on notera, comme d'habitude (sic), la discordance entre:
- les données vaxx (dernière date connue)
- les données décès "avec" c-19 (moyenne dernière semaine)
[et comme par hasard plus on va à l'est plus l'automne est précoce...]
du coup voyons voir France (FRA) vs Ukraine (UKR) avec les données owid de ce jour (n.b. données hospi. n.d.):
quelle surprise !
courbe "tests" et donc "positifs" en chute libre en FRA => courbes hospi. et décès suivent
tout le contraire en UKR #CQFD #Covid_19#COVID19
#thread follow up to previous thread below
i repeat the same excercise with positivity rate instead of reproduction rate vs stringency index by adding country, week and both effects in the panel regressions #COVID19 1/n
the graphs:
(notice higher positive rate when stringency stronger)
benchmark: within R² = 5.82%
+country dummies: same
+week dummies = 47.36% (~ x 100 w/r benchmark)
+country & week dum. = as above
again "seasonality" explains most of what is going on in the data #COVID19 2/n
and so again one can ask if they #lockdown during colder seasons and this makes actually things worse ? #COVID19
3/3
#thread
Following recent success of this thread (thanks @FatEmperor i guess :)just wanted to get back to this
i will just take the first graph as exemple: it's reproduction rate vs stringency index
panel (country-time in days) regression with random effects #COVID19 1/n
i put the initial graph as "benchmark" and i add 3 other graphs
panel regression with random effects
with countries dummies included
with weeks dummies included
with countries & weeks dummies included
and we will compare the R² as these are the only changing in this excercise 2/n
in panel regression what is most important is the R² within
adding country effects changes nothing
adding weeks (i.e. time trend or "seasonality" in this context) increases a lot the R² within (~ x100)
adding countries & weeks => same results as with weeks added only
3/n