An Automatic Portmanteau Test for Serial Correlation

By Juan-Carlos Escanciano, Ignacio N. Lobato. 2009

256 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Finance

View Paper: https://www.semanticscholar.org/paper/180920d8b86db0b3fd9130fae2d4fb934c9ba477

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

1. K. Lim
2. Jae Hyun Kim
3. Wei Luo
4. Olivier Darné
5. Amélie Charles
6. Jeffrey Chu
7. Carsten Jentsch
8. Morgan Kelly

In Finance

1. K. Lim
2. Jae Hyun Kim
3. Wei Luo
4. Carsten Jentsch
5. Amélie Charles
6. Olivier Darné
7. Jeffrey Chu
8. Morgan Kelly

Citations in the corpus

• Stock return predictability and the adaptive markets hypothesis: Evidence from century-long U.S. data (2011, unknown): “Escanciano and Lobato (2009) propose an automatic test where the optimal value of p is determined by a fully datadependent procedure.”
• On the inefficiency of Bitcoin (2017, methodology): “Seventhly, we performed the robustified portmanteau test (Escanciano and Lobato, 2009) for no serial correlation.”
• Small Sample Properties of Alternative Tests for Martingale Difference Hypothesis (2011, methodology): “Escanciano and Lobato (2009b) provides an informative review of the statistical tests for the MDH.”
• An Updated Literature Review of Distance Correlation and Its Applications to Time Series (2017, unknown): “Robinson (1991) gave a variety of test statistics for testing serial correlation under the presence of conditional heteroskedasticity, whereas Escanciano and Lobato (2009) further proposed an automatic Portmanteau test that allows for nonlinear dependencies and automatic selection of lag order p .”
• Change Points and Temporal Dependence in Reconstructions of Annual Temperature: Did Europe Experience a Little Ice Age? (2014, methodology): “s are unpredictable, call martingale differences. Specifically, for a stationary series {Y t}, let I t={Y t,Y t−1,...} denote the information set at time t. Under martingale differences E(Y t|I t−1)= µ [Escanciano and Lobato (2009a)]. 4.2.1. Tests. Martingale differences imply zero autocorrelations ρ i ”
• Are US stock index returns predictable? Evidence from automatic autocorrelation-based tests (2013, methodology): “This is because the simulations performed by Escanciano and Lobato (2009) and Kim (2009) demonstrate that both tests present high power for models commonly employed in empirical finance.”
• A test for second order stationarity of a multivariate time series (2015, methodology): “Testing for uncorrelatedness of a multivariate time series is a well established technique in time series analysis (see, for example, Hoskings (1980, 1981) and Escanciano and Lobato (2009)).”
• A bootstrap-assisted spectral test of white noise under unknown dependence (2011, background): “The BP test statistic and its variants only test for zero correlations up to lag m, where m is a prespecified integer, so they have trivial power against correlations at lags beyond m. Recently, Escanciano and Lobato (2009) proposed a data-driven BP test for serial correlation.”
• Multi-scale tests for serial correlation (2015, methodology): “Finally, Escanciano and Lobato (2009) (EL) combine robustification techniques with a data-driven approach for automatic lag selection.”