@Gambitspieler
Ich glaube, das Folgende (in "Discussion" auf Seite 3) erklärt den Effekt, wieso die Daten für alle Länder zusammen konsistenter sind als für die einzelnen Länder:
Our modelling approach is unique in pooling information from multiple countries at once. ... it also means that trends in some countries will be affected by those with more data. We argue that this effect is beneficial in that it helps minimise idiosyncrasies in the data, as well as improve consistency of estimates over time. Whilst our qualitative conclusions surrounding impact of interventionsand the value of Rt under control are robust to our choice of whether to incorporate pooling or not, the ability to utilise a greater extent of available data and share information across countries in a statistically principled manner dramatically improves the consistency of model predictions across the study period (see Videos 1-3 in the Supplementary Material).
Also dazu gibt es auch 3 Videos in Anhängen.
Ich glaube, das Folgende (in "Discussion" auf Seite 3) erklärt den Effekt, wieso die Daten für alle Länder zusammen konsistenter sind als für die einzelnen Länder:
Our modelling approach is unique in pooling information from multiple countries at once. ... it also means that trends in some countries will be affected by those with more data. We argue that this effect is beneficial in that it helps minimise idiosyncrasies in the data, as well as improve consistency of estimates over time. Whilst our qualitative conclusions surrounding impact of interventionsand the value of Rt under control are robust to our choice of whether to incorporate pooling or not, the ability to utilise a greater extent of available data and share information across countries in a statistically principled manner dramatically improves the consistency of model predictions across the study period (see Videos 1-3 in the Supplementary Material).
Also dazu gibt es auch 3 Videos in Anhängen.