scholarly journals Adjusted Bayesian Completion Rates (ABC) Estimation

2021 ◽  
Author(s):  
Bilal Fouad Barakat ◽  
Ameer Dharamshi ◽  
Leontine Alkema ◽  
Manos Antoninis
Keyword(s):  
Time Series ◽  
Predictive Performance ◽  
School Level ◽  
Household Surveys ◽  
Completion Rates ◽  
Abc Model ◽  
Informative Priors ◽  
Random Walk Process ◽  
Meaningful Improvement ◽  
Associated Data

Estimating school completion is crucial for monitoring SDG 4 on education, and unlike enrollmentindicators, relies on household surveys. Associated data challenges include gaps between waves, conflictingestimates, age misreporting, and delayed completion. Our Adjusted Bayesian Completion Rates (ABC)model overcomes these challenges to produce the first complete and consistent time series for SDGindicator 4.1.2, by school level and sex, for 153 countries. A latent random walk process for unobservedtrue rates is adjusted for a range of error and variance sources, with weakly informative priors. The modelappears well-calibrated and offers a meaningful improvement in predictive performance.

scholarly journals Nighttime Lights and County-Level Economic Activity in the United States: 2001 to 2019

2021 ◽  
Vol 13 (14) ◽  
pp. 2741
Author(s):  
John Gibson ◽  
Geua Boe-Gibson
Keyword(s):  
Time Series ◽  
Economic Activity ◽  
Validation Studies ◽  
National Level ◽  
Predictive Performance ◽  
The United States ◽  
Cross Sectional ◽  
Nation States ◽  
Nighttime Lights ◽  
Defense Meteorological Satellite Program

Nighttime lights (NTL) are a popular type of data for evaluating economic performance of regions and economic impacts of various shocks and interventions. Several validation studies use traditional statistics on economic activity like national or regional gross domestic product (GDP) as a benchmark to evaluate the usefulness of NTL data. Many of these studies rely on dated and imprecise Defense Meteorological Satellite Program (DMSP) data and use aggregated units such as nation-states or the first sub-national level. However, applied researchers who draw support from validation studies to justify their use of NTL data as a proxy for economic activity increasingly focus on smaller and lower level spatial units. This study uses a 2001–19 time-series of GDP for over 3100 U.S. counties as a benchmark to examine the performance of the recently released version 2 VIIRS nighttime lights (V.2 VNL) products as proxies for local economic activity. Contrasts were made between cross-sectional predictions for GDP differences between areas and time-series predictions of GDP changes within areas. Disaggregated GDP data for various industries were used to examine the types of economic activity best proxied by NTL data. Comparisons were also made with the predictive performance of earlier NTL data products and at different levels of spatial aggregation.

scholarly journals Prediction of Past SARS-CoV-2 Infections: A Prospective Cohort Study Among Swiss Schoolchildren

2021 ◽  
Vol 9 ◽  
Author(s):  
Jacob Blankenberger ◽  
Sarah R. Haile ◽  
Milo A. Puhan ◽  
Christoph Berger ◽  
Thomas Radtke ◽  
...  
Keyword(s):  
Prediction Models ◽  
Characteristic Curve ◽  
Community Setting ◽  
Predictive Performance ◽  
Clinical History ◽  
School Level ◽  
Sociodemographic Characteristics ◽  
Serological Tests ◽  
Time Points ◽  
June July

Objective: To assess the predictive value of symptoms, sociodemographic characteristics, and SARS-CoV-2 exposure in household, school, and community setting for SARS-CoV-2 seropositivity in Swiss schoolchildren at two time points in 2020.Design: Serological testing of children in primary and secondary schools (aged 6–13 and 12–16 years, respectively) took place in June–July (T1) and October–November (T2) 2020, as part of the longitudinal, school-based study Ciao Corona in the canton of Zurich, Switzerland. Information on sociodemographic characteristics and clinical history was collected with questionnaires to parents; information on school-level SARS-CoV-2 infections was collected with questionnaires to school principals. Community-level cumulative incidence was obtained from official statistics. We used logistic regression to identify individual predictors of seropositivity and assessed the predictive performance of symptom- and exposure-based prediction models.Results: A total of 2,496 children (74 seropositive) at T1 and 2,152 children (109 seropositive) at T2 were included. Except for anosmia (odds ratio 15.4, 95% confidence interval [3.4–70.7]) and headache (2.0 [1.03–3.9]) at T2, none of the individual symptoms were significantly predictive of seropositivity at either time point. Of all the exposure variables, a reported SARS-CoV-2 case in the household was the strongest predictor for seropositivity at T1 (12.4 [5.8–26.7]) and T2 (10.8 [4.5–25.8]). At both time points, area under the receiver operating characteristic curve was greater for exposure-based (T1, 0.69; T2, 0.64) than symptom-based prediction models (T1, 0.59; T2, 0.57).Conclusions: In children, retrospective identification of past SARS-CoV-2 infections based on symptoms is imprecise. SARS-CoV-2 seropositivity is better predicted by factors of SARS-CoV-2 exposure, especially reported SARS-CoV-2 cases in the household. Predicting SARS-CoV-2 seropositivity in children in general is challenging, as few reliable predictors could be identified. For an accurate retrospective identification of SARS-CoV-2 infections in children, serological tests are likely indispensable.Trial registration number: NCT04448717.

