From figures to facts: making sense of socio-economic surveys in the Democratic Republic of the Congo (DRC)
Year: 2017
Type: report
Abstract: From figures to facts: making sense of socioeconomic surveys in the Democratic Republic of the Congo (DRC)Over the last decades, both donor organizations and the national government have invested heavily in administering national-level surveys in the DRC.These survey results have been used in planning exercises (e.g. to elaborate the Poverty Reduction Strategy Papers) and in evaluation exercises (e.g. to decide on the country's debt relief), but the quality of these data is highly contentious as some basic demographic information on the DRC is simply unknown.This policy brief first presents the issue and illustrates its direct implications before we present a discussion of possible solutions, also for the short-run. The issuePolicymakers are typically concerned with absolute numbers of poor, ill, undernourished people; where they are located; and how their situation has evolved over time.In many developing countries, where often no routine monitoring system exists, one typically relies on representative household surveys to find answers to these questions.According to Little, survey sampling is one of the most important contributions of statistics to science as "[i]t provides the remarkable ability to obtain useful inferences about large populations from modest samples, with measurable uncertainty" (2004, p. 546).The crux of the matter of representativity lies however in the weight associated to each sampling unit, which indicates the number of population units it is supposed to "represent".Only with accurate weights is it possible to calculate any statistic from the sample as if it were derived from the whole population.Unfortunately, this weighing trick does not seem to work very well for the Democratic Republic of the Congo (DRC).The basic problem is that over the years the demographic structure of the country became largely unknown.All 21 st century survey samples have been defined in function of population projections based on the outdated and incompletely processed census of 1984.Indeed, over the 33 years
Authors: Wim Marivoet, Tom De Herdt
Language: English
Subfield: Sociology and Political Science
Field: Social Sciences
Domain: Social Sciences
SDG: No poverty
Open Access status: green
OpenAlex ID: W2620260299
