A CONSISTENT DIAGNOSTIC TEST FOR REGRESSION MODELS USING PROJECTIONS

By Juan-Carlos Escanciano. Econometric Theory, 2006

187 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/763b72f5d29a20217c0fb376eb5d994222363c51

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Statistics and Probability

Citations in the corpus

A Goodness-of-Fit Test for the Functional Linear Model with Scalar Response (2012, methodology): “The statistic test is of a Cramér-von Mises type and is based on a generalization of a previous test of Escanciano (2006), designed for the case of a regression model with multivariate covariates.”
Distribution-Free Consistent Independence Tests via Center-Outward Ranks and Signs (2019, methodology): “Using the idea of projection from Escanciano (2006), Zhu et al. (2017) generalized Hoeffding’s D (Hoeffding 1948) to multivariate cases, and Kim, Balakrishnan, and Wasserman (2020) proposed the analogues of Blum–Kiefer–Rosenblatt’s R (Blum, Kiefer, and Rosenblatt 1961) and Bergsma–Dassios–…”
An updated review of Goodness-of-Fit tests for regression models (2013, methodology): “It is also worth it mentioning the contribution made by Escanciano (2006b), based on the almost sure characterization of the null hypothesis as E(ε0I(βtX ≤ u)) = 0, for some θ0 ∈ Θ , ∀u ∈ R and ∀β such that ‖β‖ = 1.”
Model Checks Using Residual Marked Empirical Processes (2004, methodology): “Escanciano (2006) proposed in the i.i.d. setup the CvM test CV Mn,pro,P = ∫ Πpro (R1n,pro,P (β, u)) 2Fn,β,P (du)dβ, where R1n,pro,P (β, u) = σ̂ −1 e n −1/2 ∑n t=1 et(θn)1(β ′It−1,P ≤ u) and σ̂2e = n−1 ∑n t=1 e2t (θn).”
Difference-in-Differences with multiple time periods (2018, methodology): “These results build on many papers in the goodness-of-fit literature – see e.g. Bierens (1982), Bierens and Ploberger (1997), Stute (1997), and Escanciano (2006b, 2008); for a recent overview, see González-Manteiga and Crujeiras (2013).”
ON THE LACK OF POWER OF OMNIBUS SPECIFICATION TESTS (2009, methodology): “A general unified asymptotic theory is established in Escanciano (2006a), including a bootstrap approximation of the null distribution of (R1n,w).”
Robust multivariate nonparametric tests via projection averaging (2018, background): “(Escanciano, 2006) For any two non-zero vectors U1, U2 ∈ Rd, ∫ Sd−1 1(βU1 ≤ 0)1(βU2 ≤ 0)dλ(β) = 1 2 − 1 2π Ang (U1, U2) .”