Model Assisted Statistics and Applications 2 (2007) 189–200 189 IOS Press Estimation of population mean at current occasion in successive sampling under a super-population model G.N. Singh ∗ and Kumari Priyanka Department of Applied Mathematics, Indian School of Mines University, Dhanbad-826 004, India Abstract. The present work is an attempt to utilize auxiliary information through a super-population linear model as well as in the structure of estimators for estimating the population mean on current occasion in two-occasion successive sampling. Two different estimators are proposed and their theoretical properties are discussed. Results are supported with empirical studies. Suitable recommendations are made. Keywords: Successive sampling, difference type, super-population, linear model, bias, variance, optimum replacement policy Mathematics Subject Classification (2000): 62D05 1. Introduction When the value of the study character of a finite population is subject to change over time, a survey carried out on a single occasion will provide information about the characteristics of the surveyed population for the given occasion only and cannot give any information on the nature or rate of change of the characteristic at different occasions and the average value of the characteristic over all occasions or the most recent occasion. To meet these requirements successive sampling provides a strong tool for generating reliable estimates. Theory of successive sampling appears to have started with the work of Jessen [16]. He pioneered using all information collected in previous investigations (or occasions). The theory was extended by Patterson [11], Rao and Graham [12], Gupta [13], Das [1], Chaturvedi and Tripathi [5] among others. Sen [2] developed estimators for the population mean on the current occasion using information on two auxiliary variables available from a previous occasion. Sen [3,4] extended his work to several auxiliary variates. Singh et al. [19] and Singh and Singh [6] used the auxiliary information on current occasion for estimating the current population mean in two-occasion successive sampling. Singh [7] extended their work for h-occasions successive sampling. Feng and Zou [18] and Biradar and Singh [17] used the auxiliary information on both the occasions for estimating the current mean in successive sampling. In many situations, information on an auxiliary variate may be readily available on the first as well as on the second occasion; for example, tonnage (or seat capacity) of each vehicle or ship is known in survey sampling of transportation, numbers of polluting industries are known in an environmental survey. Many other situations in the life sciences could be explored to show the benefits of the present study. Utilizing the auxiliary information on both the occasions Singh [8], Singh and Priyanka [9] and Singh and Priyanka [10] have proposed chain ratio, difference ∗ Corresponding author. Department of Applied Mathematics, Indian School of Mines University, Dhanbad-826 004, India. Tel.: +91 326 2201904; Fax: +91 326 2210028, 2203042; E-mail: gnsingh ism@yahoo.com. ISSN 1574-1699/07/$17.00  2007 – IOS Press and the authors. All rights reserved