CEDIL's latest methods working paper on using big data for evaluation

CEDIL Methods Working Papers

The CEDIL Methods Working Paper Series offers innovative research methods to develop impact evaluation and evidence synthesis work in low- and middle-income countries. The papers in this series also advance the understanding of how research methods and theoretical frameworks can be applied for addressing enduring and complex development challenges in low- and middle-income countries.

Latest Publication

Evaluation and Measurement

Measurement is crucial to evaluation. Without appropriate measures we cannot assess the effectiveness of policy. This paper addresses a number of conceptual issues linked to the construction and validation of appropriate measures that are useful for evaluation.

The unfinished evidence revolution: riding the five waves

The last thirty years have seen an evidence revolution which has developed in four waves: outcome monitoring, impact evaluation, systematic reviews and knowledge brokering. This paper examines the current state of each of the waves of the evidence revolution.

Timely evaluation in international development

This paper reviews approaches to timely evaluation from different traditions and combine them in a conceptual framework that describes their goals, speed, and how they address complexity.

Evaluating complex interventions in international development

This paper reviews promising methods for the evaluation of complex interventions that are new or have been used in a limited way. It offers a taxonomy of complex interventions in international development and draws on literature to discuss several methods that can be used to evaluate these interventions.

The strategic use of evidence and gap maps to build evidence architecture

This paper introduces evidence and gap maps and draws on five case studies to illustrate how they can be used strategically to build evidence architecture.

Engaging stakeholders with evidence and uncertainty: developing a toolkit

This working paper offers a new framework that helps choose appropriate stakeholder engagement methods while conducting research and supporting decision-making.

The science in the middle: middle level theory in international development evaluation

This paper discusses three defining features of how mid-level theorising generates transferable knowledge across disciplines and settings. It consolidates empirical regularities in human behaviour, it explains the diversity of outcomes observed across contexts, and it is explicit about causal principles observed in different settings.

Using big data for evaluating development outcomes: a systematic map

The methodological, ethical and practical constraints relating to the use of big data for measuring and evaluating development outcomes are discussed in this paper.

Making predictions of programme success more reliable

This paper provides an account of how a ‘causal–process–tracing theory of change’ can be very helpful for programme prediction, planning and evaluation.