2020/03/12 by Johannes Bracher, Leonhard Held, Bracher, Johannes +1 · 1 citation
Agricultural and Biological Sciences · Economics, Econometrics and Finance · Mathematics · #Agricultural risk and resilience #COVID-19 epidemiological studies #Economics of Agriculture and Food Markets #FOS: Computer and information sciences #Methodology (stat.ME)
paper · pdf · doi:10.48550/arxiv.2003.05885
openalex publication_date 2020/03/12 · openalex created_date 2022/07/24 · openalex updated_date 2026/07/28
Count data are often subject to underreporting, especially in infectious\ndisease surveillance. We propose an approximate maximum likelihood method to\nfit count time series models from the endemic-epidemic class to underreported\ndata. The approach is based on marginal moment matching where underreported\nprocesses are approximated through completely observed processes from the same\nclass. Moreover, the form of the bias when underreporting is ignored or taken\ninto account via multiplication factors is analysed. Notably, we show that this\nleads to a downward bias in model-based estimates of the effective reproductive\nnumber. A marginal moment matching approach can also be used to account for\nreporting intervals which are longer than the mean serial interval of a\ndisease. The good performance of the proposed methodology is demonstrated in\nsimulation studies. An extension to time-varying parameters and reporting\nprobabilities is discussed and applied in a case study on weekly rotavirus\ngastroenteritis counts in Berlin, Germany.\n