Struct DiffInDiff 

pub struct DiffInDiff;

Implementations

impl DiffInDiff

pub fn from_formula( formula: &Formula, data: &DataFrame, treated_var: &str, post_var: &str, cov_type: CovarianceType, ) -> Result<DidResult, GreenersError>

Estimates DiD model using a formula and DataFrame.

The formula should specify the outcome variable and include ‘treated’ and ‘post’ variables. The interaction term is created automatically.

Examples

use greeners::{DiffInDiff, DataFrame, Formula, CovarianceType};
use ndarray::Array1;
use std::collections::HashMap;

let mut data = HashMap::new();
data.insert("y".to_string(), Array1::from(vec![1.0, 2.0, 3.0, 4.0]));
data.insert("treated".to_string(), Array1::from(vec![0.0, 0.0, 1.0, 1.0]));
data.insert("post".to_string(), Array1::from(vec![0.0, 1.0, 0.0, 1.0]));

let df = DataFrame::new(data).unwrap();
let formula = Formula::parse("y ~ treated + post").unwrap();

let result = DiffInDiff::from_formula(&formula, &df, "treated", "post", CovarianceType::HC1).unwrap();

pub fn fit( y: &Array1<f64>, treated: &Array1<f64>, post: &Array1<f64>, cov_type: CovarianceType, ) -> Result<DidResult, GreenersError>

Estimates the Canonical 2x2 DiD model.

Arguments

• y - Outcome variable.
• treated - Dummy: 1 if belongs to treatment group, 0 otherwise.
• post - Dummy: 1 if in post-intervention period, 0 otherwise.
• cov_type - Covariance type (Recommended: HC1 or Cluster if we had cluster ID).