Reducing the width of confidence intervals for the difference between two population means by inverting adaptive tests.

In the last decade, it has been shown that an adaptive testing method could be used, along with the Robbins-Monro search procedure, to obtain confidence intervals that are often narrower than traditional confidence intervals. However, these confidence interval limits require a great deal of computation and some familiarity with stochastic search methods. We propose a method for estimating the limits of confidence intervals that uses only a few tests of significance.

Regaining confidence in confidence intervals for the mean treatment effect.

In many experiments, it is necessary to evaluate the effectiveness of a treatment by comparing the responses of two groups of subjects. This evaluation is often performed by using a confidence interval for the difference between the population means. To compute the limits of this confidence interval, researchers usually use the pooled t formulas, which are derived by assuming normally distributed errors.

An adaptive test for a subset of coefficients in a multivariate regression model.

An adaptive multivariate test is proposed for a subset of regression coefficients in a linear model. This adaptive method uses the studentized deleted residuals to calculate an appropriate weight for each observation. The weights are then used to compute Wilk's lambda for the weighted model.

An adaptive test of significance for a subset of regression coefficients.

An F-test for a subset of regression coefficients is often used in order to compare two nested linear models. An adaptive test is proposed that has higher power than this F-test for many non-normal distributions of error terms. The adaptive test uses a weighted least squares procedure with weights determined from the Studentized deleted residuals from a linear model.