Non-Parametric Function Fitting

Abstract

Summary In this note we consider the problem of fitting a general functional relationship between two variables. We require only that the function to be fitted is, in some sense, “smooth”, and do not assume that it has a known mathematical form involving only a finite number of unknown parameters.

A nonparametric test for changing trends

“…In this way, we can avoid nonmonotonic power in our dynamic model. To this end, we detrend the time series y t nonparametrically based on Priestley and Chao (1972). To find a feasible estimate of r ¼ ðr 1 ; .…”

A simple ordered data estimator for inverse density weighted expectations

“…The factor 2 in the variance ofỹ was also noted by Mack and Mu¨ller (1988) in the related problem of estimating a nonparametric conditional expectation using the Priestley and Chao (1972) estimator. See also Wand and Jones (1995, p. 131).…”

Confidence intervals for nonparametric regression functions with missing data: Multiple design case

“…In the case of complete observations, the estimation of θ is studied extensively. See [2][3][4][5][6][7][8], among others.…”