Search Results for error

Fig. 2 Plot of the square root of the mean squared error of states’ detention rates by year (panel a) and boxplots of state detention rates by region and year (panel b) for the period 1999–2011. Each boxplot captures the distribution of detention rates for all states in that region and year More

Fig. 3 Out-of-sample error rate, with 95% confidence intervals calculated from bootstrapping with 100 repetitions. Testing samples are used for prediction. IBS = integrated Brier score. Cox-PH 2way = Cox proportional hazard two-way interaction model. Cox-PH 2way select = Cox proportional hazard More

Fig. 3 Model fit measure or root mean squared error (Eq. ( 5 )) in response to varying ability parameters (ρ and ϕ in panel a), and varying readiness parameters (σ and β in panel b). Lower values indicate better fit between simulated and UN SRB estimates More

Fig. 4 Mean absolute error between the observed and simulated proportions of women with at least one child according to groups defined by age and birth cohort. Figures correspond to those obtained in the baseline scenario. Source: Authors' calculations and Statistics Netherlands (2020a) . More

Fig. 3 Genetic correlations for logged migration distance. Circles and error bars indicate genetic correlation estimates and standard errors. Correlations significant at the 5% level after Bonferroni correction are highlighted as open circles. ADHD = attention-deficit/hyperactivity disorder. LDL More

Fig. 2 Migration patterns and EA PGI. Colored bars and error bars represent estimated mean PGIs and their robust standard errors. The first 20 principal components are controlled. Capital letters indicate the six-category migration groups: (A) moved from a coal mining to a non–coal mining place More

Fig. 4 Migration patterns and health-related PGIs. Colored bars and error bars represent estimated mean PGIs and their robust standard errors. The first 20 principal components are controlled. Capital letters indicate the six-category migration groups: (A) moved from a coal mining to a non–coal More

Fig. 4 Median prediction error by sample fraction, with 50 samples for each sample fraction. For each sample, the median is calculated across all ages and all mortality schedules in each sample category (in-sample and out-of-sample). Whiskers extend to 10 % and 90 % quantiles. More

Fig. 6 Marital status of men and mortality. Error bars are 95% confidence intervals. The estimates shown across the four panels are from the same model, and the common reference category is men in first monogamous marriages who have not been widowed. Estimates are based on Models 8 and 9. More

Fig. 4 Sources of error in FBH data. Date displacement refers to events reported to have occurred earlier/later than recorded by the HDSS, leading to erroneous exclusion/inclusion from the reference period. Age understatement refers to errors resulting from the fact that a respondent More

Fig. 1 Absolute error (births/woman) in TFR over alternative methods and data sets. Solid dots are at median error for each method and data set. Horizontal bars extend from the 10th to 90th percentile of error. Numbers in parentheses indicate the count of schedules for which it is possible More

Fig. 1 Probability distribution of coverage error for unauthorized Mexican men, 2018 More