An Improved Estimator for the Number of Landowners Along a Railroad Right of Way

• Activity Number: 527
• Type: Contributed
• Date/Time: Wednesday, August 3, 2011 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistical Consulting
• Author(s): Marcus Nunes*+ and James Rosenberger and Durland L. Shumway
• Companies: Penn State University and Penn State University and Penn State University
• Keywords: sampling ; estimation ; rails-to-trails ; simulation

Abstract

There are real-life situations where we are interested to know the number of experimental units that share a certain characteristic. In this work, a rails-to-trails organization would like to investigate the likelihood that property owners along an abandoned rail line would cooperate on converting the right of way to a hiking trail. However, finding the number of unique landowners of all segments is time consuming and expensive. The organization proposed a multi-sample procedure, based on the well-known Horvitz-Thompson estimator, to estimate the total number of landowners along the line. The sampling frame is based on a map with probability of landowner selection proportional to the length of each railroad segment traversing a single land parcel. Simulation studies show that this estimator is biased. We investigate another estimator, based on the same samples, which demonstrates better performance. This new estimator, with a bootstrap margin of error, is nearly unbiased, consistent and has lower MSE for estimating the total number of adjacent landowners, which is illustrated with several simulated situations.