| aggte {did} | R Documentation |
Aggregate Group-Time Average Treatment Effects
Description
A function to take group-time average treatment effects and aggregate them into a smaller number of parameters. There are several possible aggregations including "simple", "dynamic", "group", and "calendar."
Usage
aggte(
MP,
type = "group",
balance_e = NULL,
min_e = -Inf,
max_e = Inf,
na.rm = FALSE,
bstrap = NULL,
biters = NULL,
cband = NULL,
alp = NULL,
clustervars = NULL
)
Arguments
MP |
an MP object (i.e., the results of the |
type |
Which type of aggregated treatment effect parameter to compute. One option is "simple" (this just computes a weighted average of all group-time average treatment effects with weights proportional to group size). Other options are "dynamic" (this computes average effects across different lengths of exposure to the treatment and is similar to an "event study"; here the overall effect averages the effect of the treatment across all positive lengths of exposure); "group" (this is the default option and computes average treatment effects across different groups; here the overall effect averages the effect across different groups); and "calendar" (this computes average treatment effects across different time periods; here the overall effect averages the effect across each time period). |
balance_e |
If set (and if one computes dynamic effects), it balances
the sample with respect to event time. For example, if |
min_e |
For event studies, this is the smallest event time to compute
dynamic effects for. By default, |
max_e |
For event studies, this is the largest event time to compute
dynamic effects for. By default, |
na.rm |
Logical value if we are to remove missing Values from analyses. Defaults is FALSE. |
bstrap |
Boolean for whether or not to compute standard errors using
the multiplier bootstrap. If standard errors are clustered, then one
must set |
biters |
The number of bootstrap iterations to use. The default is the value set in the MP object,
and this is only applicable if |
cband |
Boolean for whether or not to compute a uniform confidence
band that covers all of the group-time average treatment effects
with fixed probability |
alp |
the significance level, default is value set in the MP object. |
clustervars |
A vector of variables to cluster on. At most, there can be two variables (otherwise will throw an error) and one of these must be the same as idname which allows for clustering at the individual level. Default is the variables set in the MP object |
Value
An AGGTEobj object that holds the results from the
aggregation
Examples
Initial ATT(g,t) estimates from att_gt()
data(mpdta)
out <- att_gt(yname="lemp",
tname="year",
idname="countyreal",
gname="first.treat",
xformla=NULL,
data=mpdta)
You can aggregate the ATT(g,t) in many ways.
Overall ATT:
aggte(out, type = "simple") #> #> Call: #> aggte(MP = out, type = "simple") #> #> Reference: Callaway, Brantly and Pedro H.C. Sant'Anna. "Difference-in-Differences with Multiple Time Periods." Journal of Econometrics, Vol. 225, No. 2, pp. 200-230, 2021. <https://doi.org/10.1016/j.jeconom.2020.12.001>, <https://arxiv.org/abs/1803.09015> #> #> #> ATT Std. Error [ 95% Conf. Int.] #> -0.04 0.013 -0.0654 -0.0145 * #> #> #> --- #> Signif. codes: `*' confidence band does not cover 0 #> #> Control Group: Never Treated, Anticipation Periods: 0 #> Estimation Method: Doubly Robust
Dynamic ATT (Event-Study):
aggte(out, type = "dynamic") #> #> Call: #> aggte(MP = out, type = "dynamic") #> #> Reference: Callaway, Brantly and Pedro H.C. Sant'Anna. "Difference-in-Differences with Multiple Time Periods." Journal of Econometrics, Vol. 225, No. 2, pp. 200-230, 2021. <https://doi.org/10.1016/j.jeconom.2020.12.001>, <https://arxiv.org/abs/1803.09015> #> #> #> Overall summary of ATT's based on event-study/dynamic aggregation: #> ATT Std. Error [ 95% Conf. Int.] #> -0.0772 0.02 -0.1165 -0.038 * #> #> #> Dynamic Effects: #> Event time Estimate Std. Error [95% Simult. Conf. Band] #> -3 0.0305 0.0150 -0.0060 0.0670 #> -2 -0.0006 0.0139 -0.0344 0.0333 #> -1 -0.0245 0.0150 -0.0610 0.0121 #> 0 -0.0199 0.0117 -0.0485 0.0087 #> 1 -0.0510 0.0168 -0.0919 -0.0100 * #> 2 -0.1373 0.0380 -0.2299 -0.0446 * #> 3 -0.1008 0.0360 -0.1887 -0.0130 * #> --- #> Signif. codes: `*' confidence band does not cover 0 #> #> Control Group: Never Treated, Anticipation Periods: 0 #> Estimation Method: Doubly Robust
ATT for each group:
aggte(out, type = "group") #> #> Call: #> aggte(MP = out, type = "group") #> #> Reference: Callaway, Brantly and Pedro H.C. Sant'Anna. "Difference-in-Differences with Multiple Time Periods." Journal of Econometrics, Vol. 225, No. 2, pp. 200-230, 2021. <https://doi.org/10.1016/j.jeconom.2020.12.001>, <https://arxiv.org/abs/1803.09015> #> #> #> Overall summary of ATT's based on group/cohort aggregation: #> ATT Std. Error [ 95% Conf. Int.] #> -0.031 0.0127 -0.0558 -0.0062 * #> #> #> Group Effects: #> Group Estimate Std. Error [95% Simult. Conf. Band] #> 2004 -0.0797 0.0308 -0.1461 -0.0134 * #> 2006 -0.0229 0.0175 -0.0606 0.0148 #> 2007 -0.0261 0.0163 -0.0612 0.0091 #> --- #> Signif. codes: `*' confidence band does not cover 0 #> #> Control Group: Never Treated, Anticipation Periods: 0 #> Estimation Method: Doubly Robust
ATT for each calendar year:
aggte(out, type = "calendar") #> #> Call: #> aggte(MP = out, type = "calendar") #> #> Reference: Callaway, Brantly and Pedro H.C. Sant'Anna. "Difference-in-Differences with Multiple Time Periods." Journal of Econometrics, Vol. 225, No. 2, pp. 200-230, 2021. <https://doi.org/10.1016/j.jeconom.2020.12.001>, <https://arxiv.org/abs/1803.09015> #> #> #> Overall summary of ATT's based on calendar time aggregation: #> ATT Std. Error [ 95% Conf. Int.] #> -0.0417 0.0177 -0.0765 -0.0069 * #> #> #> Time Effects: #> Time Estimate Std. Error [95% Simult. Conf. Band] #> 2004 -0.0105 0.0248 -0.0689 0.0479 #> 2005 -0.0704 0.0313 -0.1443 0.0035 #> 2006 -0.0488 0.0199 -0.0956 -0.0020 * #> 2007 -0.0371 0.0143 -0.0708 -0.0033 * #> --- #> Signif. codes: `*' confidence band does not cover 0 #> #> Control Group: Never Treated, Anticipation Periods: 0 #> Estimation Method: Doubly Robust