X
and Y
that you can explain with the IV Z
Z
is related to X
but all effects of Z
on Y
go THROUGH X
, you’ve isolated a causal effect of X
on Y
by isolating just the causal part of X
and ignoring all the back doors!Z
is binary, get difference in Y
divided by difference in X
Y
and explained X
library(AER)
#US income and consumption data 1950-1993
data(USConsump1993)
USC93 <- as.data.frame(USConsump1993)
#lag() gets the observation above; here the observation above is last year
IV <- USC93 %>% mutate(lastyr.invest = lag(income) - lag(expenditure)) %>%
group_by(cut(lastyr.invest,breaks=10)) %>%
summarize(exp = mean(expenditure),inc = mean(income))
cor(IV$exp,IV$inc)
## [1] 0.9993985
Rem
ediation, Pers
istence, other things.RemC
) as an instrument for “Actually in remediation” (RemA
)RemC
to Pers
?RemC
is based on the loc
ation where you live, loc -> RemC
. What else might be related to where you live?price
affect use
?price
for the same procedure varies wildly between peopleinc
ome, empl
oyment, what else?fam
ily injury is an instrument for pricecap
italization, and the Russell 2000 indexes the next top 2000price
?cap
- just big enough for the 1000 and you’re on the 1000, not quite there and you’re on the R2000
cap
and also your price
above
is an IV for being listed on R2000
EZ
)” tax incentives on emp
loyment? Draw the diagram!EZ
comm
ittee, increasing the chances of getting an EZ for their district? IV! (controlling for the rep
, we’re looking before/after here, like diff-in-diff)Z
is related to X
Z
to Y
must be closedZ
to Y
must go through X