The restricted maximum likelihood (REML) estimator of the dispersion matrix for random coefficient models is rewritten in terms of the sufficient statistics of the individual regressions.

We derive a simple empirical photometric redshift estimator using a training set of galaxies with multiband photometry and measured redshifts in the Hubble Deep Field (HDF). This estimator is model-independent; it does not use spectral templates. The dispersion between the estimated redshifts and the spectroscopically measured ones is small; the dispersions range from σz ≃ 0.03 to 0.1 for z ∼< ...

The problem of estimating the number of members in a multicast session through probabilistic polling corresponds to that of estimating the parameter n of the Binomial n p , distribution. This allows an interval estimator for n to be derived. The tradeoff between the relative dispersion of this estimator and the overhead it requires is characterized in a manner that may be mapped to application ...

The Minimum Covariance Determinant (MCD) scatter estimator is a highly robust estimator for the dispersion matrix of a multivariate, elliptically symmetric distribution. It is relatively fast to compute and intuitively appealing. In this note we derive its innuence function and compute the asymptotic variances of its elements. A comparison with the one step reweighted MCD and with S-estimators ...

Starting from the one{dimensional results by Wang et al (1994) we consider the performance of the ordinary least squares estimator in comparison to the best linear unbiased estimator under an error component model with random eeects in units and time. Upper bounds are derived for the rst{ order approximation to the diierence between both estimators and for the spectral norm of the diierence bet...

We derive a quantile-adjusted conditional maximum likelihood estimator for the dispersion parameter of the negative binomial distribution and compare its performance, in terms of bias, to various other methods. Our estimation scheme outperforms all other methods in very small samples, typical of those from serial analysis of gene expression studies, the motivating data for this study. The impac...

The Maximum Likelihood Estimator (MLE) and Extended Quasi-Likelihood (EQL) estimator have commonly been used to estimate the unknown parameters within the joint modeling of mean and dispersion framework. However, these estimators can be very sensitive to outliers in the data. In order to overcome this disadvantage, the usage of the maximum Trimmed Likelihood Estimator (TLE) and the maximum Exte...

A Phase I estimator of the dispersion should be efficient under in-control data and robust against contaminations. Most estimation methods proposed in the literature are either efficient or robust against either sustained shifts or scattered disturbances. In this article, we propose a new estimation method of the dispersion parameter, based on exponentially weighted moving average charting, whi...

Contamination of a sampled distribution, for example by a heavy-tailed distribution, can degrade the performance of a statistical estimator. We suggest a general approach to alleviating this problem, using a version of the weighted bootstrap. The idea is to “tilt” away from the contaminated distribution by a given (but arbitrary) amount, in a direction that minimises a measure of the new distri...