arXiv subjects

Emil N. Sørensen

Publications and source records attributed to Emil N. Sørensen.

7 recordsLinked to original sources

arXiv2026

The long-run returns to breastfeeding

This paper shows that the mid-20th century was characterised by a considerable reduction in breastfeeding rates, reducing from over 80% in the late 1930s to just over 40% only three decades later. We investigate how maternal breastfeeding during this period has shaped offspring health and human capital outcomes in the UK. We use a within-family design, comparing children who were breastfed to their sibling(s) who were not. Our results show that breastfeeding increases adult height, as well as fluid intelligence, but does not affect educational attainment, nor adult BMI. In further analyses, we examine whether and how this impact varies with individuals' genetic "predisposition" for these outcomes, proxied by the outcome-specific polygenic index. We find that the "height-returns" to breastfeeding are larger among those genetically predisposed to be taller, with no genetic heterogeneity for the other outcomes, though we note that power in the within-family GxE analysis is more limited. Overall, our estimates suggest that breastfeeding plays a non-negligible role in child development.

econ.GN↗

arXiv2024

The long-term human capital and health impacts of a pollution reduction programme

This paper investigates the effects of the staggered roll-out of a pollution reduction programme introduced in the UK in the 1950s. The policy allowed local authorities to introduce so-called Smoke Control Areas (SCAs) which banned smoke emissions. We start by digitizing historical pollution data to show that the policy led to an immediate reduction in black smoke concentrations. We then merge data on the exact location, boundary and month of introduction of SCAs to individual-level outcomes in older age using individuals' year-month and location of birth. We show that exposure to the programme increased individuals' birth weights as well as height in adulthood. We find no impact on their years of education or fluid intelligence.

econ.GN↗

arXiv2023

The Long-Term Effects of Early-Life Pollution Exposure: Evidence from the London Smog

This paper uses a large UK cohort to investigate the impact of early-life pollution exposure on individuals' human capital and health outcomes in older age. We compare individuals who were exposed to the London smog in December 1952 whilst in utero or in infancy to those born after the smog and those born at the same time but in unaffected areas. We find that those exposed to the smog have substantially lower fluid intelligence and worse respiratory health, with some evidence of a reduction in years of schooling.

econ.GN↗

arXiv2022

DARE: A large-scale handwritten date recognition system

Handwritten text recognition for historical documents is an important task but it remains difficult due to a lack of sufficient training data in combination with a large variability of writing styles and degradation of historical documents. While recurrent neural network architectures are commonly used for handwritten text recognition, they are often computationally expensive to train and the benefit of recurrence drastically differs by task. For these reasons, it is important to consider non-recurrent architectures. In the context of handwritten date recognition, we propose an architecture based on the EfficientNetV2 class of models that is fast to train, robust to parameter choices, and accurately transcribes handwritten dates from a number of sources. For training, we introduce a database containing almost 10 million tokens, originating from more than 2.2 million handwritten dates which are segmented from different historical documents. As dates are some of the most common information on historical documents, and with historical archives containing millions of such documents, the efficient and automatic transcription of dates has the potential to lead to significant cost-savings over manual transcription. We show that training on handwritten text with high variability in writing styles result in robust models for general handwritten text recognition and that transfer learning from the DARE system increases transcription accuracy substantially, allowing one to obtain high accuracy even when using a relatively small training sample.

cs.CV↗

arXiv2022

HANA: A HAndwritten NAme Database for Offline Handwritten Text Recognition

Methods for linking individuals across historical data sets, typically in combination with AI based transcription models, are developing rapidly. Probably the single most important identifier for linking is personal names. However, personal names are prone to enumeration and transcription errors and although modern linking methods are designed to handle such challenges, these sources of errors are critical and should be minimized. For this purpose, improved transcription methods and large-scale databases are crucial components. This paper describes and provides documentation for HANA, a newly constructed large-scale database which consists of more than 3.3 million names. The database contain more than 105 thousand unique names with a total of more than 1.1 million images of personal names, which proves useful for transfer learning to other settings. We provide three examples hereof, obtaining significantly improved transcription accuracy on both Danish and US census data. In addition, we present benchmark results for deep learning models automatically transcribing the personal names from the scanned documents. Through making more challenging large-scale databases publicly available we hope to foster more sophisticated, accurate, and robust models for handwritten text recognition.

cs.CV↗

arXiv2021

Applications of Machine Learning in Document Digitisation

Data acquisition forms the primary step in all empirical research. The availability of data directly impacts the quality and extent of conclusions and insights. In particular, larger and more detailed datasets provide convincing answers even to complex research questions. The main problem is that 'large and detailed' usually implies 'costly and difficult', especially when the data medium is paper and books. Human operators and manual transcription have been the traditional approach for collecting historical data. We instead advocate the use of modern machine learning techniques to automate the digitisation process. We give an overview of the potential for applying machine digitisation for data collection through two illustrative applications. The first demonstrates that unsupervised layout classification applied to raw scans of nurse journals can be used to construct a treatment indicator. Moreover, it allows an assessment of assignment compliance. The second application uses attention-based neural networks for handwritten text recognition in order to transcribe age and birth and death dates from a large collection of Danish death certificates. We describe each step in the digitisation pipeline and provide implementation insights.

cs.CV↗

arXiv2021

Time Series (re)sampling using Generative Adversarial Networks

We propose a novel bootstrap procedure for dependent data based on Generative Adversarial networks (GANs). We show that the dynamics of common stationary time series processes can be learned by GANs and demonstrate that GANs trained on a single sample path can be used to generate additional samples from the process. We find that temporal convolutional neural networks provide a suitable design for the generator and discriminator, and that convincing samples can be generated on the basis of a vector of iid normal noise. We demonstrate the finite sample properties of GAN sampling and the suggested bootstrap using simulations where we compare the performance to circular block bootstrapping in the case of resampling an AR(1) time series processes. We find that resampling using the GAN can outperform circular block bootstrapping in terms of empirical coverage.

cs.LG↗