Nowcasting Dataset for Covid-19 updates in Sweden and Results from the Model

This data was used in my Master Thesis for the Programme Statistics and Machine Learning in Linkoping University, Sweden. The topic is on Understanding Folkhalsomyndigheten’s (The Public Health Agency in Sweden) data updates. This thesis focuses on analysing and proposing solutions to improve the accuracy of real-time COVID-19 case reporting using nowcasting techniques. It addresses challenges from delays and inconsistencies in reporting by assessing the quality of historical data and identifying regions with unusual reporting patterns. The study proposes dynamic correction methods using nowcasting and hierarchical Bayesian models to tackle common issues of underreporting and lag. The dataset used in this study originates from the Public Health Agency of Sweden (Folkhälsomyndigheten, FHM), which is responsible for monitoring and reporting COVID-19 statistics across Sweden. The dataset provides a comprehensive view of the pandemic's progression, covering the period from January 2020 to December 2024. It includes records of new hospital admissions due to COVID-19, differentiating between general hospitalizations and ICU treatment, offering insights into case severity.