Сравнение методов
Просматривайте выбранные методы рядом; строки с различиями подсвечены.
| Корректировка по фронтдору (критерий фронтдора)× | Алгоритмы каузального обнаружения (PC, FCI, LiNGAM)× | Two-Stage Least Squares (2SLS)× | |
|---|---|---|---|
| Область | Причинно-следственный вывод | Причинно-следственный вывод | Причинно-следственный вывод |
| Семейство | Regression model | Regression model | Regression model |
| Год появления≠ | 1995 | 2000 | 2009 |
| Автор метода≠ | Judea Pearl | Spirtes, Glymour & Scheines (PC/FCI); Shimizu et al. (LiNGAM) | Angrist & Pischke (textbook treatment); Stock & Yogo (weak-instrument theory) |
| Тип≠ | Causal identification (graphical adjustment) | Causal structure learning | Instrumental-variables regression |
| Основополагающий источник≠ | Pearl, J. (1995). Causal Diagrams for Empirical Research. Biometrika, 82(4), 669-688. DOI ↗ | Spirtes, P., Glymour, C., & Scheines, R. (2000). Causation, Prediction, and Search (2nd ed.). MIT Press. ISBN: 978-0262194402 | Angrist, J. D. & Pischke, J. S. (2009). Mostly Harmless Econometrics: An Empiricist's Companion. Princeton University Press. ISBN: 978-0691120355 |
| Другие названия≠ | frontdoor criterion, Pearl's frontdoor adjustment, frontdoor formula, Ön Kapı Düzenlemesi (Frontdoor Adjustment) | PC algorithm, FCI algorithm, LiNGAM, causal structure learning | instrumental variables, IV estimation, 2SLS, instrumental variable regression |
| Связанные≠ | 4 | 5 | 5 |
| Сводка≠ | Frontdoor adjustment is Judea Pearl's graphical identification strategy, introduced in 1995, that recovers the causal effect of a treatment on an outcome through a fully mediating variable even when an unobserved confounder sits between the treatment and the outcome. It is the go-to tool when the backdoor criterion cannot be satisfied because the confounder is unmeasured. | Causal discovery is a family of algorithms that automatically learn a directed acyclic graph (DAG) describing causal structure directly from observational data. The constraint-based PC and FCI algorithms were developed by Spirtes, Glymour and Scheines (2000), while the LiNGAM model of Shimizu et al. (2006) exploits linear non-Gaussian structure to orient edges. | IV/2SLS is a two-stage estimation method that recovers the causal effect of an endogenous regressor by isolating the part of its variation driven by an external instrument. It is the workhorse identification strategy in modern applied econometrics, developed at length in Angrist and Pischke's Mostly Harmless Econometrics (2009). |
| ScholarGateНабор данных ↗ |
|
|
|