Advancing Microdata Models and Methods

This research develops and applies tools to extract information about individual behaviour, and influences on it, from data on individuals' actions and outcomes in their normal environment. Typically, this environment is not a controlled laboratory-like situation. The 'individuals' the project studies can be, for example, people, households or enterprises. The availability, scope, and scale of microdata are growing very fast, as is the computing technology to process this so-called "big data". Many weighty public sector policy decisions and private sector decisions on pricing, investment and strategy are based on the results of analysis of microdata. Analysis of microdata presents great challenges that this project will tackle. Some of these arise because the processes in which individuals are engaged are complex, involving risk and uncertainty set in a dynamic context in which the outcomes of decisions occur long after decisions are made. Saving and pension planning behaviour is of this type. It is critically important for government and firms, for example insurance companies, to understand such behaviours. Further complication arises because there is enormous heterogeneity. People have very different attitudes to risk or make very different estimates of their likely needs or longevity. This heterogeneity may produce big differences in savings outcomes, possibly resulting in great inequality in circumstances amongst the old. Housing location, purchase and rental outcomes are determined in a similarly complex heterogeneous process. This project will produce new models, methods and approaches for understanding behaviour of this sort, and it will apply them to develop answers to real policy questions using real microdata. An integral part of the project is a major programme of: hands-on basic training in microdata methods; advanced training given in masterclasses on themes at our research frontier; workshops giving themed presentations of research and stimulating new thinking amongst users and researchers. These activities will be conducted under the auspices of CeMMAP, the ESRC Centre for Microdata Methods and Practice. The research is organised under five headings. 1) Big data and machine learning. We will study the performance of big data and machine learning methods, develop models and research applications in which economic and social science poses deep questions and guides model construction. Applications will study the impact of policies to change behaviour using taxes on e.g. sugar and fat, and the impact of planning laws on housing supply and prices. 2) Dynamics and Complexity. We will develop models and tools to understand influences on complex life planning choices made by people in the face of uncertainty and incomplete information. Applications will study e.g. housing location and tenure choice. 3) Robust models. We will study the utility and performance of incomplete models of complex economic and social process in which only theory-grounded restrictions on behaviour are employed. Applications will consider e.g. models of auction bidding behaviour, determination of well-being and firm market entry and product choice. 4) Networks and interactions. We will study properties of tools to estimate aspects of network structure and develop methods for estimating the impact of network structure on outcomes. Applications will consider e.g. employer-employee matching processes and trade flows between countries. 5) Survey design and measurement. We will research the optimal choice of scope, scale and measurement quality in investigations such as field experiments constructed to answer specific social science questions. This work, delivering tools for robust analysis of emerging microdata resources, will be the core of CeMMAP's ongoing research programme, sustaining its outreach engagement and networking activities through to 2021.