nep-big New Economics Papers
on Big Data
Issue of 2017‒09‒03
five papers chosen by
Tom Coupé
University of Canterbury

  1. Media and crime perceptions: Evidence from Mexico By Aurora Alejandra Ramirez-Alvarez
  2. Robust Determinants of Bilateral Trade By Marianne Baxter
  3. Heterogeneous Employment Effects of Job Search Programmes: A Machine Learning Approach By Knaus, Michael C.; Lechner, Michael; Strittmatter, Anthony
  4. P2P Lending: Information Externalities, Social Networks and Loans' Substitution By Faia, Ester; Paiella, Monica
  5. Invention Machines: How Control Instruments and Information Technologies Drove Global Technologigal Progress over a Century of Invention By Koutroumpis, Pantelis; Leiponen, Aija; Thomas, Llewellyn D W

  1. By: Aurora Alejandra Ramirez-Alvarez (El Colegio de México)
    Abstract: This paper examines whether individuals' crime perceptions and crime avoidance behavior respond to changes in crime news coverage. I use data from Mexico, where major media groups agreed to reduce coverage of violence in March 2011. Using a unique dataset on national news content and machine learning techniques, I document that after the Agreement, crime news coverage on television, radio, and newspapers decreases relative to the national homicide rate. Using survey data, I find robust evidence that crime perceptions respond to this change in content. After the Agreement, individuals with higher media exposure are less likely to report that they feel insecure and that their country, state, or municipality is insecure, relative to individuals with lower media exposure. However, I show that these changes in crime perceptions are not accompanied by changes in crime avoidance behavior (i.e. no longer going out at night for fear of being a victim of crime), or at least that e ects are much smaller.
    Keywords: mass media; persuasion; crime perception; Mexico.
    JEL: D83 K42 L82
    Date: 2017–05
  2. By: Marianne Baxter (Boston University)
    Abstract: What are the policies and country-level conditions which best explain bilateral trade flows between countries? The beloved “gravity model” has had widespread empirical success, yet there is little guidance on which set of explanatory variables appropriately balances in-sample fit against out-of-sample prediction. Toward that end, this paper examines the problem of model selection, using modern empirical methods, in two steps. First, we use data from 1970 to 2000 as a baseline period to estimate the gravity model according three model selection methods – Lasso regularized regression, Bayesian Model Averaging, and Extreme Bound Analysis. We consider a wide variety of candidate variables commonly found in empirical gravity models. We find that about ¼ of commonly used variables found in empirical gravity equations are not robust. We explore the sensitivity of the prediction results to the specific regularization method and the choice of tuning parameters. We find surprising consistency in the set of variables selected by the various measured considered.
    Date: 2017
  3. By: Knaus, Michael C. (University of St. Gallen); Lechner, Michael (University of St. Gallen); Strittmatter, Anthony (University of St. Gallen)
    Abstract: We systematically investigate the effect heterogeneity of job search programmes for unemployed workers. To investigate possibly heterogeneous employment effects, we combine non-experimental causal empirical models with Lasso-type estimators. The empirical analyses are based on rich administrative data from Swiss social security records. We find considerable heterogeneities only during the first six months after the start of training. Consistent with previous results of the literature, unemployed persons with fewer employment opportunities profit more from participating in these programmes. Furthermore, we also document heterogeneous employment effects by residence status. Finally, we show the potential of easy-to-implement programme participation rules for improving average employment effects of these active labour market programmes.
    Keywords: machine learning, individualized treatment effects, conditional average treatment effects, active labour market policy
    JEL: J68 H43 C21
    Date: 2017–08
  4. By: Faia, Ester; Paiella, Monica
    Abstract: Despite the lack of delegated monitor and of collateral guarantees P2P lending platforms exhibit relatively low loan and delinquency rates. The adverse selection is indeed mitigated by a new screening technology (information processing through machine learning) that provides costless public signals. Using data from Prosper and Lending Club we show that loans' spreads, proxing asymmetric information, decline with credit scores or hard information indicators and with indications from "group ties" (soft information from social networks). Also an increase in the risk of bank run in the traditional banking sector increases participation in the P2P markets and reduces their rates (substitution effect). We rationalize this evidence with a dynamic general equilibrium model where lenders and borrowers choose between traditional bank services (subject to the risk of bank runs and early liquidation) and P2P markets (which clear at a pooling price due to asymmetric information, but where public signals facilitate screening).
    Keywords: liquidity shocks; peer-to-peer lending; pooling equilibria; signals; value of information
    JEL: G11 G23
    Date: 2017–08
  5. By: Koutroumpis, Pantelis; Leiponen, Aija; Thomas, Llewellyn D W
    Abstract: Abstract Inventions depend on skills, experience, and information exchange. Information is shared among individuals and organizations both intentionally and unintentionally. Unintentional flows of knowledge, or knowledge spillovers, are viewed as an integral element of technological progress. However, little is known about the overall patterns of knowledge flows across technology sectors or over long periods of time. This paper explores whether it is possible to identify “invention machines” – technologies that help create new inventions in a wide range of other sectors – and whether shifts in the patterns of knowledge flows can predict future technological change. In the spirit of big data we analyze the entire PatStat database of 90 million published patents from 160 patent offices over a century of invention and exploit variation within and across countries and technology fields over time. The direction and intensity of knowledge spillovers measured from prior-art citations highlight the transition from mechanical to electrical instruments, especially industrial control systems, and the rise of information and communication technologies as “invention machines” after 1970. Most recently, the rapidly increasing impact of digital communications on other fields may herald the emergence of cloud computing and the industrial internet as the new dominant industrial paradigm.
    Keywords: Innovation, patents, electrical instruments, instruments, information technology
    JEL: O32 O31 O12
    Date: 2017–08–23

This nep-big issue is ©2017 by Tom Coupé. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.