DD & DDD Flashcards
What do we use as the counterfactual?
time trend for observations that belong to the control group
1st DD assumption
E[Y0igt | g,t] =
what assumption do we check in the pre-period ?
common/parallel trends assumption:
want to observe common/parallel trends in treatment vs control groups in the pre-period
What are the 3 SE problems ?
how do you correct group correlation?
-no longer I.I.D, everyone in group g has a correlated
the moulton factor
MF= sqrt(B1 hat)/sqrt(B2 hat)
How do you correct for the SE problem of serial correlation?
-observations for the same underlying unit are not independent over time
cluster SE approach, run regressions at group level
How do you correct for the SE problem of heteroskedasticity?
-variability of a variable is not equal across the range of values of a second variable that is predicts
robust standard error –> always use the bigger of the robust SE and SE
IV
what is the word meaning of exclusion restriction?
the instruments Zi are not correlated with any other determinants of the dependent variables
IV
what kind of treatment effect does IV create?
LATE
–> local refers to the part of the sample that is influenced by the instruments
IV/2SLS
when using IV/2SLS what happens to the SE?
IV/2SLS almost always increases SE on coefficient for variable of interest
IV w/ heterogenous potential outcomes
2 assumptions:
- Z is binary
- assume a constant causal effect
IV w/ heterogenous potential outcomes
internal validity?
external validity?
internal validity: unbiased estimator for some sample
external validity: predictice value of studys findings (in other sample)w
IV w/ heterogenous potential outcomes
four assumptions that give internally valid LATE?
- non zero 1st stage
- exclusion restriction
- monotonicity assumption
- treatment is as good as randomly assigned
IV w/ heterogenous treatment effects
definition of complier, never taker, always taker
complier: people who change their behavior based on the instrument
always taker: people who always take treatment regardless of the instrument
never taker: people who never take treatment regardless of the instrument
IV w/ heterogenous treatment effects
is LATE usually equal to the effect of the average treatment effect on the treated?
no
since IV is based on the compliers