Let and be stationarily cross-correlated multivariate stationary sequences. Assume that all values of and all but one values of are known. We determine the best linear interpolation of the unknown value on the basis of the known values and derive a formula for the interpolation error matrix. Our assertions generalize a result of Budinský [1].
Implicit sampling is a sampling scheme for particle filters, designed to move particles one-by-one so that they remain in high-probability domains. We present a new derivation of implicit sampling, as well as a new iteration method for solving the resulting algebraic equations.
Implicit sampling is a sampling scheme for particle filters, designed to move particles one-by-one so that they remain in high-probability domains. We present a new derivation of implicit sampling, as well as a new iteration method for solving the resulting algebraic equations.
We consider a finite mixture of Gaussian regression models for high-dimensional heterogeneous data where the number of covariates may be much larger than the sample size. We propose to estimate the unknown conditional mixture density by an ℓ1-penalized maximum likelihood estimator. We shall provide an ℓ1-oracle inequality satisfied by this Lasso estimator with the Kullback–Leibler loss. In particular, we give a condition on the regularization parameter of the Lasso to obtain such an oracle inequality....
In this paper a new integrated approach to the analysis of square non-symmetric tables is introduced by means of cortrespondence analysis. The application of correspondence analysis to such tables is not successful due to the strong role played by the diagonal values: overloaded diagonals and structural zeros. Two main families of methods of resolution are integrated in this paper. The resulting method is applied to the study of commuting between the 41 Catalan counties.
En este trabajo se demuestra que las soluciones clásicas a los contrastes de hipótesis paramétricos son casos particulares de la solución bayesiana a un problema de decisión con dos alternativas, en el que el incremento de utilidad por rechazar la hipótesis nula cuando es falsa es una función lineal de la discrepancia entre el modelo paramétrico aceptado y el más verosímil de los modelos compatibles con la hipótesis nula.
En este trabajo se presenta un modelo matemático general y operativo para los problemas de decisión unietápicos cuyas consecuencias se cuantifican mediante números difusos. Ese modelo va a permitir establecer los fundamentos de las utilidades difusas mediante un desarrollo axiomático, y generalizar las formas normal y extensiva del análisis bayesiano dando condiciones para la equivalencia de las mismas. Se examinará también la particularización del análisis bayesiano en forma extensiva a la estimación...