For a number of reasons, the agencies responsible for evaluating social programs in both industrialized and developing countries have been much slower in adopting data science approaches than their colleagues who work in research and planning. York, P. and Bamberger, M. (2020), p.1. Big Data and Evaluation: a tale of two cities Beyond the humanitarian […]
mind the gap: bridging the methodological divide Read More »
Predictive analytics is the use of big data to feed machine learning and statistical models which then predict the likely occurance and character of future events. In humanitarian action, this could mean, for example, combining historical famine records with mobile phone operator data and social media activity, feeding these into an algorithm or statistical model,
evaluating the use of predictive analytics Read More »
Welcome to the Data Conscious blog! This is the first entry in a new blog series looking at the application of data science to the monitoring and evaluating of humanitarian action. The blog will cover topics like: Big data: how can it be practically used to help measure the results of humanitarian action? AI and
Launching Data conscious Read More »
An online community of evaluation practitioners devoted to sharing learning, tools and frameworks for evaluation. Covers all aspects of evaluation practice including methods, tools, approaches and key themes. The resource library hosts a large free-access collection of publications on evaluation methods. Doesn’t focus on any one sector for evaluation, but does include a specific page
This paper looks at potential ways to improve the capture and uptake of qualitative data in monitoring of humanitarian programmes. The first section of the paper dispels three pervasive myths about the use of qualitative approaches in the humanitarian sector. The second section of the paper identifies promising practice used by humanitarian agencies when monitoring
This paper, published by the ALNAP Secretariat, aims to encourage humanitarian agencies to step back and reflect on what is currently being done to measure outcomes and how it can be improved in the future. It starts by identifying core assumptions and foundational thinking behind current monitoring systems. It then outlines issues arising from current
Back to the Drawing Board: How to improve monitoring of outcomes Read More »
This paper, published by the ALNAP Secretariat, looks at a range of M&E innovations that are designed specifically to provide input to ongoing iterative decision-making and learning at the project level for humanitarian action. It identifies three key areas for potential innovation: 1) timing of M&E data provision; 2) flexibility of M&E frameworks to evolve
Breaking the Mould: Alternative approaches to monitoring and evaluation Read More »
Online certified course designed by Harvard and hosted by EdX. The course covers R, fundamentals of statistics, data wrangling, visualisation, wrangling, machine learning models and more. Capstone project included. Recommended 17 month timeframe based on 2-3 hours per week. https://www.edx.org/professional-certificate/harvardx-data-science
harvard university professional certificate in data science Read More »
Online coding courses covering R, Python, SQL and more. Data analysis, visualisation and statistics included. Covers basics of data science, engineering and analytics. Courses are interactive and focused on guided exercises and practical problem sets. Learn Data Science and Build Data Skills with Dataquest – HP
MIT statistics and data science micromasters Read More »
Online certified course designed by Johns Hopkins and hosted by Coursera. The course covers data science, R, GitHub, data cleansing, regression analysis, cluster analysis, debugging and more. Recommended 11 month timeframe based on 7 hours per week. Beginner level Python recommended prior to taking this course. https://www.coursera.org/specializations/jhu-data-science
Johns hopkins university Data science specialization Read More »