Applied Nonparametric Regression: The kernel method

By Wolfgang Karl Härdle. 1990

How researchers see this paper

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

Citations in the corpus

Trend analysis of climate time series: A review of methods (2019, neutral): “There exist bootstrap adaptations Davison and Hinkley, 1997; Härdle, 1990) aimed at further increasing the accuracy of resampling-derived uncertainty measures.”
Kernel Regression for Image Processing and Reconstruction (2007, background): “In the nonparametric statistics literature, locally constant, linear, and quadratic approximations (corresponding to 0, 1, 2) have been considered most widely [3], [12]–[14].”
ROBUST LOCAL POLYNOMIAL REGRESSION FOR DEPENDENT DATA (2001, background): “Other choices of ζ are possible, for example in the context of robustness (see Hampel, Ronchetti, Rousseeaus and Stahl (1986) and Huber (1981)), leading to the local M-type regression estimators (see Cleveland (1979), Härdle (1990), Boente and Fraiman (1989), for example).”
Regression trees for longitudinal and multiresponse data (2012, unknown): “Then J1 = ḡ(x ∗, u∗)−g(x∗, u∗) P→ 0 by condition (B3) [Härdle (1990), page 29] and J2 P→ 0 by condition (B2).”
POLYNOMIAL SPLINE CONFIDENCE BANDS FOR REGRESSION CURVES (2009, unknown): “5.2 Motorcycle data Although many authors such as Härdle (1990) have used the motorcycle data to illustrate the need for nonparametric smoothing, no formal testing was done to establish the inadequacy of parametric model for this data.”
Intertemporal Consumption and Credit Constraints: Does Total Expenditure Respond to an Exogenous Shock to Credit? (2010, unknown): “Confidence intervals are bootstrap point wise confidence intervals based on 500 replications, cf. Härdle (1990).”
Managerial Ownership and Performance (2009, unknown): “analytically in Härdle (1990). An important advantage of this approach in comparison to the piecewise regressions is that it does not pre-specify cutoff points.”
UNIFORM BAHADUR REPRESENTATION FOR LOCAL POLYNOMIAL ESTIMATES OF M-REGRESSION AND ITS APPLICATION TO THE ADDITIVE MODEL (2007, unknown): “Standard arguments (Härdle, 1990) show that under suitable smoothness conditions, m̂(x)−m(x) = h(2)b(x)+ 1 n f (x) n ∑ i=1 Kh(X i − x)εi + Rn(x), (1) where b(x) = ∫ u(2) K (u)du [m(x)+2m(x) f (x)/ f (x)]/2, while f (x) is the covariate density function and εi ≡ Yi − m(X i ) is the error term.”