sweden-excess-mort-analysis.R

#data source:
# https://scb.se/om-scb/nyheter-och-pressmeddelanden/overdodligheten-fortsatter-att-sjunka-efter-toppen-i-april/

library(readxl)
library(excessmort)
library(tidyr)

dset <- read_excel("2020-05-22-preliminar_statistik_over_doda_inkl_eng.xlsx", sheet = 2,
                   skip = 6)
dset2 <- dset[-nrow(dset),]

months <- c("januari","februari","mars","april","maj","juni","juli","augusti","september",
            "oktober","november","december")
mlook <- 1:12
names(mlook) <- months

dset2$monthn <- mlook[dset2$Månad]

# population size data source:
# https://www.statistikdatabasen.scb.se/pxweb/sv/ssd/START__BE__BE0101__BE0101A/BefolkningNy/

menc <- c(417132, 420985, 425487, 430740, 436291)
Womenc <- c(540682, 546653, 553226, 560918, 568879)
yearc <- 2015:2019

popsize <- approx_demographics(data.frame(population = menc + Womenc, year = yearc),
                               "2015-01-01", "2020-05-17")


dset3 <- pivot_longer(dset2[, c(2:7, 11, 13)], cols = 1:6, names_to = "year", values_to = "outcome")

dset3$date <- as.Date(paste(dset3$year, dset3$monthn, dset3$Dag), format = "%Y %m %d")
dset3 <- subset(dset3, date < as.Date("2020-05-17"))

findat <- merge(dset3[, c("date", "outcome")], popsize, by = "date", all.x = TRUE)



############


library(dplyr)
library(lubridate)

exclude_dates <- c(seq(make_date(2017, 12, 16), make_date(2018, 1, 16), by = "day"),
                   seq(make_date(2020, 1, 1), max(findat$date), by = "day"))

counts <- findat %>%
  compute_expected(exclude = exclude_dates, weekday.effect = FALSE)

kable(head(counts))

expected_plot(counts) + ggtitle("Mortality in Sweden") + theme_bw()