Deep learning provides powerful methods to impute structured information from large-scale, unstructured text and image datasets. For example, economists might wish to detect the presence of economic activity in satellite images or measure the topics or entities mentioned in social media, the congressional record, or firm filings. This review introduces deep neural networks, covering methods such as classifiers, regression models, generative artificial intelligence (AI), and embedding models. Applications include classification, document digitization, record linkage, and methods for data exploration in massive-scale text and image corpora. When suitable methods are used, deep learning models can be cheap to tune and can scale affordably to problems involving millions or billions of data points. The review is accompanied by a regularly updated companion website, EconDL ( https://econdl.github.io/ ), with user-friendly demo notebooks, software resources, and a knowledge base that provides technical details and additional applications.

This study utilizes regression discontinuity to examine the long-run impacts of the mita, an extensive forced mining labor system in effect in Peru and Bolivia between 1573 and 1812. Results indicate that a mita effect lowers household consumption by around 25% and increases the prevalence of stunted growth in children by around 6 percentage points in subjected districts today. Using data from the Spanish Empire and Peruvian Republic to trace channels of institutional persistence, I show that the mita's influence has persisted through its impacts on land tenure and public goods provision. Mita districts historically had fewer large landowners and lower educational attainment. Today, they are less integrated into road networks and their residents are substantially more likely to be subsistence farmers.

Drug trade-related violence has escalated dramatically in Mexico since 2007, and recent years have also witnessed large-scale efforts to combat trafficking, spearheaded by Mexico's conservative PAN party. This study examines the direct and spillover effects of Mexican policy toward the drug trade. Regression discontinuity estimates show that drug-related violence increases substantially after close elections of PAN mayors. Empirical evidence suggests that the violence reflects rival traffickers' attempts to usurp territories after crackdowns have weakened incumbent criminals. Moreover, the study uses a network model of trafficking routes to show that PAN victories divert drug traffic, increasing violence along alternative drug routes.

This study uses discontinuities in U.S. strategies employed during the Vietnam War to estimate their causal impacts. It identifies the effects of bombing by exploiting rounding thresholds in an algorithm used to target air strikes. Bombing increased the military and political activities of the communist insurgency, weakened local governance, and reduced noncommunist civic engagement. The study also exploits a spatial discontinuity across neighboring military regions that pursued different counterinsurgency strategies. A strategy emphasizing overwhelming firepower plausibly increased insurgent attacks and worsened attitudes toward the U.S. and South Vietnamese government, relative to a more hearts-and-minds-oriented approach.

Colonial powers typically organized economic activity in the colonies to maximize their economic returns. While the literature has emphasized long-run negative economic impacts via institutional quality, the changes in economic organization implemented to spur production historically could also directly influence economic organization in the long-run, exerting countervailing effects. We examine these in the context of the Dutch Cultivation System, the integrated industrial and agricultural system for producing sugar that formed the core of the Dutch colonial enterprise in 19th century Java. We show that areas close to where the Dutch established sugar factories in the mid-19th century are today more industrialized, have better infrastructure, are more educated, and are richer than nearby counterfactual locations that would have been similarly suitable for colonial sugar factories. We also show, using a spatial regression discontinuity design on the catchment areas around each factory, that villages forced to grow sugar cane have more village-owned land and also have more schools and substantially higher education levels, both historically and today. The results suggest that the economic structures implemented by colonizers to facilitate production can continue to promote economic activity in the long run, and we discuss the contexts where such effects are most likely to be important.

This study examines how the historical state conditions long‐run development, using Vietnam as a laboratory. Northern Vietnam (Dai Viet) was ruled by a strong, centralized state in which the village was the fundamental administrative unit. Southern Vietnam was a peripheral tributary of the Khmer (Cambodian) Empire, which followed a patron‐client model with more informal, personalized power relations and no village intermediation. Using a regression discontinuity design, the study shows that areas exposed to Dai Viet administrative institutions for a longer period prior to French colonization have experienced better economic outcomes over the past 150 years. Rich historical data document that in Dai Viet villages, citizens have been better able to organize for public goods and redistribution through civil society and local government. We argue that institutionalized village governance crowded in local cooperation and that these norms persisted long after the original institutions disappeared.

A rapidly growing body of research applies panel methods to examine how temperature, precipitation, and windstorms influence economic outcomes. These studies focus on changes in weather realizations over time within a given spatial area and demonstrate impacts on agricultural output, industrial output, labor productivity, energy demand, health, conflict, and economic growth, among other outcomes. By harnessing exogenous variation over time within a given spatial unit, these studies help credibly identify (i) the breadth of channels linking weather and the economy, (ii) heterogeneous treatment effects across different types of locations, and (iii) nonlinear effects of weather variables. This paper reviews the new literature with two purposes. First, we summarize recent work, providing a guide to its methodologies, datasets, and findings. Second, we consider applications of the new literature, including insights for the “damage function” within models that seek to assess the potential economic effects of future climate change.

Temperature and Income: Reconciling New Cross-Sectional and Panel Estimates by Melissa Dell, Benjamin F. Jones and Benjamin A. Olken. Published in volume 99, issue 2, pages 198-204 of American Economic Review, May 2009