Sohnesen, Thomas PaveStender, Niels2016-04-262016-04-262016-03https://hdl.handle.net/10986/24154Random forest is in many fields of research a common method for data driven predictions. Within economics and prediction of poverty, random forest is rarely used. Comparing out-of-sample predictions in surveys for same year in six countries shows that random forest 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.en-USCC BY 3.0 IGOPREDICTIONSPOOR HOUSEHOLDCONSUMPTION EXPENDITURESHOUSEHOLD SIZEHOUSEHOLD SURVEYAGRICULTURAL GROWTHCONSUMPTIONPOVERTY REDUCTIONIMPACT ON POVERTYPOVERTY RATESERRORSFARMERPOVERTY RATEFOOD CONSUMPTIONINCOMELINEAR REGRESSIONPOVERTY RATESPOVERTY ESTIMATESALGORITHMSHOUSEHOLD SURVEYSPROGRAMSCONSUMPTION DATAHOUSEHOLD SIZEHOUSINGPOVERTY ESTIMATESAGRICULTURAL PRACTICESIMPACTSNATIONAL POVERTYSAMPLESRURALVARIABLESMEASUREMENTCOUNTINGHOUSEHOLD BUDGETCONSUMPTION AGGREGATEQUALITYSURVEYSSOCIAL ASSISTANCEMEASURESINSTRUMENTSPOVERTY REDUCTIONTARGETINGRANDOM SAMPLESAGRICULTURAL PRACTICESCONSUMPTION EXPENDITURERURAL AREASCROSS‐SECTION DATAWELFARE MEASURESCROSS‐SECTION DATAWELFARE INDICATORSPANEL DATA SETSSOCIAL ASSISTANCEREGIONSSTATISTICSEVALUATIONSIGNIFICANCE LEVELPOOR HOUSEHOLDSSAMPLINGRURAL AREASPOVERTYPOOR HOUSEHOLDHOUSEHOLD HEADPANEL DATA SETSCONSUMPTION EXPENDITURESSIGNIFICANCE LEVELNATIONAL POVERTYHOUSEHOLD CONSUMPTIONECONOMETRICSSTANDARD ERRORSCONSUMPTION DATAPOVERTY STATUSPOVERTY RATEPOORPREDICTIONPOVERTY ASSESSMENTCONSUMPTION EXPENDITUREHOUSEHOLD SURVEYSLEARNINGINDICATORSRESEARCHCONSUMPTION POVERTYWELFARE INDICATORSOUTCOMESSOCIAL INDICATORSPOVERTY STATUSLINEAR REGRESSIONMISSING OBSERVATIONSINEQUALITYPOOR HOUSEHOLDSWorking PaperWorld Bank10.1596/1813-9450-7612