Nonparametric estimation of large covariance matrices of longitudinal data
Estimation of an unstructured covariance matrix is difficult because of its positive-definiteness constraint. This obstacle is removed by regressing each variable on its predecessors, so that estimation of a covariance matrix is shown to be equivalent to that of estimating a sequence of varying-coefficient and varying-order regression models. Our framework is similar to the use of increasing-order autoregressive models in approximating the covariance matrix or the spectrum of a stationary time series. As an illustration, we adopt Fan & Zhang's (2000) two-step estimation of functional linear models and propose nonparametric estimators of covariance matrices which are guaranteed to be positive definite. For parsimony a suitable order for the sequence of (auto)regression models is found using penalised likelihood criteria like AIC and BIC. Some asymptotic results for the local polynomial estimators of components of a covariance matrix are established. Two longitudinal datasets are analysed to illustrate the methodology. A simulation study reveals the advantage of the nonparametric covariance estimator over the sample covariance matrix for large covariance matrices. Copyright Biometrika Trust 2003, Oxford University Press.
Year of publication: |
2003
|
---|---|
Authors: | Wu, Wei Biao |
Published in: |
Biometrika. - Biometrika Trust, ISSN 0006-3444. - Vol. 90.2003, 4, p. 831-844
|
Publisher: |
Biometrika Trust |
Saved in:
Saved in favorites
Similar items by person
-
Dynamic semiparametric factor model with a common break
Chen, Likai, (2017)
-
Sequential detection of common transient signals in high dimensional data stream
Wu, Yanhong, (2021)
-
Efficient estimation of copula-based semiparametric Markov models
Chen, Xiaohong, (2009)
- More ...