Random forest (RF) is in many fields of research a common method for data‐driven predictions. Within economics and prediction of poverty, RF is rarely used. Comparing out‐of‐sample predictions in surveys for the same year in six countries shows that RF is often more accurate than current common practice (multiple imputations with variables selected by Stepwise and Lasso), suggesting that this method could contribute to better poverty predictions. However, none of the methods consistently provides accurate predictions of poverty over time, highlighting that technical model fitting by any method within a single year is not always, by itself, sufficient for accurate predictions of poverty over time.
For disaster emergency response, timely information is critical and satellite data is a potential source for such information. High-resolution optical satellite images are often the most informative, but these are only available on cloud-free days. For some extreme weather disasters, like cyclones, access to cloud-free images is unlikely for days both before and after the main impact. In this situation, Synthetic Aperture Radar (SAR) data is a unique first source of information, as it works irrespective of weather and sunlight conditions. This paper shows, in the context of the cyclone Idai that hit Mozambique in March 2019, that Change Detection between pairs of SAR data is a perfect match with weather data, and therefore captures impact from the severe cyclone. For emergency operations, the filtering of Change Detections by external data on the location of houses prior to an event allows assessment of the impact on houses as opposed to impact on the surrounding natural environment. The free availability of SAR data from Sentinel-1, with further automated processing of it, means that this analysis is a cost-effective and quick potential first indication of cyclone destruction.
Reducing child undernutrition is a key social policy objective of the Ethiopian government. Despite substantial reduction over the last decade and a half, child undernutrition is still high; with 48 percent of children either stunted, underweight or wasted, undernutrition remains an important child health challenge. The existing literature highlights that targeting of efforts to reduce undernutrition in Ethiopia is inefficient, in part due to lack of data and updated information. This paper remedies some of this shortfall by estimating levels of stunting and underweight in each woreda for 2014. The estimates are small area estimations based on the 2014 Demographic and Health Survey and the latest population census. It is shown that small area estimations are powerful predictors of undernutrition, even compared to household characteristics, such as wealth and education, and hence a valuable targeting metric. The results show large variations in share of children undernourished within each region, more than between regions. The results also show that the locations with larger challenges depend on the chosen undernutrition statistic, as the share, number and concentration of undernourished children point to vastly different locations. There is also limited correlation between share of children underweight and stunted across woredas, indicating that different locations face different challenges.