Density estimation for randomly distributed circular objects

Springer Science and Business Media LLC - Tập 37 - Trang 63-69 - 1990
V. R. Prayag1, A. P. Gore2
1Department of Statistics, Modern College, Pune, India
2Department of Statistics, University of Poona, Pune, India

Tóm tắt

Nearest neighbour methods traditionally used to estimate density of a sessile biological population treat individuals as points. The present paper suggests distance-based density estimators which treat individuals as circles with variable areas. Distribution of distance between a sample point and thek-th (k = 1, 2, 3, …) nearest circle is derived. Maximum likelihood estimator of density is obtained from a random sample of point tok-th order distances. Assuming a skewed distribution for the circle radius, moment estimators of density and mean circle area are derived.

Tài liệu tham khảo

Byth K (1982) On robust distance based intensity estimators. Biometrics 38:127–135 Diggle PJ (1975) Robust density estimation using distance methods. Biometrika 62:39–48 Holgate P (1964) The efficiency of nearest neighbour estimators. Biometrics 20:647–649 Pielou EC (1960) A single mechanism to account for regular, random and aggregated populations. Journal of Ecology 48:575–584 Ripley BO (1981) Spatial statistics. John Wiley and Sons, New York Simberloff DS (1979) Nearest neighbour assessment of spatial configurations of circles rather than points. Ecology 60(4):679–685 Simberloff DS, Dillon P, King L, Lorence D, Lowrie S, Schilling E (1978) Holes in the doughnut theory. The dispersion of ant-lions. Brenesia 14/15:13–46