在生態學中，為了維護及保育物種，知曉物種數量是相當重要的過程，而估計物種數量的方法中，使用有無地圖又是較節省成本及方便的估計方式。本篇運用核估計，並單純只使用有無地圖來估計物種的豐富度，並與之前提及的估計方法，比較是否能改善估計出來的結果。在第三章中，本篇使用R軟體套件，搭配不同的標準差去模擬生物在實際區域的分布行為，而第四章中，本篇使用一座巴拿馬的實際小島資料去進行物種豐富度的分析，在模擬及實例分析下，探討使用核估計法來估計物種豐富度，並與隨機放置模型、HG 方法和修正 HG 方法、混合珈瑪普瓦松模型進行比較，在哪些情況下有較好的表現。

In ecology, the information of the species abundance is very important for natural conservation. Using presence-absence map is cost-effective and convenient to estimate amounts of species. In this study, we use kernel density estimation method  to estimate the species abundance in presence-absence map. We simulate data under several different spatial distributions, and compare our method with the random placement model, the HG method, the modified HG method and the mixed Gamma-Poisson model. The data of Panama is also used for comparing the estimation performance.

目錄
第一章 緒論 1 
第二章 估計方法 4 
第一節 隨機放置模型(Random placement model) 4 
第二節 HG方法及修正HG方法(HG Method And The modified HG Method) 5 
第三節 混合珈瑪普瓦松模型(The Mixed Gamma-Poisson(MGP) Model) 6 
第四節 核估計方法(Kernel Density Estimation Method) 10 
第三章 模擬研究  14 
第四章 實例分析  18 
第五章 結論 20 
參考文獻 22

圖目錄
1.1 有無地圖的繪製方法 2 
2.1 有無地圖尺度劃分方式 9 
2.2 頻寬選取差異圖  11 
3.1 湯瑪士模擬物種散佈圖 給定N=2000  15

表目錄
3.1 使用 rThomas 指令進行500次模擬，利用五種方法所得到物種豐富度的估計結果  16
4.1 巴拿馬實際資料分析，使用五種估計方法所得到的物種豐度  18

[1] E. Conlisk, J. Conlisk, B. Enquist, J. Thompson, and J. Harte, “Improved abundance prediction from presence–absence data,” Global Ecology and Biogeography, vol. 18, no. 1, pp. 1–10, 2009. 
[2] A. R. Solow and W. K. Smith, “On predicting abundance from occupancy,” The American Naturalist, vol. 176, no. 1, pp. 96–98, 2010. 
[3] B. D. Coleman, “On random placement and species-area relations,” Mathematical Biosciences, vol. 54, no. 3-4, pp. 191–215, 1981. 
[4] F. He and K. J. Gaston, “Estimating species abundance from occurrence,” The American Naturalist, vol. 156, no. 5, pp. 553–559, 2000. 
[5] M. Warren, M. McGeoch, and S. Chown, “Predicting abundance from occupancy: a test for an aggregated insect assemblage,” Journal of Animal Ecology, vol. 72, no. 3, pp. 468–477, 2003. 
[6] W.-H. Hwang and F. He, “Estimating abundance from presence/absence maps,” Methods in Ecology and Evolution, vol. 2, no. 5, pp. 550–559, 2011. 
[7] M. Rosenblatt, “Remarks on some nonparametric estimates of a density function,” The Annals of Mathematical Statistics, vol. 27, no. 3, pp. 832– 837, 1956. 22 
[8] E. Parzen, “On estimation of a probability density function and mode,” The annals of mathematical statistics, vol. 33, no. 3, pp. 1065–1076, 1962.
[9] F. He and S. P. Hubbell, “Percolation theory for the distribution and abundance of species,” Physical Review Letters, vol. 91, no. 19, p. 198103, 2003. 
[10] P. Hall, J. S. Marron, and B. U. Park, “Smoothed cross-validation,” Probability Theory and Related Fields, vol. 92, no. 1, pp. 1–20, 1992. 
[11] Y.-M. Chang, N.-J. Hsu, and H.-C. Huang, “Semiparametric estimation and selection for nonstationary spatial covariance functions,” Journal of Computational and Graphical Statistics, vol. 19, pp. 117–139, 2010. 
[12] D. Yin and F. He, “A simple method for estimating species abundance from occurrence maps,” Methods in Ecology and Evolution, vol. 5, no. 4, pp. 336–343, 2014. 
[13] A. Baddeley, R. Turner, et al., “Spatstat: an r package for analyzing spatial point patterns,” Journal of statistical software, vol. 12, no. 6, pp. 1–42, 2005. 
[14] B. Vilela and F. Villalobos, “letsr: a new r package for data handling and analysis in macroecology,” Methods in Ecology and Evolution, vol. 6, no. 10, pp. 1229–1234, 2015. 
[15] E. Conlisk, J. Conlisk, and J. Harte, “The impossibility of estimating a negative binomial clustering parameter from presence-absence data: a 23 comment on he and gaston,” The American Naturalist, vol. 170, no. 4, pp. 651–654, 2007.