An Improved Heteroskedasticity and Autocorrelation Consistent Covariance Matrix Estimator

Andrews, Donald W.K.; Monahan, J. Christopher

doi:10.2307/2951574

Cited by 948 publications

(765 citation statements)

References 0 publications

Supporting

Mentioning

745

Contrasting

Unclassified

Order By: Relevance

“…41 Los autores aplican la matriz de varianzas y covarianzas consistente con heterocedasticidad y autocorrelación de Andrews (1991) y Andrews y Monahan (1992). 42 Los valores críticos de los estadísticos sup F (k) y sup F (l+1|-l) se encuentran tabulados en Bai & Perron (1998 …”

Section: Conclusiónunclassified

Análisis de la deflación española de la primera mitad del siglo XIX: Una comparación internacional

Marco

2005

RHE / JILAEH

View full text Add to dashboard Cite

RESUMENLa deflación española de la primera mitad del siglo XIX es una característica destacada en la mayoría de los análisis historiográficos del periodo. Sin embargo, carecemos de estudios que cuantifiquen la intensidad de dicha deflación en relación con la experiencia registrada en otros países. Por ello, el objetivo de este trabajo es la elaboración e interpretación de un índice Laspeyres de precios al consumo en Barcelona para el periodo 1775-1844. El ejercicio se divide en dos partes. La primera parte explica el método de elaboración del índice. La segunda parte analiza la evolución del nivel de precios españoles en relación con el caso internacional. * Este trabajo es el resultado de la investigación realizada para la obtención del ABSTRACTAccording to historiography, deflation was one of the main features of early 19th century Spanish economy. However, studies that quantify the intensity of this deflation in relation to the experiences in other countries are lacking. For this reason, the purpose of the paper is the construction and the interpretation of a Laspeyres index of consumer prices in Barcelona for the years 1775-1844. The paper is divided into two sections. The first part describes the method used to construct the index. The second section compares the evolution of Spanish prices with other international cases.

show abstract

Section: Conclusiónunclassified

Análisis de la deflación española de la primera mitad del siglo XIX: Una comparación internacional

Marco

2005

RHE / JILAEH

View full text Add to dashboard Cite

show abstract

“…At the same time, the expectation is only one of many parameters describing the distribution ofΩ T , and robustness of the expectation is of course not sufficient for the whole distribution ofΩ T to be robust to the contaminations. On the one hand, a focus on the bias can be motivated by the finding of Andrews and Monahan (1992) that the bias properties of LRV estimators seem to be mainly responsible for size control of the tests (4). On the other hand, Theorem 5 below shows that, at least for a broad class of LRV estimators, a uniformly bounded robustness function (in T ) does imply that the distributions of the LRV estimator for an exact Brownian Bridge and a contaminated 13 Brownian Bridge are arbitrarily close for a small enough contamination.…”

Section: It Corresponds Tomentioning

confidence: 99%

“…The small sample experiment design closely follows similar exercises in Andrews (1991), Andrews and Monahan (1992) and Kiefer, Vogelsang, and Bunzel (2000). We are interested in the empirical rejection probability of a nominal 5% level, two-sided t-test concerning the second element of the coefficient vector in a OLS regression of {y t } on {x t }, where…”

Section: Quantitative Evaluationmentioning

confidence: 99%

“…For comparison purposes, we include in our experiments two popular LRV estimators that are consistent in the usual asymptotic thought experiment: the quadratic spectral estimator Ω QA with an automatic bandwidth selection using an AR(1) model for the bandwidth determination as suggested by Andrews (1991), and an AR(1) prewhitened LRV estimatorΩ P W with a second stage automatic bandwidth quadratic spectral kernel estimator as described in Andrews and Monahan (1992). The (asymptotically justified) critical values of thet and F -tests (4) based onΩ QA andΩ P W are accordingly those from standard normal and χ 2 distributions.…”

Section: Quantitative Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

A theory of robust long-run variance estimation

Müller

2007

Journal of Econometrics

101

View full text Add to dashboard Cite

The paper studies the robustness of long-run variance estimators employed for conducting Wald-type tests in standard time series models. It is shown that all long-run variance estimators that are consistent for the variance of Gaussian White Noise lack robustness in the sense that they yield arbitrary results for some underlying process that satisfies a Functional Central Limit Theorem. An analytical measure of robustness of long-run variance estimators is suggested that captures the degree of this fragility.A family of inconsistent long-run variance estimators is derived that optimally trade off this measure of robustness against efficiency. A minor modification of these optimal estimators lead to asymptotically F-distributed test statistics under the null hypothesis, so that robust large sample inference can be conducted very similarly to well-understood small sample Gaussian inference.JEL Classification: C13, C12, C32

show abstract

“…In fact Levine (1983) employed le with (2.20) but with Cj replaced by NCj/ (N -[ji), giving even more weight to the longer 1ags than the truncated estima te, and relating to the undesirable practice of approximating a Fourier series by its partial sumo Newey and West (1987) advocated the modified Bartlett k (2.22), beca use of its simplicity and the psd property it bestows on the spectrum estimate. Andrews and Monahan (1992) employed a version of prewhitening, prior to weighted autocovariance estimation, see again Section 2. A number of other contributions focus on alternative estimates and on improvements to rates of convergence and regularity conditions, e.g.…”

Section: Inference In Econometric Modelsmentioning

confidence: 99%