Miguel Villas-Boas, marketing .

Response to Buyout Options in Internet Auctions

In todays e-market, many sellers on Electronic Multisided Platforms (EMPs) conduct channel bifurcation, i.e., starting their proprietary websites while maintaining presences on EMPs. This study explores the antecedents of the timing that a seller bifurcates from EMPs. We hypothesize that a sellers customer demand has a U-shaped effect on its EMP membership duration before bifurcation, while competitive intensity has an inverted U-shaped effect. Service differentiation has a negative effect and further dampens the curvilinear effects of customer demand and competitive intensity. Using the data of 422 booksellers on Taobao.com and the accelerated failure time duration model, we found substantial support for our hypotheses.

Consumer Segmentation and the Information Rule of Online Reviews in Horizontally Differentiated Product Markets

A buyout option allows a bidder to acquire an auctioned product immediately at a posted price without going through the hassle of monitoring the auction process and submitting bids. This study examines the influence of three forms of buyout options, namely, temporary without reserve price (TempNR) (i.e., option ceases to exist once the first bid is received), temporary with reserve price (TempR) (i.e., option ceases to exist once the bid received is equal to or more than the reserve price), and permanent (Perm) (i.e., option is available until the end of the auction or when a bidder chooses to buy out) on the decision of a bidder in Internet auctions. The first two auction forms can be labeled as temporary buyout options. By using two studies, we demonstrate that a bidder is more likely to be averse to losses and exhibits a higher propensity to buy out in the presence of Perm. However, when faced with temporary buyout options (i.e., TempNR or TempR), a bidder would prevent other bidders from prematurely ending the auction by attempting to “remove” the buyout option.