Created
March 5, 2019 14:11
-
-
Save vanatteveldt/46375691c7b0aac48ff04c0bfa2f6e81 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# get pikkety data on public and private capital accumulation | |
base = "https://raw.githubusercontent.com/ccs-amsterdam/r-course-material/master/data" | |
private = read_csv(paste(base, "private_capital.csv", sep = "/")) | |
public = read_csv(paste(base, "public_capital.csv", sep = "/")) | |
private | |
public | |
# we'd like to compute the correlation between private and public capital | |
# it's easy to do so for one country by joining the whole data sets: | |
d = inner_join(private, public, by="Year", suffix=c("_private", "_public")) | |
cor.test(d$U.S._private, d$U.S._public) | |
# however, the merged data is quite horrible to calculate the overall (pooled) | |
# correlation. We could do it by gathering the countries and separating coutry and type: | |
d2= d %>% gather(-Year, key = "country_type", value = "capital") %>% | |
separate(country_type, into=c("country", "type"), sep="_") %>% | |
spread(key = "type", value="capital") | |
cor.test(d2$private, d2$public) | |
# The above had to first combine country and type, and then separate it and spread it again | |
# This is more cumbersome than needed: it's a lot easier if we 'tidy' up the data first: | |
priv = private %>% gather(-Year, key = "Country", value = "Private") | |
pub = public %>% gather(-Year, key = "Country", value = "Public") | |
# now, we can just join and test: | |
c = full_join(priv, pub) | |
cor.test(c$Private, c$Public) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment