Alternative Sampling Designs Some Applications of Qualitative Data in Survey Sampling
In this paper the author introduces alternative sampling designs based on order statistics, i.e. ranked set sampling RSS and extreme ranked set sampling ERSS. It is known that RSS is in many cases more efficient than the widely used standard simple random sampling SRS, i.e. it gives more precise assessments of basic population parameters. And what is important, the increase of the efficiency can be often achieved at no additional cost or very little cost. The major objective of this paper is to present a possibility of application of the RSS procedure in market and consumer surveys. The author introduces and analyses an example of sales estimation in pharmacies. The method of data collection in this survey is exact (without non-sampling errors) and is done by a connection with pharmacies' computers. An additional information used in the survey is qualitative data from questionnaires, which are known to be not exact because of non-sampling errors (e.g. intentional incorrect answers, poor memory etc.). In the presented survey errors affect about 50% of the questionnaires. Despite of these errors, the use of auxiliary information in the form of qualitative data leads to the increase of the efficiency of the estimation and gives more precise assessments than the widely used simple random sampling. The problem is analyzed on a basis of a simulation study. Also another example of a successful application of RSS method is presented. The author analyzes a survey, which is aimed at estimation of the number of pharmacies in Polish towns of 10000-100000 inhabitants. A concomitant (auxiliary) variable used to implement the ranking is the number of inhabitants in the town. In a conducted simulation study RSS also proved to be superior to standard simple random sampling and gave much more precise assessments. (original abstract)
- Cobby J. M., Ridout M. S., Basset P.J., Large R.V., (1985), An Investigation into the Use of Ranked Set Sampling on Grass and Grass-Clover Swards, Grass Forage Sci. 40, pp. 257-263.
- Dell T.R., Clutter J.L., (1972), Ranked Set Sampling Theory with Order Statistics Background, Biometrics 28, pp. 545-555.
- Halls L.S., Dell T.R., (1966), Trial of Ranked Set Sampling for Forage Yields, Forest Sci. 12 (1), pp. 22-26.
- Johnson G.D., Patil G.P., Sinha A.K., (1993), Ranked Set Sampling for Vegetation Research, Abstracta Botanica 17, pp. 87-102.
- Martin W.L., Sharik T.L., Oderwald R.G., D.W. Smith., (1980), Evaluation of Ranked set Sampling for Estimating Scrub Phytomass in Appalachian Oak Forests, Publication No. FWS-4-80, School of Forestry and Wildlife Resources, Virginia Polytechnic Institute and State University, Blacksburg, V. A.
- McIntyre G.A., (1952), A Method of Unbiased Selective Sampling, Using Ranked Sets, Australian J. Agricultural Research 3, pp. 385-390.
- Mutlak H.A., McDonald L.L., (1990a), Ranked Set Sampling with Size Biased Probability of Selection, Biometrics 46, pp. 435-445.
- Mutlak H.A., McDonald L.L., (1990b), Ranked Set Sampling with Respect to Concomitant Variables and with Size Biased Probability of Selection, Commun. Statist. - Theory Math. 19 (1), pp. 205-219.
- Patil G.P., Taillie C., (1993), Environmental Sampling Observational Economy, and Statistical Inference with Emphasis on Ranked Set Sampling, Encounter Sampling and Composite Sampling, Bulletin ISI Proceedings of 49-th Session, Firenze, pp. 295-312.
- Samawi H.M., Mohmmad S., Abu-Dayyeh W., (1996), Estimating the Population Means Using Extreme Ranked Set Sampling, Biom. Journal, 38, pp. 577-586.
- Stokes S.L., (1977), Ranked Set Sampling with Concomitant Variables, Comm. Statist. Theory Methods 6, pp. 1207-1211.
- Stokes S.L., (1980), Estimation of Variance using Judgment Ordered Ranked Set Samples, Biometrics 36, pp. 35-42.
- Stokes S.L., (1986), Ranked Set Sampling. [in:] S. Kotz et al., eds., Encyclopedia of Statistical Sciences, Wiley, New York, pp. 585-588.
- Takahasi K., Wakimoto K., (1968), On Unbiased Estimates of the Population Mean Based on the Sample Stratified Means of Ordering, Ann. Inst. Statist. Math. 20, pp. 1-31.
- Yanagawa T., Chen S.H., (1980), The MG Procedure in Ranked Set Sampling, J. Statist. Plann. Inference 4, pp. 33-44.
- Yu P.L.H., Lam K. (1997), Regression Estimator in Ranked Set Sampling, Biometrics, 53, pp. 1070-1080.