scholarly journals A Note on Wavelet Estimation of the Derivatives of a Regression Function in a Random Design Setting

2014 ◽  
Vol 2014 ◽  
pp. 1-8 ◽  
Author(s):  
Christophe Chesneau
Keyword(s):  
Regression Function ◽  
Rates Of Convergence ◽  
Nonparametric Regression Model ◽  
Random Design ◽  
Squared Error ◽  
Integrated Squared Error ◽  
The Mean ◽  
Derivatives Of ◽  
Wavelet Estimators ◽  
Fast Rates

We investigate the estimation of the derivatives of a regression function in the nonparametric regression model with random design. New wavelet estimators are developed. Their performances are evaluated via the mean integrated squared error. Fast rates of convergence are obtained for a wide class of unknown functions.

scholarly journals A Note on the Adaptive Estimation of a Multiplicative Separable Regression Function

2014 ◽  
Vol 2014 ◽  
pp. 1-7
Author(s):  
Christophe Chesneau
Keyword(s):  
Regression Model ◽  
Rate Of Convergence ◽  
Nonparametric Regression ◽  
Adaptive Estimation ◽  
Regression Function ◽  
Nonparametric Regression Model ◽  
Mean Integrated Squared Error ◽  
Squared Error ◽  
Integrated Squared Error ◽  
Separable Regression

We investigate the estimation of a multiplicative separable regression function from a bidimensional nonparametric regression model with random design. We present a general estimator for this problem and study its mean integrated squared error (MISE) properties. A wavelet version of this estimator is developed. In some situations, we prove that it attains the standard unidimensional rate of convergence under the MISE over Besov balls.

scholarly journals Nonparametric relative recursive regression

2020 ◽  
Vol 8 (1) ◽  
pp. 221-238
Author(s):  
Yousri Slaoui ◽  
Salah Khardani
Keyword(s):  
Approximation Method ◽  
Regression Function ◽  
Mean Integrated Squared Error ◽  
Response Variable ◽  
Squared Error ◽  
Regression Estimators ◽  
Integrated Squared Error ◽  
The Mean ◽  
Outlier Data ◽  
Bias Variance

AbstractIn this paper, we propose the problem of estimating a regression function recursively based on the minimization of the Mean Squared Relative Error (MSRE), where outlier data are present and the response variable of the model is positive. We construct an alternative estimation of the regression function using a stochastic approximation method. The Bias, variance, and Mean Integrated Squared Error (MISE) are computed explicitly. The asymptotic normality of the proposed estimator is also proved. Moreover, we conduct a simulation to compare the performance of our proposed estimators with that of the two classical kernel regression estimators and then through a real Malaria dataset.

scholarly journals Transmetric Density Estimation

2016 ◽  
Vol 5 (2) ◽  
pp. 35
Author(s):  
Sigve Hovda
Keyword(s):  
Density Estimation ◽  
Kernel Density Estimation ◽  
Kernel Density ◽  
Convergence Order ◽  
Graphical Display ◽  
Mean Integrated Squared Error ◽  
Squared Error ◽  
Integrated Squared Error ◽  
The Mean ◽  
Convergence Orders

<div>A transmetric is a generalization of a metric that is tailored to properties needed in kernel density estimation.  Using transmetrics in kernel density estimation is an intuitive way to make assumptions on the kernel of the distribution to improve convergence orders and to reduce the number of dimensions in the graphical display.  This framework is required for discussing the estimators that are suggested by Hovda (2014).</div><div> </div><div>Asymptotic arguments for the bias and the mean integrated squared error is difficult in the general case, but some results are given when the transmetric is of the type defined in Hovda (2014).  An important contribution of this paper is that the convergence order can be as high as $4/5$, regardless of the number of dimensions.</div>

Minimization of Error Functionals over Perceptron Networks

2008 ◽  
Vol 20 (1) ◽  
pp. 252-270 ◽  
Author(s):  
Věra Kůrková
Keyword(s):  
Gaussian Function ◽  
Regression Function ◽  
Rates Of Convergence ◽  
Oscillatory Behavior ◽  
Training Data ◽  
Partial Derivatives ◽  
High Regularity ◽  
Variational Norms ◽  
Derivatives Of ◽  
Error Dependence

Supervised learning of perceptron networks is investigated as an optimization problem. It is shown that both the theoretical and the empirical error functionals achieve minima over sets of functions computable by networks with a given number n of perceptrons. Upper bounds on rates of convergence of these minima with n increasing are derived. The bounds depend on a certain regularity of training data expressed in terms of variational norms of functions interpolating the data (in the case of the empirical error) and the regression function (in the case of the expected error). Dependence of this type of regularity on dimensionality and on magnitudes of partial derivatives is investigated. Conditions on the data, which guarantee that a good approximation of global minima of error functionals can be achieved using networks with a limited complexity, are derived. The conditions are in terms of oscillatory behavior of the data measured by the product of a function of the number of variables d, which is decreasing exponentially fast, and the maximum of the magnitudes of the squares of the L1-norms of the iterated partial derivatives of the order d of the regression function or some function, which interpolates the sample of the data. The results are illustrated by examples of data with small and high regularity constructed using Boolean functions and the gaussian function.

