For order $q$ kernel density estimators we show that the constant $b_q$ in $bias=b_qh^q+o(h^q)$ can be made arbitrarily small, while keeping the variance bounded. A data-based selection of bq is presented and Monte Carlo simulations illustrate the advantages of the method.

<Para ID="Par1">Motivated by a roundoff problem, we derive new expressions for cumulants of a random variable distributed uniformly on <InlineEquation ID="IEq3"> <EquationSource Format="TEX">$$0,1, \ldots , n-1$$</EquationSource> <EquationSource Format="MATHML"> <math xmlns:xlink="http://www.w3.org/1999/xlink"> <mrow> <mn>0</mn> <mo>,</mo> <mn>1</mn> <mo>,</mo> <mo>…</mo> <mo>,</mo> <mi>n</mi> <mo>-</mo> <mn>1</mn> </mrow> </math> </EquationSource> </InlineEquation>. Their computational efficiency over a known expression is discussed. Copyright Springer-Verlag Berlin Heidelberg 2015

Simple transformations are given for reducing/stabilizing bias, skewness and kurtosis, including the first such transformations for kurtosis. The transformations are based on cumulant expansions and the effect of transformations on their main coefficients. The proposed transformations are...

We show that the correlation between the estimates of two parameters is almost unchanged if they are each transformed in an arbitrary way. To be more specific, the correlation of two estimates is invariant (except for a possible sign change) up to a first order approximation, to smooth...

We give expressions for the distribution and density of a product of gamma or equivalently chi-square random variables. In particular, we give the distribution of the product of two independent gamma variables of mean k in terms of the Bessel functions K <Subscript>1</Subscript>, … , K <Subscript> k </Subscript>. Copyright Springer...</subscript></subscript>

A family of confidence bands (simultaneous confidence regions) is given for EY=<Emphasis Type="Bold">x′<Emphasis Type="BoldItalic">β that are piecewise-linear in <Emphasis Type="Bold">x. Normality is assumed. These confidence bands are advocated over the usual hyperbolic band when the region of prime interest is distant from <InlineEquation ID="IEq1"> <EquationSource Format="TEX">$${\overline{\bf x}}$$</EquationSource> </InlineEquation>. In...</equationsource></inlineequation></emphasis></emphasis></emphasis>

Given a random sample of size <InlineEquation ID="IEq1"> <EquationSource Format="TEX">$$n$$</EquationSource> <EquationSource Format="MATHML"> <math xmlns:xlink="http://www.w3.org/1999/xlink"> <mi>n</mi> </math> </EquationSource> </InlineEquation> with mean <InlineEquation ID="IEq2"> <EquationSource Format="TEX">$$\overline{X} $$</EquationSource> <EquationSource Format="MATHML"> <math xmlns:xlink="http://www.w3.org/1999/xlink"> <mover> <mi>X</mi> <mo>¯</mo> </mover> </math> </EquationSource> </InlineEquation> and standard deviation <InlineEquation ID="IEq3"> <EquationSource Format="TEX">$$s$$</EquationSource> <EquationSource Format="MATHML"> <math xmlns:xlink="http://www.w3.org/1999/xlink"> <mi>s</mi> </math> </EquationSource> </InlineEquation> from a symmetric distribution <InlineEquation ID="IEq4"> <EquationSource Format="TEX">$$F(x; \mu , \sigma )=F_{0} (( x- \mu ) / \sigma ) $$</EquationSource> <EquationSource Format="MATHML"> <math xmlns:xlink="http://www.w3.org/1999/xlink"> <mrow> <mi>F</mi> <mrow> <mo stretchy="false">(</mo> <mi>x</mi> <mo>;</mo> <mi mathvariant="italic">μ</mi> <mo>,</mo> <mi mathvariant="italic">σ</mi> <mo stretchy="false">)</mo> </mrow> <mo>=</mo> <msub> <mi>F</mi> <mn>0</mn> </msub> <mrow> <mo stretchy="false">(</mo> <mrow> <mo stretchy="false">(</mo> <mi>x</mi> <mo>-</mo> <mi mathvariant="italic">μ</mi> <mo stretchy="false">)</mo> </mrow> <mo stretchy="false">/</mo> <mi mathvariant="italic">σ</mi> <mo stretchy="false">)</mo> </mrow> </mrow> </math> </EquationSource> </InlineEquation> with <InlineEquation ID="IEq5"> <EquationSource Format="TEX">$$F_0$$</EquationSource> <EquationSource Format="MATHML"> <math xmlns:xlink="http://www.w3.org/1999/xlink"> <msub> <mi>F</mi> <mn>0</mn> </msub> </math> </EquationSource> </InlineEquation>...</equationsource></equationsource></inlineequation></equationsource></equationsource></inlineequation></equationsource></equationsource></inlineequation></equationsource></equationsource></inlineequation></equationsource></equationsource></inlineequation>

Consider a sample of independent and identical bivariate observations. Simple consistent confidence intervals for the variances, covariance, and correlation of the underlying population are obtained from their influence functions. They contrast with their confidence intervals obtained under the...

We consider the (possibly nonlinear) regression model in <InlineEquation ID="IEq4"> <EquationSource Format="TEX">$$\mathbb{R }^q$$</EquationSource> <EquationSource Format="MATHML"> <math xmlns:xlink="http://www.w3.org/1999/xlink"> <msup> <mrow> <mi mathvariant="double-struck">R</mi> </mrow> <mi>q</mi> </msup> </math> </EquationSource> </InlineEquation> with shift parameter <InlineEquation ID="IEq5"> <EquationSource Format="TEX">$$\alpha $$</EquationSource> <EquationSource Format="MATHML"> <math xmlns:xlink="http://www.w3.org/1999/xlink"> <mi mathvariant="italic">α</mi> </math> </EquationSource> </InlineEquation> in <InlineEquation ID="IEq6"> <EquationSource Format="TEX">$$\mathbb{R }^q$$</EquationSource> <EquationSource Format="MATHML"> <math xmlns:xlink="http://www.w3.org/1999/xlink"> <msup> <mrow> <mi mathvariant="double-struck">R</mi> </mrow> <mi>q</mi> </msup> </math> </EquationSource> </InlineEquation> and other parameters <InlineEquation ID="IEq7"> <EquationSource Format="TEX">$$\beta $$</EquationSource> <EquationSource Format="MATHML"> <math xmlns:xlink="http://www.w3.org/1999/xlink"> <mi mathvariant="italic">β</mi> </math> </EquationSource> </InlineEquation> in <InlineEquation ID="IEq8"> <EquationSource Format="TEX">$$\mathbb{R }^p$$</EquationSource> <EquationSource Format="MATHML"> <math xmlns:xlink="http://www.w3.org/1999/xlink"> <msup> <mrow> <mi mathvariant="double-struck">R</mi> </mrow> <mi>p</mi> </msup> </math> </EquationSource> </InlineEquation>. Residuals are assumed to be from an unknown...</equationsource></equationsource></inlineequation></equationsource></equationsource></inlineequation></equationsource></equationsource></inlineequation></equationsource></equationsource></inlineequation></equationsource></equationsource></inlineequation>

Two methods are given for adapting a kernel density estimate to obtain an estimate of a density function with bias O(h <Superscript> p </Superscript>) for any given p, where h=h(n) is the bandwidth and n is the sample size. The first method is standard. The second method is new and involves use of Bell polynomials. The...</superscript>