Modeling social interactions: Identification, empirical methods and policy implications

Hartmann, Wesley R.; Manchanda, Puneet; Nair, Harikesh S.; Bothner, Matthew S.; Dodds, Peter Sheridan; Godes, David; Hosanagar, Kartik; Tucker, Catherine M.

doi:10.1007/s11002-008-9048-z

Cited by 198 publications

(100 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Third, to control for simultaneity, in accordance with Hartmann et al (2008), we use an exclusion restriction that imposes a temporal ordering i.e., the focal individual's behavior in time t is affected by the social network behavior up to time t-1. That is, we use the lagged social network variable in accordance with Manski (1993) and other work that has studied the impact of the social network effect on user behavior (Van den Bulte and Lilien 2001, Iyengar et al 2010 Lagging avoids the simultaneity problem, unless (1) people are forward-looking not only about their own behavior but also that of others and (2) social ties over which influence flows are symmetric (Hartmann et al 2008, Iyengar et al 2010.…”

Section: Identification Of the Social Network Endogeneitymentioning

confidence: 99%

“…That is, we use the lagged social network variable in accordance with Manski (1993) and other work that has studied the impact of the social network effect on user behavior (Van den Bulte and Lilien 2001, Iyengar et al 2010 Lagging avoids the simultaneity problem, unless (1) people are forward-looking not only about their own behavior but also that of others and (2) social ties over which influence flows are symmetric (Hartmann et al 2008, Iyengar et al 2010. The first condition is quite unlikely in large networks such as ours, and the second condition does not hold in our data.…”

Section: Identification Of the Social Network Endogeneitymentioning

confidence: 99%

See 1 more Smart Citation

An Empirical Analysis of User Content Generation and Usage Behavior on the Mobile Internet

2011

View full text Add to dashboard Cite

We quantify how user mobile Internet usage relates to unique characteristics of the mobile Internet. In particular, we focus on examining how the mobile-phone-based content generation behavior of users relates to content usage behavior. The key objective is to analyze whether there is a positive or negative interdependence between the two activities. We use a unique panel data set that consists of individual-level mobile Internet usage data that encompass individual multimedia content generation and usage behavior. We combine this knowledge with data on user calling patterns, such as duration, frequency, and locations from where calls are placed, to construct their social network and to compute their geographical mobility. We build an individuallevel simultaneous equation panel data model that controls for the different sources of endogeneity of the social network. We find that there is a negative and statistically significant temporal interdependence between content generation and usage. This finding implies that an increase in content usage in the previous period has a negative impact on content generation in the current period and vice versa. The marginal effect of this interdependence is stronger on content usage (up to 8.7%) than on content generation (up to 4.3%). The extent of geographical mobility of users has a positive effect on their mobile Internet activities. Users more frequently engage in content usage compared to content generation when they are traveling. In addition, the variance of user mobility has a stronger impact on their mobile Internet activities than does the mean. We also find that the social network has a strong positive effect on user behavior in the mobile Internet. These analyses unpack the mechanisms that stimulate user behavior on the mobile Internet. Implications for shaping user mobile Internet usage behavior are discussed. Sang-Pil HanPostdoctoral Researcher, Stern School of Business, New York University AbstractWe quantify how users' mobile Internet use is related to some unique characteristics of the mobile Internet space like usage-based data pricing, the extent of their geographical mobility and their social network behavior. We use a unique panel dataset consisting of individual-level mobile Internet usage data encompassing their multimedia content uploading and downloading behavior along with detailed data on their voice and text calls, and demographics. We build and estimate an individual-level simultaneous equations panel data model using three-stage least-squares (3SLS) after controlling for the endogeneity of the social network. We find that there exists negative temporal interdependence between the content generation and usage behavior for a given user. While the extent of geographical mobility of users is positively associated with their mobile Internet activities, users more frequently engage in content downloading compared to content uploading when they travel. We find statistically significant social network effects that are robust across model specific...

show abstract

Section: Identification Of the Social Network Endogeneitymentioning

confidence: 99%

Section: Identification Of the Social Network Endogeneitymentioning

confidence: 99%

An Empirical Analysis of User Content Generation and Usage Behavior on the Mobile Internet

2011

View full text Add to dashboard Cite

show abstract

“…Van der Merwe [11] described its effect on the role of opinion leaders. According to various authors [13,14], both opinion spreading and speed of innovation adoption depend on the considered network structure and density. Second, the interest of adopting a non-local approach is backed by several Marketing studies like [15], which, following a stream of Sociology studies, emphasized the necessity of taking sub-networks or cliques into account.…”

Section: Network Analysis In Business Sciencementioning

confidence: 99%

Informative Value of Individual and Relational Data Compared Through Business-Oriented Community Detection

Labatut¹,

Balasque²

2012

Lecture Notes in Social Networks

View full text Add to dashboard Cite

Despites the great interest caused by social networks in Business Science, their analysis is rarely performed in both a global and systematic way in this field. This could be explained by the fact their practical extraction is a difficult and costly task. One may ask if equivalent information could be retrieved from less expensive, individual data (i.e. describing single individuals instead of pairs). In this work, we try to address this question through group detection. We gather both types of data from a population of students, estimate groups separately using individual and relational data, and obtain sets of clusters and communities, respectively. We measure the overlap between clusters and communities, which turns out to be relatively weak. We also define a predictive model, allowing us to identify the most discriminant attributes for the communities, and to reveal the presence of a tenuous link between the relational and individual data. Our results indicate both types of data convey considerably different information in this specific context, and can therefore be considered as complementary. To emphasize the interest of communities for Business Science, we also conduct an analysis based on hobbies and purchased brands.

show abstract

“…Unless we have more detailed information about how frequently the consumers update their estimate of installed base, the choice of perception lag will be ad hoc and in practice determined by the frequency of data. Another problem, pointed out by Hartmann et al (2008) in relation to the Bass (1969) model, is that the relationship between the installed base and current network might be driven by serial correlation in sales-related unobservables over time. We address these concerns in the empirical section of the paper by comparing the estimated model using various perception lags.…”

Section: Functional Specification and Identification Issuesmentioning

confidence: 99%

Estimating Critical Mass in the Global Cellular Telephony Market

Grajek

Kretschmer

2010

SSRN Journal

View full text Add to dashboard Cite

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Critical Mass is a common feature of technology diffusion processes. We develop a structural model of demand with network effects to provide a rigorous definition of critical mass as a function of installed base, price and network effects. Using data from the digital cellular telephony market, we identify critical mass phenomena and find that differences in the critical mass point in different countries rest mainly on different countries' socioeconomic characteristics and the extent of competition in a country. This application illustrates that our demand model can be operationalized easily and can generate theoretically grounded empirical insights about critical mass phenomena. Terms of use: Documents in EconStor may

show abstract

Modeling social interactions: Identification, empirical methods and policy implications

Abstract: Social interactions, Networking, Social multiplier, Peer effects,

Cited by 198 publications

References 42 publications

An Empirical Analysis of User Content Generation and Usage Behavior on the Mobile Internet

An Empirical Analysis of User Content Generation and Usage Behavior on the Mobile Internet

Informative Value of Individual and Relational Data Compared Through Business-Oriented Community Detection

Estimating Critical Mass in the Global Cellular Telephony Market

Contact Info

Product

Resources

About