scholarly journals Explainable Fraud Detection for Few Labeled Time Series Data

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Zhiwen Xiao ◽  
Jianbin Jiao
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Research Work ◽  
Fraud Detection ◽  
Predictive Performance ◽  
Multiple Instance Learning ◽  
Detection Methods ◽  
Series Data ◽  
Causal Explanations ◽  
Detection Technology

Fraud detection technology is an important method to ensure financial security. It is necessary to develop explainable fraud detection methods to express significant causality for participants in the transaction. The main contribution of our work is to propose an explainable classification method in the framework of multiple instance learning (MIL), which incorporates the AP clustering method in the self-training LSTM model to obtain a clear explanation. Based on a real-world dataset and a simulated dataset, we conducted two comparative studies to evaluate the effectiveness of the proposed method. Experimental results show that our proposed method achieves the similar predictive performance as the state-of-art method, while our method can generate clear causal explanations for a few labeled time series data. The significance of the research work is that financial institutions can use this method to efficiently identify fraudulent behaviors and easily give reasons for rejecting transactions so as to reduce fraud losses and management costs.

Visualization of uncertainty in air quality ensemble forecasts

2021 ◽  
Author(s):  
Angelika Heil ◽  
Augustin Colette
Keyword(s):  
Air Pollution ◽  
Time Series ◽  
Air Quality ◽  
Mobile Apps ◽  
Predictive Performance ◽  
User Preferences ◽  
Ensemble Forecasts ◽  
The Public ◽  
Pollution Levels ◽  
Wide Range

<p>Air quality forecasts help decision-makers to respond to air pollution episodes and to improve air quality management. In recent years, the public increasingly uses mobile apps to check forecasted air pollution levels and then adjusts outdoor activities accordingly. For Europe, state-of-the-art daily air quality forecasts are provided by the regional Copernicus Atmosphere Monitoring System (CAMS). The system integrates forecasts from 9 individual models. This ensemble approach not only achieves better predictive performance compared to a single model, but also allows a better quantification of forecast uncertainty. How to best communicate this uncertainty to a broad audience is by no means a trivial task, but yet essential to maintain trust in the forecasts.</p><p>We developed innovative visualizations to convey CAMS forecast uncertainties in time series and maps. The development is strongly user-driven and involves iterative consultation with a wide range of expert and non-expert users. We investigate the feasibility of different bivariate techniques to communicate the ensemble's best estimate and its uncertainty in a single map. We explore user preferences for a variety of time-series graphs, including boxplots, violinplots, and fancharts. Whilst preferences are largely driven by the data and visualization literacy of the users, we identify some generally valid best practices in terms of graph types, choices of colors and labels, and accompanying textual explanations. Finally, we present our candidate designs for the public display of air quality forecasts on the regional CAMS webpage.</p>

scholarly journals Comparative assessment of predictions in ungauged basins – Part 3: Runoff signatures in Austria

2013 ◽  
Vol 17 (6) ◽  
pp. 2263-2279 ◽  
Author(s):  
A. Viglione ◽  
J. Parajka ◽  
M. Rogger ◽  
J. L. Salinas ◽  
G. Laaha ◽  
...  
Keyword(s):  
Time Series ◽  
Predictive Performance ◽  
Comparative Assessment ◽  
Ungauged Basins ◽  
Rainfall Runoff ◽  
High Flows ◽  
Seasonal Runoff ◽  
Rainfall Runoff Model ◽  
Predictions In Ungauged Basins ◽  
Runoff Model

Abstract. This is the third of a three-part paper series through which we assess the performance of runoff predictions in ungauged basins in a comparative way. Whereas the two previous papers by Parajka et al. (2013) and Salinas et al. (2013) assess the regionalisation performance of hydrographs and hydrological extremes on the basis of a comprehensive literature review of thousands of case studies around the world, in this paper we jointly assess prediction performance of a range of runoff signatures for a consistent and rich dataset. Daily runoff time series are predicted for 213 catchments in Austria by a regionalised rainfall–runoff model and by Top-kriging, a geostatistical estimation method that accounts for the river network hierarchy. From the runoff time-series, six runoff signatures are extracted: annual runoff, seasonal runoff, flow duration curves, low flows, high flows and runoff hydrographs. The predictive performance is assessed in terms of the bias, error spread and proportion of unexplained spatial variance of statistical measures of these signatures in cross-validation (blind testing) mode. Results of the comparative assessment show that, in Austria, the predictive performance increases with catchment area for both methods and for most signatures, it tends to increase with elevation for the regionalised rainfall–runoff model, while the dependence on climate characteristics is weaker. Annual and seasonal runoff can be predicted more accurately than all other signatures. The spatial variability of high flows in ungauged basins is the most difficult to estimate followed by the low flows. It also turns out that in this data-rich study in Austria, the geostatistical approach (Top-kriging) generally outperforms the regionalised rainfall–runoff model.

