Differences
Differences-
-
in
in-
-
Differences estimation in R and
Differences estimation in R and
S
tata
Stata
Stata
{ a.k.a. Difference
{ a.k.a. Difference-
-
in
in-
-
Difference, Difference
Difference, Difference-
-
in
in-
-
Differences,DD, DID, D
Differences,DD, DID, D-
-
I
-
D. }
D. }
DID estimation uses four data points to deduce the impact of a policy change or some
other shock (a.k.a. treatment) on the t
other shock (a.k.a. treatment) on the treated population:
reated population:
the effect of the treatment on the
treated
.
T
he structure of the experiment implies that the treatment group and control group
The structure of the experiment implies that the treatment group and control group
have similar characteristics and are trending in the same way over time.
T
his means that
This means that
the counterfactual
the counterfactual (unobserved scenario) is that had the treated group
(unobserved scenario) is that had the treated group
not
received
treatment, its mean value would be the same distance from the control group in the second
period.
S
ee the diagram below; the four data points are the observed mean (average) of
See the diagram below; the four data points are the observed mean (average) of
each group. T
each group. These are the only data points necessary to calculate
hese are the only data points necessary to calculate
the effect of the treatment
on the treated
.
T
he dotted lines represent the trend that is not observed by the
The dotted lines represent the trend that is not observed by the
researcher.
N
otice that although the means are different, they both have the same time
Notice that although the means are different, they both have the same time
trend
trend (i.e. slope).
(i.e. slope).
(i.e. slope).
For a more thorough work through of the effect of the Earned Income Tax Credit on
female employment, see an