Click the star to add/remove an item to/from your individual schedule.
You need to be logged in to avail of this functionality, and to see the links to virtual rooms.

Accepted Paper:

Decolonising data analysis: addressing epistemic injustice in econometric modelling  
Sharada Davidson (University of Strathclyde)

Paper short abstract:

This paper analyses the origins of colonialism in econometrics, exploring the history of econometrics, hierarchies in knowledge production, globalisation, and the Big Data era. I argue that to decolonise econometrics we must not only rectify geographical data gaps but address epistemic injustice.

Paper long abstract:

Econometric modelling, the analysis of economic data using statistical techniques, remains a dominant methodology favoured by mainstream economics and related disciplines. While a growing literature has sought to decolonise theories relating to economic development, the literature seeking to decolonise economic data analysis remains sparse. This paper focuses on time series econometrics (TSE) were new methods are devised to analyse (inter)dependence and spillovers between countries, the changing nature of the global economy and the transmission of economic policy. In TSE, a Eurocentric approach prevails. New techniques are designed with advanced economies in mind and evaluated using data from the US and Western Europe. Similarly, a simplistic centre-periphery lens is applied when modelling (inter)dependence between countries. I argue that this has led to datasets, models and analysis which cannot adequately capture developing and emerging economies and their role in the global economy. To unpack the origins and evolution of colonialism in TSE, I draw on postcolonial and decolonial theory and praxis as well as different strands of dependency theory. I consider the history of econometrics, hierarchies in knowledge production, globalisation and the displacement of space by time, and the empirical turn and Big Data era. I conclude that to decolonise data analysis we must go beyond rectifying geographical data gaps and bias. Instead, epistemic injustice underpinning data collection and existing modelling frameworks must be addressed so that new approaches centred on the local context can emerge.

Panel P04
Data justice and development [Digital Technologies, Data and Development SG]
  Session 1 Thursday 27 June, 2024, -