Masaaki Taguri

Prediction of nitrogen oxide concentration by a regression model

Abstract In a previous paper (Inoue et al ., 1986, Atmospheric Environment 20 , 71–85), we carried out regression analysis on hourly NO-concentration data and outlined the basis for predicting concentrations from such models. That analysis was carried out under the assumption that the values of explanatory variables at a prediction time were available. In this follow-up paper, we have investigated some prediction schemes applicable in more practical situations and have concluded that our scheme is practicable for the prediction of concentrations for 1 h later, however it may be difficult to apply this scheme to predictions for 2 or more h later.

Stability of two prediction schemes for hourly nitrogen oxide concentrations by a regression model

Abstract In a preceding paper (Inoue et al, 1986b, Atmospheric Environment20, 2325–2337), we proposed two prediction schemes for hourly nitrogen oxide (NO) concentration using the regression model with autocorrelated error terms, and applied these schemes to the prediction of NO-concentration at m h later. Data analyses based on the data sets observed at a measurement site for a year showed that these schemes are practical for the predictions 1 h later. In this follow up paper, we apply these schemes to the prediction for other years and/or other measurement sites, and investigate the stability of the assumed regression model and the adopted prediction schemes not only numerically but also theoretically. From these analyses, our prediction schemes are shown to be stable for the prediction of NO-concentration in other years.

OPTIMUM CLASSIFICATION BOUNDARIES BASED ON A CONCOMITANT VARIABLE IN SAMPLE SURVEY: SOME APPLICATION TO THE CURRENT STATISTICS OF COMMERCE

Publisher Summary This chapter presents a stratified random sampling procedure using a concomitant variable for two sample allocation methods—equal allocation (EA) and Neyman allocation (NA). It discusses some kinds of robustness in the proposed procedure. The analysis of these facets of robustness must give effect to the procedure in practical situations. The procedure is applied to some practical example—the Current Statistics of Commerce in Japan, which shows great improvement of the precision in estimation. It is impossible to stratify the population based on the information of the objective variable Y, whose mean should be estimated. It is usual to carry out the stratification based on the information of a concomitant variable X, which has high correlation with Y.