A conditional independence test for dependent data based on maximal conditional correlation

Cheng, Yu-Hsiang; Huang, Tzee‐Ming

doi:10.1016/j.jmva.2012.01.017

Cited by 6 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As mentioned in Section 1, a well-known phenomenon of financial time series is that global correlations, in general, fail in describing the dependence. See [16] for a different approach to this problem. Note that Granger causality could be present at higher lags; see [7].…”

Section: Lead-lag Relations For Global and Local Correlationsmentioning

confidence: 99%

Local Lead–Lag Relationships and Nonlinear Granger Causality: An Empirical Analysis

Otneim

Berentsen

Tjøstheim

2022

Entropy

View full text Add to dashboard Cite

The Granger causality test is essential for detecting lead–lag relationships between time series. Traditionally, one uses a linear version of the test, essentially based on a linear time series regression, itself being based on autocorrelations and cross-correlations of the series. In the present paper, we employ a local Gaussian approach in an empirical investigation of lead–lag and causality relations. The study is carried out for monthly recorded financial indices for ten countries in Europe, North America, Asia and Australia. The local Gaussian approach makes it possible to examine lead–lag relations locally and separately in the tails and in the center of the return distributions of the series. It is shown that this results in a new and much more detailed picture of these relationships. Typically, the dependence is much stronger in the tails than in the center of the return distributions. It is shown that the ensuing nonlinear Granger causality tests may detect causality where traditional linear tests fail.

show abstract

Section: Lead-lag Relations For Global and Local Correlationsmentioning

confidence: 99%

Local Lead–Lag Relationships and Nonlinear Granger Causality: An Empirical Analysis

Otneim

Berentsen

Tjøstheim

2022

Entropy

View full text Add to dashboard Cite

show abstract

“…One fairly recent method for testing (25) is based on the maximal conditional correlation and was introduced by Huang (2010) and later extended to the time series case by Cheng and Huang (2012). The latter authors use this test to examine whether trading volume Granger caused index value, or vice versa, on the S&P 500 stock index during the first decade of this century.…”

Section: Empirical Example: Granger Causalitymentioning

confidence: 99%

“…Su and White have published a series of such tests: Su and White ( 2007) is based on detecting differences between estimated characteristic functions (which is also the method used by Wang and Hong (2017)), Su and White (2008) is based on estimating the Hellinger distance between conditional density estimates, Su and White (2012) use local polynomial quantile regression to test for conditional independence, and Su and White (2014) present a test based on empirical likelihood. Huang (2010) introduces the maximal nonlinear conditional correlation which is used in a test for conditional independence, in turn extended to dependent data by Cheng and Huang (2012). Song (2009) constructs a test via Rosenblatt transformations, while Bergsma (2010) and Bouezmarni, Rombouts, and Taamouti (2012) present new tests for conditional independence based on copula constructions.…”

Section: The Recent Fauna Of Nonparametric Testsmentioning

confidence: 99%

“…Next, we move to Su and White (2014), who provide simulations for their test for conditional independence based on the empirical likelihood (SEL), as well as the test by Su and White (2007) of the conditional characteristic function (CHF). Cheng and Huang (2012) provide simulations for their tests based on the maximal conditional correlation (MCC) at various levels of smoothing.…”

Section: Comparing With Other Testsmentioning

confidence: 99%

See 1 more Smart Citation

The Locally Gaussian Partial Correlation

Otneim¹,

Tjøstheim²

2019

Preprint

View full text Add to dashboard Cite

It is well known that the dependence structure for jointly Gaussian variables can be fully captured using correlations, and that the conditional dependence structure in the same way can be described using partial correlations. The partial correlation does not, however, characterize conditional dependence in many non-Gaussian populations. This paper introduces the local Gaussian partial correlation (LGPC), a new measure of conditional dependence. It is a local version of the partial correlation coefficient that characterizes conditional dependence in a large class of populations. It has some useful and novel properties besides: The LGPC reduces to the ordinary partial correlation for jointly normal variables, and it distinguishes between positive and negative conditional dependence. Furthermore, the LGPC can be used to study departures from conditional independence in specific parts of the distribution. We provide several examples of this, both simulated and real, and derive estimation theory under a local likelihood framework. Finally, we indicate how the LGPC can be used to construct a powerful test for conditional independence, which, again, can be used to detect Granger causality in time series.

show abstract

General tests of conditional independence based on empirical processes indexed by functions

Bouzebda

2023

Jpn J Stat Data Sci

View full text Add to dashboard Cite

A conditional independence test for dependent data based on maximal conditional correlation

Cited by 6 publications

References 11 publications

Local Lead–Lag Relationships and Nonlinear Granger Causality: An Empirical Analysis

Local Lead–Lag Relationships and Nonlinear Granger Causality: An Empirical Analysis

The Locally Gaussian Partial Correlation

General tests of conditional independence based on empirical processes indexed by functions

Contact Info

Product

Resources

About