Hi all, I need to sub sample some large data sets. The problem is using complete data samples for bats that are ? data per 1-minute time blocks using acoustic data collection and a method I published some time back. Miller, B. W. 2001. A method for determining relative activity of free flying bats using a new activity index for acoustic monitoring. Acta Chiropterologica. 3: 93-105. I am convinced after analyzing complete data for each night to derive relative abundance and species compositions that the consultants who are doing wind power monitoring and ONLY using 5 to 10 minute sub samples for each hour like the first 5 or 10 minutes are missing especially eh rare species that have only a few occurrences so misleading results. Anyone have any suggestions to a field ecologists who is not a dyed in the wool stats person on how to sub sample the data sets and robustly test this hypothesis? Happy to co-author a paper if some one is interested as I have the data. Cheers, Bruce -- Bruce W. Miller, Ph.D. Conservation Ecologist Neotropical Bat Projects office details 11384 Alpine Road Stanwood, Mi. 49346 Phone (231) 679-6059