scholarly journals Evaluation of Alternate Categorical Tumor Metrics and Cut Points for Response Categorization Using the RECIST 1.1 Data Warehouse

2014 ◽  
Vol 32 (8) ◽  
pp. 841-850 ◽  
Author(s):  
Sumithra J. Mandrekar ◽  
Ming-Wen An ◽  
Jeffrey Meyers ◽  
Axel Grothey ◽  
Jan Bogaerts ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Data Warehouse ◽  
Tumor Response ◽  
Metastatic Breast ◽  
Predictive Performance ◽  
Tumor Type ◽  
Validation Data ◽  
Meaningful Improvement ◽  
Cut Points ◽  
The Impact

Purpose We sought to test and validate the predictive utility of trichotomous tumor response (TriTR; complete response [CR] or partial response [PR] v stable disease [SD] v progressive disease [PD]), disease control rate (DCR; CR/PR/SD v PD), and dichotomous tumor response (DiTR; CR/PR v others) metrics using alternate cut points for PR and PD. The data warehouse assembled to guide the Response Evaluation Criteria in Solid Tumors (RECIST) version 1.1 was used. Methods Data from 13 trials (5,480 patients with metastatic breast cancer, non–small-cell lung cancer, or colorectal cancer) were randomly split (60:40) into training and validation data sets. In all, 27 pairs of cut points for PR and PD were considered: PR (10% to 50% decrease by 5% increments) and PD (10% to 20% increase by 5% increments), for which 30% and 20% correspond to the RECIST categorization. Cox proportional hazards models with landmark analyses at 12 and 24 weeks stratified by study and number of lesions (fewer than three v three or more) and adjusted for average baseline tumor size were used to assess the impact of each metric on overall survival (OS). Model discrimination was assessed by using the concordance index (c-index). Results Standard RECIST cut points demonstrated predictive ability similar to the alternate PR and PD cut points. Regardless of tumor type, the TriTR, DiTR, and DCR metrics had similar predictive performance. The 24-week metrics (albeit with higher c-index point estimate) were not meaningfully better than the 12-week metrics. None of the metrics did particularly well for breast cancer. Conclusion Alternative cut points to RECIST standards provided no meaningful improvement in OS prediction. Metrics assessed at 12 weeks have good predictive performance.

Tempel: time-series mutation prediction of influenza A viruses via attention-based recurrent neural networks

2020 ◽  
Vol 36 (9) ◽  
pp. 2697-2704 ◽  
Author(s):  
Rui Yin ◽  
Emil Luusua ◽  
Jan Dabrowski ◽  
Yu Zhang ◽  
Chee Keong Kwoh
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Recurrent Neural Networks ◽  
Influenza A ◽  
Sequence Data ◽  
Predictive Performance ◽  
Influenza Viruses ◽  
Supplementary Information ◽  
Influenza A Viruses ◽  
Mutation Prediction

Abstract Motivation Influenza viruses are persistently threatening public health, causing annual epidemics and sporadic pandemics. The evolution of influenza viruses remains to be the main obstacle in the effectiveness of antiviral treatments due to rapid mutations. The goal of this work is to predict whether mutations are likely to occur in the next flu season using historical glycoprotein hemagglutinin sequence data. One of the major challenges is to model the temporality and dimensionality of sequential influenza strains and to interpret the prediction results. Results In this article, we propose an efficient and robust time-series mutation prediction model (Tempel) for the mutation prediction of influenza A viruses. We first construct the sequential training samples with splittings and embeddings. By employing recurrent neural networks with attention mechanisms, Tempel is capable of considering the historical residue information. Attention mechanisms are being increasingly used to improve the performance of mutation prediction by selectively focusing on the parts of the residues. A framework is established based on Tempel that enables us to predict the mutations at any specific residue site. Experimental results on three influenza datasets show that Tempel can significantly enhance the predictive performance compared with widely used approaches and provide novel insights into the dynamics of viral mutation and evolution. Availability and implementation The datasets, source code and supplementary documents are available at: https://drive.google.com/drive/folders/15WULR5__6k47iRotRPl3H7ghi3RpeNXH. Supplementary information Supplementary data are available at Bioinformatics online.

Sign in / Sign up

Export Citation Format

Share Document