Hybrid and Size-Corrected Subsampling Methods

By Donald W. K. Andrews, Patrik Guggenberger. 2007

126 citations recorded by the source corpus.

Subfields: Finance, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/b48f735e639dc75012917b1079c09afbf693a4e9

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

Select the Valid and Relevant Moments: An Information-Based LASSO for GMM with Many Moments (2013, methodology): “More recent papers include Berkowitz et al. (2012), Conley et al. (2012), Doko Tchatoka and Dufour (2012), Guggenberger (2012), Nevo and Rosen (2012), and DiTraglia (2012), among others.”
Uniform Inference in Autoregressive Models (2007, background): “Symmetric subsampling intervals would have asymptotically uniformly correct coverage, but will be asymptotically uniformly conservative, that is, the limit of the maximal coverage is higher than the declared level (see Andrews and Guggenberger (2007a)).”
Fixed-Effect Panel Threshold Model using Stata (2015, methodology): “Andrews and Guggenberger (2009) then introduced a hybrid subsampling method and size-corrected methods of constructing tests and confidence intervals that have correct asymptotic size. However, literature concerning the panel threshold model is still very limited, and there is still no theoretical d”
Incorrect asymptotic size of subsampling procedures based on post-consistent model selection estimators (2009, methodology): “Furthermore, the size-correction methods of Andrews and Guggenberger (2005a, 2009a) do not work in this example because Assumptions LF, LS, and LH in the Appendix of Andrews and Guggenberger (2005a) fail.”
Nonparametric Instrumental Variable Estimation Under Monotonicity (2015, unknown): “Q.E.D.”
Testing for Predictability in Conditionally Heteroskedastic Stock Returns (2015, background): “and, by using the same arguments as in Proof of Theorem 2 of Andrews and Guggenberger (2012), we can further show that 1 T T ∑ t=q+2 ŝ−2 y,t x d t−1εy,t = 1 T T ∑ t=q+2 s−2 y,t x d t−1εy,t + 1 T T ∑ t=q+2 (ŝ−2 y,t − s−2 y,t )xd t−1εy,t”
Bootstrap Methods in Econometrics (2018, unknown): “Andrews and Guggenberger (2009) describe methods for overcoming this problem.”
Sensitivity analysis using approximate moment condition models (2018, background): “These bounds have implications for procedures proposed by Andrews and Guggenberger (2009), DiTraglia (2016) and McCloskey (2020), who consider the case where some moments are known to be correctly specified and no a priori bound is placed on the magnitude of misspecification of the remaining moments”
Nonparametric estimation and inference about the overlap of two distributions (2012, background): “In addition, it can be that the two densities while not identical are close to each other over a range of values, the so-called drifting distribution case, Andrews and Guggenberger (2009), and this would induce a distortion in the usual asymptotic approximation.”
ASYMPTOTIC SIZE AND A PROBLEM WITH SUBSAMPLING AND WITH THE m OUT OF n BOOTSTRAP (2009, methodology): “…two-sided tests for all values of a correlation not close to zero, see Andrews and Guggenberger (2005); (iii) the moment inequality example, see Andrews and Guggenberger (2009b), and (iv) the autoregressive example for lower one-sided and symmetric two-sided tests, see Andrews and Guggenberger…”
Bonferroni-Based Size-Correction for Nonstandard Testing Problems (2017, methodology): “…and Pötscher (2005) in the context of inference after model selection, Stoye (2009) in the context of inference on partially identified parameters and Andrews and Guggenberger (2009a) (AG henceforth) in the context of inference on the autoregressive parameter in a first-order autoregressive model.”
Extrapolate-Ing: External Validity and Overidentification in the Late Framework (2010, unknown): “In a related setting, Andrews and Guggenberger (2009) addressed a pretest problem using subsampling.”
Bootstrapping and sample splitting for high-dimensional, assumption-lean inference (2016, methodology): “While this is a larger literature than can be addressed completely here, it includes early work on model selection [35] and model averaging interpretations [31]; the impossibility results of [38] and [16] on random X and model misspecification; methods based on resampling or sample splitting [18, 19”
VALIDITY OF SUBSAMPLING AND “PLUG-IN ASYMPTOTIC” INFERENCE FOR PARAMETERS DEFINED BY MOMENT INEQUALITIES (2009, methodology): “For the case of PSC-FCV tests, which are relevant here, only Assumptions A, B, L(i), N, and O(a), defined in Andrews and Guggenberger (2009a), are needed for Theorem 3 of Andrews and Guggenberger (2009a).”