You-Gan Wang

 CSIRO Mathematical and Information Sciences, CSIRO Long Pocket Laboratories,

120 Meiers Road, Indooroopilly, Queensland 4068, Australia

This talk considers how to efficiently select sampling  sites or subsamples from a finite number of samples by borrowing information from a concomitant variable (e.g. historical data) that are correlated with the outcome variable of interest.  When such concomitant variables are available, the new design can reduce cost or increase efficiency greatly at a fixed cost (sample size) compared with simple random sampling. The merits of the methodology are illustrated by two studies. Using the trawl survey data from the Northern Prawn Fisheries, the relative efficiencies in terms of the variance and MSE of the estimated mean abundance indices are estimated to range from 100% to 200%.  Using data from the aging study on Tenualosa ilisha, we show that the efficiency of age prediction using weight data is as high as 140% when compared with simple random sampling.  

This methodology has wide applications in envirometrics, genetics, fisheries and other areas. 

 For more details about the speaker, please visit:    http://www.cmis.csiro.au/You-Gan.Wang/