The Role of Statistical Models in the Prediction of Tropical Cyclone Motion

Tropical cyclones (tropical storms, hurricanes, typhoons, etc.) occur over many of the earth's tropical marine areas. Responsibility for tracking and predicting the future course of these storms is assigned to one or more domestic or foreign meteorological services. These services routinely activate a number of statistical and dynamical prediction models as objective guidance preparatory to issuing official forecasts on these storms. In this article, the role of the statistical models in this process is examined.     

Non-Normal Bivariate Distributions with Normal Marginals

The purpose of this note is to indicate that Fieller's Theorem can be expressed in the matrix formulation of the general linear model. The practical consequence is that one general computer program which can estimate the parameters and test the validity of a pertinent model, can also compute confidence limits for the ratios of any linear combinations of the parameters.     

Effects of Political Advertising

Relationships between broadcast advertising exposure and variouscognitive and affective orientations were assessed in a surveyof voters during a congressional election campaign. Exposurewas moderately correlated with political knowledge and interest.Highly exposed voters were somewhat more likely to attach higheragenda priorities to issues and candidate attributes emphasizedin the commercials. Personal affect toward each candidate wasmildly associated with advertising exposure frequency.     

Tell Your Stories about China

I have just finished writing my new book and I appreciate the efforts of everyone who has written stories for "My Foreign Teacher and I "essay contest. Those which I read left me with the knowledge that their experiences were all worth sharing and writing about. Whether foreign teachers or Chinese students, both have had     

Response transformations in repeated measures and growth curve models

This article describes estimation and inference procedures for the parameters of the Box-Cox and foided-power transformations in repeated measures and growth curve models. Procedures for computing maximum likelihood estimates of the transformation and covariance parameters under several covanance structures (omnibus sphericity, local sphericity, and unstructured) are described. Lack of fit statistics and hypothesis tests for comparing these structures also are described. The procedures are illustrated on three data sets. Software for performing the analyses in the SAS System is described and is available from the authors.