Abstract
An analytical framework is presented for the evaluation of composite probability forecasts using empirical quantiles. The framework is demonstrated via the examination of forecasts of the changes in the number of US COVID-19 confirmed infection cases, applying 18 two-week ahead quantile forecasts from four forecasting organisations. The forecasts are analysed individually for each organisation and in combinations of organisational forecasts to ascertain the highest level of performance. It is shown that the relative error reduction achieved by combining forecasts depends on the extent to which the component forecasts contain independent information. The implications of the study are discussed, suggestions are offered for future research and potential limitations are considered.
Highlights
Over the course of the COVID-19 pandemic, the virus has mutated with new variants having increased the rate and ease of transmission and reproduction (Davies et al, 2021)
To examine the accuracy of such forecasts we propose an analytical framework for COVID-19 predictions using empirical quantiles
The overall performance of a set of forecasts for each quantile cumulative probability, for forecaster g, can be measured by the mean squared quantile performance score (MSQPS g), which is the average of the squared forecast errors, where the forecast error is measured as the forecast quantile value minus the empirical quantile value
Summary
Over the course of the COVID-19 pandemic, the virus has mutated with new variants having increased the rate and ease of transmission and reproduction (Davies et al, 2021). To demonstrate the application of the framework, the current study employed two-week quantile forecasts on the changes in the number of confirmed infection cases from four forecasting models provided from the Git COVID-19 Forecasting Hub (2021a) for the US These four models made quantile probability predictions with the median and point predictions, and six quantiles. The framework extends the empirical quantile probability technique set out in Thomson et al (2021), to consider situations where changes in the variable follow an autoregressive first order, AR(1), process This section describes the derivation of empirical quantiles and illustrates that a simple statistical test can be applied to the AR(1) model coefficient for each 14-day period that can be used to aid interpretation
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Scientific Research and Management
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
