USGS - science for a changing world

Northern Prairie Wildlife Research Center

  Home About NPWRC Our Science Staff Employment Contacts Common Questions About the Site

Using Known Populations of Pronghorn to Evaluate
Sampling Plans and Estimators


Kathy M. Kraft1, Douglas H. Johnson2, Jack M. Samuelson3, and Stephen H. Allen4


Abstract: Although sampling plans and estimators of abundance have good theoretical properties, their performance in real situations is rarely assessed because true population sizes are unknown. We evaluated widely used sampling plans and estimators of population size on 3 known clustered distributions of pronghorn (Antilocapra americana). Our criteria were accuracy of the estimate, coverage of 95% confidence intervals, and cost. Sampling plans were combinations of sampling intensities (16, 33, and 50%), sample selection (simple random sampling without replacement, systematic sampling, and probability proportional to size sampling with replacement), and stratification. We paired sampling plans with suitable estimators (simple, ratio, and probability proportional to size). We used area of the sampling unit as the auxiliary variable for the ratio and probability proportional to size estimators. All estimators were nearly unbiased, but precision was generally low (overall [mean of x] coefficient of variation [CV] = 29). Coverage of 95% confidence intervals was only 89% because of the highly skewed distribution of the pronghorn counts and small sample sizes, especially with stratification. Stratification combined with accurate estimates of optimal stratum sample sizes increased precision, reducing the mean CV from 33 without stratification to 25 with stratification; costs increased 23%. Precise results ([mean of x] CV = 13) but poor confidence interval coverage (83%) were obtained with simple and ratio estimators when the allocation scheme included all sampling units in the stratum containing most pronghorn. Although areas of the sampling units varied, ratio estimators and probability proportional to size sampling did not increase precision, possibly because of the clumped distribution of pronghorn. Managers should be cautious in using sampling plans and estimators to estimate abundance of aggregated populations.

Key words: aerial survey, Antilocapra americana, North Dakota, population estimation, pronghorn, strip transect.


This resource is based on the following source (Northern Prairie Publication 0923):
Kraft, Kathy M., Douglas H. Johnson, Jack M. Samuelson, and Stephen H. Allen.  
     1995.  Using known populations of pronghorn to evaluate sampling plans 
     and estimators.  Journal of Wildlife Management 59(1):129-137.

This resource should be cited as:

Kraft, Kathy M., Douglas H. Johnson, Jack M. Samuelson, and Stephen H. Allen.  
     1995.  Using known populations of pronghorn to evaluate sampling plans 
     and estimators.  Journal of Wildlife Management 59(1):129-137.
     Jamestown, ND: Northern Prairie Wildlife Research Center Online.  
     http://www.npwrc.usgs.gov/resource/mammals/sampplan/index.htm  
     (Version 26JAN2001).

Table of Contents

Tables


1 National Biological Survey, Northern Prairie Science Center, Jamestown, ND 58401, USA
   Present address: 6059 Jamestown College, Department of Mathematics, Jamestown, ND 58405, USA.
2 National Biological Survey, Northern Prairie Science Center, Jamestown, ND 58401, USA
3 North Dakota Game and Fish Department, Mott, ND 58646, USA
4 North Dakota Game and Fish Department, Bismarck, ND 58501, USA
Downloading Instructions -- Instructions on downloading and extracting files from this site.
(Download) sampplan.zip ( 51K) -- Using Known Populations of Pronghorn to Evaluate Sampling Plans and Estimators Installation: Extract all files and open index.htm in a web browser.

Accessibility FOIA Privacy Policies and Notices

Take Pride in America logo USA.gov logo U.S. Department of the Interior | U.S. Geological Survey
URL: http://www.npwrc.usgs.gov/resource/mammals/sampplan/index.htm
Page Contact Information: Webmaster
Page Last Modified: Saturday, 02-Feb-2013 05:55:02 EST
Sioux Falls, SD [sdww55]