New impact evaluation technique for the global economy

Challenge

The literature on program/impact evaluation is rapidly evolving, with new impact evaluation techniques and econometric solutions appearing every year.

However, it remains difficult to develop counterfactuals at the level of region or country. Econometric analysis at the country level is challenging, because of small sample sizes and the high levels of variation in macro- and socio-economic indicators. In addition, program/impact evaluations are significant projects that are expensive to carry out.

Synthetic controls, developed by Abadie and Gardeazabal (2003), is of the few methods that has been used for this purpose at the country-level to date.

Innovation

We have developed a tool to conduct impact evaluation at the aggregate level called “proximity controls”. It is a quicker and easier way to construct a control region or groups to measure the impact of an intervention or event at a larger scale. This method exploits the similarities of countries of interest to conduct counterfactual analysis. Our findings have been published in the Journal of Globalization and Development.

In our paper, we use exports as a case study to explore just how similar the growth trajectory of countries with similar exports are.

We find that a synthetic combination of a country’s most similar exporters often perfectly matches economic growth in the reference country over a long period of time. This measure can predict how similar countries are in terms of a whole range of indicators. Examples include GDP per capita, growth, imports, educational attainment, and institutional performance.

We apply our proximity controls method to the case of Indonesia’s 1997 financial and political crisis. In addition, we highlight applications to the cases of political instability in Ivory Coast, election violence in Kenya and Greece’s debt crisis.

Outcome

We hope this new technique equips policy-makers with a number of data-driven strategies they can use to identify optimal comparator countries for a country of interest.

The proximity controls method offers an innovative way to carry out aggregate counterfactual analysis at the sector or country level. The approach can offer new insights about economic growth. For example, we see that countries with similar export structures tend to grow at similar rates. At the same time, countries that deviate from these shared growth rates tend to converge back towards them.

Our paper, “Export Similartiy Networks and Proximity Control Methods for Comparative Case Studies”, has been published in the Journal of Globalization and Development. You can download it here.