Assessing excess mortality in Vienna and Austria after the first year of the COVID-19 pandemic

In Austria, the first confirmed COVID-19 death occurred in early March 2020. Since then, the question as to whether and, if so, to what extent the COVID-19 pandemic has increased overall mortality has been raised in the public and academic discourse. In an effort to answer this question, Statistics Vienna (City of Vienna, Department for Economic Affairs, Labour and Statistics) has evaluated the weekly mortality trends in Vienna, and compared them to the trends in other Austrian provinces. For our analysis, we draw on data from Statistics Austria and the Austrian Agency for Health and Food Safety (AGES), which are published along with data on the actual and the expected weekly numbers of deaths via the Vienna Mortality Monitoring website. Based on the definition of excess mortality as the actual number of reported deaths from all causes minus the expected number of deaths, we calculate the weekly prediction intervals of the expected number of deaths for two age groups (0 to 64 years and 65 years and older). The temporal scope of the analysis covers not only the current COVID-19 pandemic, but also previous flu seasons and summer heat waves. The results show the actual weekly numbers of deaths and the corresponding prediction intervals for Vienna and the other Austrian provinces since 2007. Our analysis underlines the importance of comparing time series of COVID-19-related excess deaths at the sub-national level in order to highlight within-country heterogeneities.

Optimal Adaptive Prediction Intervals for Electricity Load Forecasting in Distribution Systems via Reinforcement Learning

Prediction intervals (PIs) offer an effective tool for quantifying uncertainty of loads in distribution systems. The traditional central PIs cannot adapt well to skewed distributions, and their offline training fashion is vulnerable to the unforeseen change in future load patterns. Therefore, we propose an optimal PI estimation approach, which is online and adaptive to different data distributions by adaptively determining symmetric or asymmetric probability proportion pairs for quantiles of PIs’ bounds. It relies on the online learning ability of reinforcement learning (RL) to integrate the two online tasks, i.e., the adaptive selection of probability proportion pairs and quantile predictions, both of which are modeled by neural networks. As such, the quality of quantiles-formed PI can guide the selection process of optimal probability proportion pairs, which forms a closed loop to improve PIs’ quality. Furthermore, to improve the learning efficiency of quantile forecasts, a prioritized experience replay (PER) strategy is proposed for online quantile regression processes. Case studies on both load and net load demonstrate that the proposed method can better adapt to data distribution compared with online central PIs method. Compared with offline-trained methods, it obtains PIs with better quality and is more robust against concept drift.

Optimal Adaptive Prediction Intervals for Electricity Load Forecasting in Distribution Systems via Reinforcement Learning

Prediction intervals (PIs) offer an effective tool for quantifying uncertainty of loads in distribution systems. The traditional central PIs cannot adapt well to skewed distributions, and their offline training fashion is vulnerable to the unforeseen change in future load patterns. Therefore, we propose an optimal PI estimation approach, which is online and adaptive to different data distributions by adaptively determining symmetric or asymmetric probability proportion pairs for quantiles of PIs’ bounds. It relies on the online learning ability of reinforcement learning (RL) to integrate the two online tasks, i.e., the adaptive selection of probability proportion pairs and quantile predictions, both of which are modeled by neural networks. As such, the quality of quantiles-formed PI can guide the selection process of optimal probability proportion pairs, which forms a closed loop to improve PIs’ quality. Furthermore, to improve the learning efficiency of quantile forecasts, a prioritized experience replay (PER) strategy is proposed for online quantile regression processes. Case studies on both load and net load demonstrate that the proposed method can better adapt to data distribution compared with online central PIs method. Compared with offline-trained methods, it obtains PIs with better quality and is more robust against concept drift.

Prediction of future failures in the log-logistic distribution based on hybrid censored data

We consider the prediction of future observations from the log-logistic distribution. The data is assumed hybrid right censored with possible left censoring. Different point predictors were derived. Specifically, we obtained the best unbiased, the conditional median, and the maximum likelihood predictors. Prediction intervals were derived using suitable pivotal quantities and intervals based on the highest density. We conducted a simulation study to compare the point and interval predictors. It is found that the point predictor BUP and the prediction interval HDI have the best overall performance. An illustrative example based on real data is given.