single_augsynth: Fit Augmented SCM

In ebenmichael/augsynth: The Augmented Synthetic Control Method

Fit Augmented SCM

Description

Fit Augmented SCM

Usage

single_augsynth(
  form,
  unit,
  time,
  t_int,
  data,
  progfunc = "ridge",
  scm = T,
  fixedeff = FALSE,
  cov_agg = NULL,
  ...
)

Arguments

form	outcome ~ treatment | auxillary covariates
unit	Name of unit column
time	Name of time column
t_int	Time of intervention
data	Panel data as dataframe
progfunc	What function to use to impute control outcomes ridge=Ridge regression (allows for standard errors), none=No outcome model, en=Elastic Net, RF=Random Forest, GSYN=gSynth, mcp=MCPanel, cits=Comparitive Interuppted Time Series causalimpact=Bayesian structural time series with CausalImpact
scm	Whether the SCM weighting function is used
fixedeff	Whether to include a unit fixed effect, default F
cov_agg	Covariate aggregation functions, if NULL then use mean with NAs omitted
...	optional arguments for outcome model

Value

augsynth object that contains:

• "weights"Ridge ASCM weights

• "l2_imbalance"Imbalance in pre-period outcomes, measured by the L2 norm

• "scaled_l2_imbalance"L2 imbalance scaled by L2 imbalance of uniform weights

• "mhat"Outcome model estimate

• "data"Panel data as matrices

ebenmichael/augsynth documentation built on March 20, 2024, 5:20 a.m.