The Regression Anatomy (RA) theorem (Angrist and Pischke 2009) is an alternative formulation of the Frisch-Waugh-Lovell (FWL) theorem (Frisch and Waugh 1933; Lovell 1963), a key finding in the algebra of OLS multiple regression models. In this paper, we present a command, reganat, to implement graphically the method of RA. This addition complements the built-in Stata command avplot in the validation of linear models, producing bidimensional scatterplots and regression lines obtained controlling for the other covariates, along with several fine-tuning options. Moreover, the article provides (1) a fully worked-out proof of the RA theorem and (2) an explanation of how the RA and FWL theorems relate to partial and semipartial correlations, whose coefficients are informative when evaluating relevant variables in a linear regression model.
REGANAT: Stata module to perform graphical inspection of linear multivariate models based on regression anatomy / Filoso, Valerio. - (2013).
REGANAT: Stata module to perform graphical inspection of linear multivariate models based on regression anatomy
FILOSO, VALERIO
2013
Abstract
The Regression Anatomy (RA) theorem (Angrist and Pischke 2009) is an alternative formulation of the Frisch-Waugh-Lovell (FWL) theorem (Frisch and Waugh 1933; Lovell 1963), a key finding in the algebra of OLS multiple regression models. In this paper, we present a command, reganat, to implement graphically the method of RA. This addition complements the built-in Stata command avplot in the validation of linear models, producing bidimensional scatterplots and regression lines obtained controlling for the other covariates, along with several fine-tuning options. Moreover, the article provides (1) a fully worked-out proof of the RA theorem and (2) an explanation of how the RA and FWL theorems relate to partial and semipartial correlations, whose coefficients are informative when evaluating relevant variables in a linear regression model.File | Dimensione | Formato | |
---|---|---|---|
Abstract.pdf
accesso aperto
Descrizione: Abstract
Tipologia:
Abstract
Licenza:
Dominio pubblico
Dimensione
458.2 kB
Formato
Adobe PDF
|
458.2 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.