Resampling Methods for Dependent Data

By V. Carey. 2005

624 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/2319708570fece72b522f43860cb8555f99d14df

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistics and Probability

Citations in the corpus

A GENERALIZED BLOCK BOOTSTRAP FOR SEASONAL TIME SERIES (2014, methodology): “The proof is based on the proof of Theorem 4.1 from Lahiri (2003) and Theorem 3.5 from Synowiecki (2008).”
A penalized empirical likelihood method in high dimensions (2013, methodology): “LAHIRI AND S. MUKHOPADHYAY Step (I): Let Zn(t) = ∑p j=1( √ nȲnj)1((j−1)/p,j/p](t), t ∈ (0,1] and let Zn(0)≡ Zn(0+). Then, P (Zn ∈ L2[0,1]) = 1. The first step is to prove that Zn(·)→ Z(·) as elements of L2[0,1]. Recall that {φj : j ∈N} is a complete orthonormal basis for L2[0,1]. By Theorem 1.84 of ”
Forecasting: theory and practice (2020, methodology): “The resampling stage uses moving block bootstrap (MBB: Lahiri and Lahiri, 2003), applied to the remainder.”
Covariance matrix estimation and linear process bootstrap for multivariate time series of possibly increasing dimension (2015, methodology): “For an overview of existing bootstrap methods see the monograph of Lahiri (2003) and the review papers by Bühlmann (2002), Paparoditis (2002), Härdle, Horowitz and Kreiss (2003), Politis (2003a) or the recent review paper by Kreiss and Paparoditis (2011). Among the most popular bootstrap procedures ”
High dimensional generalized empirical likelihood for moment restrictions with dependent data (2013, background): “As indicated in Hall, Horowitz and Jing (1995) and Lahiri (2003), although there has been much research in determining the order of magnitude of M , there is in general a lack of research for selecting the tuning parameter, the coefficient of M for general nonlinear time series models.”
Comparing Forecast Skill (2014, methodology): “…methods draw random samples from the available data to estimate an empirical distribution of a statistic; see Efron and Tibshirani (1994), Good (2006), and Gilleland (2010) for accessible introductions, and Davison and Hinkley (1997), Lahiri (2003), and Good (2005) for more advanced treatments.”
Banded and tapered estimates for autocovariance matrices and the linear process bootstrap (2010, methodology): “There are several bootstraps for time series data [see, for example, Bühlmann (2002), Lahiri (2003), or Politis (2003b) for reviews].”
A test for second order stationarity of a multivariate time series (2015, methodology): “Lahiri (2003) for a review), but the majority of these sampling schemes, are nonstationary when conditioned on the original time series. An exception is the stationary bootstrap, proposed in Politis and Romano (1994), which is designed such that the bootstrap distribution is stationary. As we are te”
Control of generalized error rates in multiple testing (2007, methodology): “For time series or data-dependent situations, bootstrap methods that can capture the underlying dependence structure should be employed, such as block bootstraps, sieve bootstraps or Markov bootstraps; see [16].”
TFT-bootstrap: Resampling time series in the frequency domain to obtain replicates in the time domain (2011, background): “Bühlmann [6], Lahiri [36] and Politis [50] give reviews of the state-of-the-art in resampling time series and dependent data.”
Accuracy assessment of digital elevation models by means of robust statistical methods (2009, methodology): “One approach to treat this problem is to modify the above bootstrap procedure to take the dependence of data into account using e.g. a block bootstrap (Lahiri, 2003).”
Reliability diagrams for non‐parametric density forecasts of continuous variables: Accounting for serial correlation (2010, methodology): “For an overview of those methods, see e.g. Lahiri (2003).”
Gaussian Approximation for High Dimensional Time Series (2015, background): “The latter problem has been extensively studied in the scalar case; see Politis et al. (1999), B¨uhlmann (2002), Lahiri (2003), Alexopoulos and Goldsman (2004), among others.”
Breaking the curse of dimensionality in regression (2017, background): “For bootstrapping low-dimensional problems, the issue of optimal choice of block size has been studied; see Lahiri (2013). For high-dimensional problems, deriving the optimal choice of block size based on MSE or other criteria is much harder and unknown at the moment; thus, it is left for future res”
Toward Elimination of the Warm Bias in Historic Radiosonde Temperature Records—Some New Results from a Comprehensive Intercomparison of Upper-Air Data (2008, methodology): “The trend-sampling uncertainty in the trend estimates has been estimated with a bootstrap method (Lahiri 2003) and is 0.”
Resampling methods for spatial regression models under a class of stochastic designs (2006, methodology): “See Chapter 12 of [21] for more on resampling methodology for spatial data.”
On the range of validity of the autoregressive sieve bootstrap (2012, background): “For an overview see Bühlmann (2002), Lahiri (2003), Politis (2003) and Paparoditis and Politis (2009).”
Robust Performance Hypothesis Testing with the Sharpe Ratio (2008, positive): “Most of the commonly used kernels have q = 2, such as the Parzen, Tukey-Hanning, and QuadraticSpectral (QS) kernels, but exceptions do exist. For example, the Bartlett kernel has q = 1 and the Truncated kernel has q = ∞. For a broader discussion on this issue, see see Andrews (1991) again. Once a pa”
Bipower-type estimation in a noisy diffusion setting (2008, background): “1 in Lahiri [17], which can be proven in the same way as Theorem 6.”