decade <- c(1950, 1960, 1970, 1980, 1990)
billions <- c(3.5, 5, 7.5, 13, 40)
plot(decade, billions, xlim=c(1950,2050), ylim=c(0,1000), main="average yearly inflation-adjusted dollar cost of extreme weather events worldwide")
pm <- lm(billions ~ poly(decade, 3))
curve(predict(pm, data.frame(decade=x)), add=TRUE)
The adjusted R^2 statistic is 0.98, meaning that 98% of the variation is explained by the third-degree polynomial, which means that the extrapolation is probably accurate.
Dangerous storms: they cost $3.5 Billion a year in the 50's, and they're projected to cost 300 times that in the 40's, adjusting for inflation.
Is health care projected to increase 300 times in 90 years in real terms?