L. Freijeiro González, M. Febrero Bande, W. González Manteiga
Novel dependence tests are proposed in order to assess covariates relevance in the concurrent model framework. For this aim, we make use of new adaptations of the well-known covariance distance. An example is the martingale difference divergence coefficient of Shao and Zhang (2014). In particular, global dependence tests to quantify the effect of all covariates in the response and partial dependence ones to apply covariates selection are introduced considering all observed time instants. Their asymptotic distribution is obtained on each case and a bootstrap algorithm is proposed to obtain the p-value in practice. These new procedures are tested by means of a simulation study.
Shao, X. and Zhang, J. (2014). Martingale difference correlation and its use in high-dimensional variable screening. Journal of the American Statistical Association, 109(507):13021318.
Keywords: Dependence tests, covariates selection, concurrent model, MDD
Scheduled
GT06 Functional Data Analysis III. Recent contributions
June 8, 2022 5:20 PM
Grade Hall