NONLINEAR WAVELET ESTIMATION OF CONDITIONAL DENSITY UNDER LEFT-TRUNCATED AND α-MIXING ASSUMPTIONS

2011 ◽  
Vol 09 (06) ◽  
pp. 989-1023 ◽  
Author(s):  
SI-LI NIU ◽  
HAN-YING LIANG
Keyword(s):  
Asymptotic Expression ◽  
Kernel Estimator ◽  
Conditional Density ◽  
Left Truncation ◽  
Mean Integrated Squared Error ◽  
Wavelet Estimator ◽  
Squared Error ◽  
Integrated Squared Error ◽  
The Mean ◽  
Mixing Sequence

In this paper, we construct a nonlinear wavelet estimator of conditional density function for a left truncation model. We provide an asymptotic expression for the mean integrated squared error (MISE) of the estimator. It is assumed that the lifetime observations form a stationary α-mixing sequence. Unlike for kernel estimator, the MISE expression of the nonlinear wavelet estimator is not affected by the presence of discontinuities in the curves.

scholarly journals CONSISTENCY OF KERNEL-TYPE ESTIMATORS FOR THE FIRST AND SECOND DERIVATIVES OF A PERIODIC POISSON INTENSITY FUNCTION

2007 ◽  
Vol 6 (2) ◽  
pp. 47
Author(s):  
I W. MANGKU ◽  
S. SYAMSURI ◽  
H. HERNIWAT
Keyword(s):  
Mean Squared Error ◽  
Intensity Function ◽  
Parametric Form ◽  
Bounded Interval ◽  
Squared Error ◽  
Single Realization ◽  
Second Derivatives ◽  
The Mean ◽  
Derivatives Of ◽  
Kernel Type

<p>We construct and investigate consistent kernel-type estimators for the first and second derivatives of a periodic Poisson intensity function when the period is known. We do not assume any particular parametric form for the intensity function. More- over, we consider the situation when only a single realization of the Poisson process is available, and only observed in a bounded interval. We prove that the proposed estimators are consistent when the length of the interval goes to infinity. We also prove that the mean-squared error of the estimators converge to zero when the length of the interval goes to infinity.<br />1991 Mathematics Subject Classification: 60G55, 62G05, 62G20.</p>

scholarly journals Properties of Transmetric Density Estimation

2016 ◽  
Vol 5 (3) ◽  
pp. 63
Author(s):  
Sigve Hovda
Keyword(s):  
Density Estimation ◽  
Kernel Density ◽  
Density Estimator ◽  
Unified Approach ◽  
Squared Error ◽  
Special Cases ◽  
Integrated Squared Error ◽  
The Common ◽  
The Mean ◽  
Convergence Orders

Transmetric density estimation is a generalization of kernel density estimation that is proposed in Hovda(2014) and Hovda (2016), This framework involves the possibility of making assumptions on the kernel of the distribution to improve convergence orders and to reduce the number of dimensions in the graphical display.  In this paper we show that several state-of-the-art nonparametric, semiparametric and even parametric methods are special cases of this formulation, meaning that there is a unified approach. Moreover, it is shown that parameters can be trained using unbiased cross-validation.  When parameter estimation is included, the mean integrated squared error of the transmetric density estimator is lower than for the common kernel density estimator, when the number of dimensions is larger than two.

scholarly journals Optimizing Time Histograms for Non-Poissonian Spike Trains

2011 ◽  
Vol 23 (12) ◽  
pp. 3125-3144 ◽  
Author(s):  
Takahiro Omi ◽  
Shigeru Shinomoto
Keyword(s):  
Goodness Of Fit ◽  
Optimization Method ◽  
Spike Trains ◽  
Time Axis ◽  
Squared Error ◽  
Neurophysiological Studies ◽  
Inhomogeneous Density ◽  
Integrated Squared Error ◽  
The Mean ◽  
The Given

The time histogram is a fundamental tool for representing the inhomogeneous density of event occurrences such as neuronal firings. The shape of a histogram critically depends on the size of the bins that partition the time axis. In most neurophysiological studies, however, researchers have arbitrarily selected the bin size when analyzing fluctuations in neuronal activity. A rigorous method for selecting the appropriate bin size was recently derived so that the mean integrated squared error between the time histogram and the unknown underlying rate is minimized (Shimazaki & Shinomoto, 2007 ). This derivation assumes that spikes are independently drawn from a given rate. However, in practice, biological neurons express non-Poissonian features in their firing patterns, such that the spike occurrence depends on the preceding spikes, which inevitably deteriorate the optimization. In this letter, we revise the method for selecting the bin size by considering the possible non-Poissonian features. Improvement in the goodness of fit of the time histogram is assessed and confirmed by numerically simulated non-Poissonian spike trains derived from the given fluctuating rate. For some experimental data, the revised algorithm transforms the shape of the time histogram from the Poissonian optimization method.

Sign in / Sign up

Export Citation Format

Share Document