Using Machine Learning to Assess the Impact of Electricity Access on Livelihoods

  • Devarajan, the statistical tragedy of South Africa. Rev. Income Wealth 59S9–S15 (2013).

    Google Scholar article

  • Burke, M., Driscoll, A., Lobell, D. & Ermon, S. Using satellite imagery to understand and promote sustainable development. Science 371eabe8628 (2021).

    CAS PubMed Google Scholar Article

  • Yeh, C. et al. Using publicly available satellite imagery and deep learning to understand economic well-being in Africa. Nat. Common. 112583 (2020).

    Article ADS CAS PubMed PubMed Central Google Scholar

  • John, N. et al. Combining satellite imagery and machine learning to predict poverty. Science 353790–794 (2016).

    ADS CAS PubMed Google Scholar Article

  • Chi, G., Fang, H., Chatterjee, S. & Blumenstock, JE Wealth micro-estimates for all low- and middle-income countries. proc. Natl Acad. Science. UNITED STATES 119e2113658119 (2022).

    PubMed Article PubMed Central Google Scholar

  • Steele, JE et al. Mapping poverty using cell phone and satellite data. JR Soc. Interface 1420160690 (2017).

    PubMed Article PubMed Central Google Scholar

  • Pokhriyal, N. & Jacques, D. Combining disparate data sources to improve poverty forecasting and mapping. proc. Natl Acad. Science. UNITED STATES 114E9783–E9792 (2017).

    Article ADS CAS PubMed PubMed Central Google Scholar

  • Huang, L., Hsiang, S. & Gonzalez-Navarro, M. Using satellite imagery and deep learning to assess the impact of poverty reduction programs. Preprint at https://arxiv.org/abs/2104.11772 (2021).

  • The World Bank. Access to electricity (% of population)—Uganda. https://data.worldbank.org/indicator/EG.ELC.ACCS.ZS?locations=UG (2021).

  • International Energy Agency (IEA). World Energy Outlook 2019 (2019).

  • International Energy Agency (IEA). Africa Energy Outlook 2019 (2019).

  • Lenz, L., Munyehirw, A., Peters, J. & Seivert, M. Do large-scale infrastructure investments alleviate poverty? Impacts of the electricity access deployment program in Rwanda. Dev. 8988-110 (2017).

    Google Scholar article

  • Chakravorty, U., Emerick, K. & Ravago, M.-L. Lighting the last mile: the benefits and costs of extending electricity to the rural poor. Resources for the future working document 16-22 (2016).

  • Dinkelman, T. The effects of rural electrification on employment: new evidence from South Africa. A m. Econ. Round. 1013078–3108 (2011).

    Google Scholar article

  • Lee, K., Miguel, E. & Wolfram, C. Does Household Electrification Boost Economic Development? J.Econ. Perspective. 34122–144 (2020).

    Google Scholar article

  • Lee, K. et al. Electrification for “on-grid” households in rural areas of Kenya. Dev. Eng. 126–35 (2016).

    Google Scholar article

  • Bayer, P., Kennedy, R., Yang, J. & Urpelainen, J. The need for impact evaluation in electricity access research. Energy policy 137111099 (2020).

    Google Scholar article

  • Bernard, T. Impact analysis of rural electrification projects in sub-Saharan Africa. World Bank Res. Obs. 2733–51 (2012).

    Google Scholar article

  • Jaeger, DA, Joyce, TJ, and Kaestne, R. A cautionary tale about testing identifying hypotheses: Has reality TV really caused a decline in teenage childbearing? J.Bus. Econ. Statistical 38317–326 (2020).

    MathSciNet Google Scholar Article

  • Kahn-Lang, A. & Lang, K. The Promise and Pitfalls of Differences in Differences: Reflections on 16 and pregnant and other apps. J.Bus. Econ. Statistical 38613–620 (2020).

    MathSciNet Google Scholar Article

  • Sahn, DE & Stifel, D. Exploring alternative measures of well-being in the absence of expenditure data. Rev. Income Wealth 49463–489 (2003).

    Google Scholar article

  • Filmer, D. & Scott, K. Assessing Asset Indices. Demography 49359–392 (2012).

    PubMed Google Scholar article

  • He, K., Zhang, X., Ren, S. & Sun, J. in proc. European Conference on Computer Vision – ECCV 2016 (eds Leibe, B., Matas, J., Sebe, N. & Welling, M.) 630–645 (2016).

  • Athey, S., Bayati, M., Doudchenko, N., Imbens, G. & Khosravi, K. Matrix completion methods for causal panel data models. Jam. Statistics Assoc. 1161716-1730 (2021).

    MathSciNet CAS Google Scholar Article

  • Doudchenko, N. & Imbens, G. Balancing, Regression, Difference-in-Differences, and Synthetic Control Methods: A Synthesis. Preprint at https://arxiv.org/abs/1610.07748 (2016).

  • Jedwab, R. & Storeygard, A. The average and heterogeneous effects of transport investments: evidence from sub-Saharan Africa 1960–2010. J.Eur. Econ. Assoc. 201–38 (2022).

    Google Scholar article

  • Uganda National Roads Authority. Connect Uganda. https://www.unra.go.ug/home (2021).

  • Collins Bartholomew Ltd. Collins Mobile Coverage Explorer (2014).

  • World Bank Group. Uganda Poverty Maps (2018).

  • World Bank Group. Systematic Country Diagnostic of Uganda: Boosting Inclusive Growth and Accelerating Poverty Reduction (2015).

  • Burlig, F. & Preonas, L. From darkness to light? Developmental effects of rural electrification. Haas Energy Institute WP 26826 (2016).

    Google Scholar

  • Lee, K., Miguel, E. & Wolfram, C. Experimental evidence on the economics of rural electrification. J. Polit. Econ. 1281523-1565 (2020).

    Google Scholar article

  • Filmer, D. & Pritchett, LH Estimating wealth effects without expenditure data – or tears: an application to school enrollments in Indian states. Demography 38115–132 (2001).

    CAS PubMed Google Scholar

  • Omulo, G., Banadda, N. & Kiggundu, N. Harnessing the banana ripening process for banana juice extraction in Uganda. Afr. J.Food Sci. 6108-117 (2015).

    Google Scholar

  • Ministry of Energy and Mining Development. Uganda Sustainable Energy for All (SE4ALL) Action Program (2015).

  • Uganda Power Sector GIS Working Group. Distribution lines operational (2016) (2017).

  • Kingma, DP & Ba, J. Adam: a stochastic optimization method. Preprint at https://arxiv.org/abs/1412.6980 (2017).

  • OpenStreetMap contributors. Planet dump retrieved from https://planet.osm.org (2019).

  • Goodman-Bacon, A. Difference in differences with variation in treatment timing. J. Econom. 225254-277 (2021).

    MathSciNet MATH Google Scholar Article

  • Callaway, B. & Sant’Anna, PHC Difference in differences with multiple time periods. J. Econom. 225200–230 (2021).

    MathSciNet MATH Google Scholar Article

  • Abadie, A., Diamond, A. & Hainmuelle, J. Synthetic control methods for comparative case studies: estimating the effect of the California tobacco control program. Jam. Statistics Assoc. 105493–505 (2010).

    MathSciNet CAS Google Scholar Article

  • Sherry J. Basler