An Edgeworth expansion for the m out of n bootstrapped median

By A. Sakov, Peter J. Bickel. 2000

62 citations recorded by the source corpus.

Subfields: Finance, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/183f38540cf080d3d0bcaa86381a7fc6a968771d

How researchers see this paper

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

In Finance

In Statistics and Probability

Citations in the corpus

Renewable energy, oil prices, and economic activity: A Granger-causality in quantiles analysis (2018, methodology): “Following Sakov and Bickel (2000), we choose a subsample of size = T n / U, where Q⋅R is the integer part of a number, and k is a constant parameter.”
ROBUST BACKTESTING TESTS FOR VALUE-AT-RISK MODELS (2011, methodology): “In the present article, for simplicity in the computations we follow the suggestion of Sakov and Bickel (2000) and choose b = ⌊ kP 2/5 ⌋ , where b·c denotes the integer part, which yields the optimal minimax accuracy under certain conditions.”
Specification Tests of Parametric Dynamic Conditional Quantiles (2010, unknown): “As the number of subsamples, we follow the suggestion of Sakov and Bickel (2000) and we chose b = kn ; with several choices of k: For DGP1 we consider k from 7 to 9: These values correspond to b = 42; 48 and 54 for n = 100 and b = 63; 72 and 81 for n = 300; respectively. For DGP2, k is chosen to be ”
The Impact of Bootstrap Methods on Time Series Analysis (2003, result): “Nevertheless, some very recent results of Sakov and Bickel (2000) and Arcones (2001) indicate that this is not always the case: for the sample median, the i.i.d. bootstrap with resample size b = o(n) has improved accuracy as compared to the bootstrap with resample size n; an analogous result is…”
Subsampling Inference on Quantile Regression Processes (2005, methodology): “In Sakov and Bickel (2000) and in Politis, Romano and Wolf (1999) various rules are suggested for choosing the appropriate subsample size.”
Testing for Granger-causality in quantiles (2018, methodology): “Horowitz (1998) and Sakov and Bickel (2000), among others, have proposed resampling methods for quantile regression models, but their approach is valid only for independent and identically distributed (i.i.d.) data.”