Smoothed population size estimation of human rights violations in Colombia 1985–2018

We estimate the extent of conflict-related homicides, kidnappings, and forced recruitments in Colombia between 1985 and 2018; also at the gender, department, and year level. In order to do so, we first introduce general principles for stratified estimation. We then implement Ridge and fused Ridge type penalties to smooth generalized Chao and Zelterman estimators. The fused Ridge type penalties are particularly apt at pooling information across time and space, after specification of an opportune adjacency matrix. Penalty parameters are selected through an empirical Focused Information Criterion strategy. A simulation study illustrates how penalized estimators outperform competitors in terms of mean squared error, and stability, both overall and at the stratified level. We estimate more than 640,000 conflict-related homicides, almost 30,000 forced recruitments, and more than 60,000 conflict-related kidnappings in the period; with clear temporal and spatial patterns. The Antioquia department, and years between 2000 and 2005, were most severely affected by violence. We also estimate that after the peace agreements of 2016 in some departments the conflict experienced a slight resurgence in killings and, more broadly, in human rights violations.