@@ -5,6 +5,22 @@ All notable changes to this project will be documented in this file.
55The format is based on [ Keep a Changelog] ( https://keepachangelog.com/en/1.1.0/ ) ,
66and this project adheres to [ Semantic Versioning] ( https://semver.org/spec/v2.0.0.html ) .
77
8+ ## [ 2.5.0] - 2026-02-19
9+
10+ ### Added
11+ - Stacked DiD estimator (` StackedDiD ` ) implementing Wing, Freedman & Hollingsworth (2024)
12+ with corrective Q-weights for compositional balance across event times
13+ - Sub-experiment construction per adoption cohort with clean (never-yet-treated) controls
14+ - IC1/IC2 trimming for compositional balance across event times
15+ - Q-weights for aggregate, population, or sample share estimands (Table 1)
16+ - WLS event study regression via sqrt(w) transformation
17+ - ` stacked_did() ` convenience function
18+ - R benchmark scripts for Stacked DiD validation (` benchmarks/R/benchmark_stacked_did.R ` )
19+ - Comprehensive test suite for Stacked DiD (` tests/test_stacked_did.py ` )
20+
21+ ### Fixed
22+ - NaN inference handling in pure Python mode for edge cases
23+
824## [ 2.4.3] - 2026-02-19
925
1026### Changed
@@ -792,6 +808,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
792808 - ` to_dict() ` and ` to_dataframe() ` export methods
793809 - ` is_significant ` and ` significance_stars ` properties
794810
811+ [ 2.5.0 ] : https://github.com/igerber/diff-diff/compare/v2.4.3...v2.5.0
795812[ 2.4.3 ] : https://github.com/igerber/diff-diff/compare/v2.4.2...v2.4.3
796813[ 2.4.2 ] : https://github.com/igerber/diff-diff/compare/v2.4.1...v2.4.2
797814[ 2.4.1 ] : https://github.com/igerber/diff-diff/compare/v2.4.0...v2.4.1
0 commit comments