Skip to Content

SoDa Laboratories Working Paper Series

Strategic Campaign Communication: Evidence from 30,000 Candidate Manifestos

Caroline Le Pennec

2020-05

In representative democracy, individual candidates often run for parliamentary seats under a national party platform, which limits their ability to compete on policy issues at the local level.  I exploit a novel dataset of 30,000 candidate manifestos issued before the first and second rounds of nine French legislative elections to show that politicians strategically adjust their campaign communication to persuade voters who do not support their platform—not by moderating their policy positions but by advertising neutral non-policy issues instead. Doing so predicts better performance in office and may therefore provide voters with information that matters for representation.

Estimating Sleep and Work Hours from Alternative Data by Segmented Functional Classification Analysis (SFCA)

Klaus Ackermann, Simon D. Angus, Paul A. Raschky

2020-04

Alternative data is increasingly adapted to predict human and economic behaviour. This paper introduces a new type of alternative data by re-conceptualising the internet as a data-driven insights platform at global scale. Using data from a unique internet activity and location dataset drawn from over 1.5 trillion observations of end-user internet connections, we construct a functional dataset covering over 1,600 cities during a 7 year period with temporal resolution of just 15min. To predict ac- curate temporal patterns of sleep and work activity from this data-set, we develop a new technique, Segmented Functional Classification Analysis (SFCA), and compare its performance to a wide array of linear, functional, and classification methods. To confirm the wider applicability of SFCA, in a second application we predict sleep and work activity using SFCA from US city-wide electricity demand functional data. Across both problems, SFCA is shown to out-perform current methods.

Geographic Diversity in Economic Publishing

Simon D. Angus, Kadir Atalay, Jonathan Newton, David Ubilava

2020-03

Is the representation of editors at prestigious economics journals geographically diverse? Using data on the affiliations of academics working in an editorial capacity at such journals, we map the locations of editorial power within the economics profession. This allows us to rank institutions, countries and continents according to this measure of power. In addition, by considering the average distance of a journal’s editorial affiliations from a geographic mean, we rank journals by geographic diversity. The magnitudes of the geographic differences we find are striking. Over half the journals we consider have over two thirds of their editorial power located in the USA. A large majority of journals have a tiny editorial contribution from academics located outside of North America and Europe. Any one of the states of California, Massachusetts and Illinois has more power than the four continents of Asia, South America, Africa and Australasia combined.

Object Recognition for Economic Development from Daytime Satellite Imagery

Klaus Ackermann, Alexey Chernikov, Nandini Anantharama, Miethy Zaman, Paul A. Raschky

2020-02

Reliable data about the stock of physical capital and infrastructure in developing countries is typically very scarce. This is a particular problem for data at the subnational level where existing data is often outdated, not consistently measured or coverage is incomplete. Traditional data collection methods are time and labor-intensive which often prohibits developing countries from collecting this type of data.

This paper proposes a novel method to extract infrastructure features from high-resolution satellite images. We collected high-resolution satellite images for 5 million 1km 1km grid cells covering 21 African countries. We contribute to the growing body of literature in this area by training our machine learning algorithm on ground-truth data.

We show that our approach strongly improves the predictive accuracy over existing models. Our methodology can build the foundation to then predict subnational indicators of economic development for areas where this data is either missing or unreliable.

Reassessing the Resource Curse using Causal Machine Learning

Roland Hodler, Michael Lechner, Paul A. Raschky

2020-01

We reassess the effects of natural resources on economic development and conflict, applying a causal forest estimator and data from 3,800 Sub-Saharan African districts. We find that, on average, mining activities and higher world market prices of locally mined minerals both increase economic development and conflict.

Consistent with the previous literature, mining activities have more positive effects on economic development and weaker effects on conflict in places with low ethnic diversity and high institutional quality. In contrast, the effects of changes in mineral prices vary little in ethnic diversity and institutional quality, but are non-linear and largest at relatively high prices.