Portal de Periódicos da CAPES

Refinements in Scent-Station Methodology for Assessing Trends in Carnivore Populations

1982; Wiley; Volume: 46; Issue: 1 Linguagem: Inglês

10.2307/3808424

1937-2817

Robert D. Roughton, Mark W. Sweeny,

Archaeology and Natural History

The scent-station index method used by the U.S. Fish and Wildlife Service (USFWS) and others is a practical means for determining trends in carnivore populations. Suggested refinements of the USFWS standard procedure to improve efficiency include (1) use of an inexpensive plaster disc saturated with attractant, permitting rapid volatilization; (2) lines of 10 scent stations operated for 1 night to increase sample sizes, enhance sampling distribution, and minimize weather interference; and (3) computer analysis of data by a program incorporating the Fisher Randomization Test and Wilcoxon Signed Rank Test, which avoid unwarranted assumptions and yield greater sensitivity to changes in visitation rates than that afforded by the Z test used previously. The Fisher Randomization Test is a particularly powerful and efficient tool. The computer program, applicable to any paired data, is described. Scent-station survey recommendations based on these refinements and our experience are given. J. WILDL. MANAGE. 46(1):217-229 Interest in carnivore, especially coyote (Canis latrans), ecology and management dictates a need for assessing carnivore abundance. Because direct enumeration of the animals is impractical, the U.S. Fish and Wildlife Service, in its West-wide survey of predator abundance, assesses trends on the basis of animal visitation to lines of artificial scent stations. Each station is a circle of sifted earth having, in the center, a perforated plastic capsule filled with an odor attractant. Tracks visible in the sifted earth are recorded and smoothed over daily by an observer (Linhart and Knowlton 1975, Roughton and Sweeny 1979). Efficiency and reliability of the scentstation method are influenced by the quality and quantity of the odor attractant used, method of presentation, sampling design, and sensitivity of the data analysis. Attractant quality and the selection of fatty acid scent (FAS) are discussed in a companion paper (Roughton 1982). The presen paper reports upon tests of (1) volatilization rates of FAS from several substrates, (2) several methods of presenting FAS at scent stations, (3) relative s atistical and time efficiencies of several sampling designs (i.e., combinations of number of stations per line 'and number of nights the lines are in operation), and (4) alternative methods of analysis for inferring differences in visitation rates. The final section summarizes our recommendations from these studies and 8 years of experience with the scent-station method. The first 2 objectives were directed at increasing scent-station visitation, to reduce the estimate of variance in comparing results from different sampling periods (Hodges 1975). Theoretically, the optimal range for detecting percent change in visitation rates is 40-60% (D. Anderson and C. Romesburg, pers. commun.), well above the West-wide average of 10% for the USFWS survey. Conjecture about the influence of the amount of attractant released into the atmosphere led to studies of volatilization rates, even though we do not understand the inter1 Present address: Brigantine National Wildlife Refuge, U.S. Fish and Wildlife Service, Oceanville, NJ 08231. J. Wildl. Manage. 46(1):1982 217 This content downloaded from 157.55.39.159 on Sun, 18 Sep 2016 06:27:00 UTC All use subject to http://about.jstor.org/terms 218 SCENT-STATION METHODOLOGYRoughton and Sweeny action between quality (in terms of odor components) and quantity (in terms of molecules/m3 of air vs. thresholds of detection). Originally, a plastic capsule served to protect the powdered attractant and limited the amount used at station. These capsules are expensive, accounting for 65% of the material costs (Roughton 1980), and are inconvenient to use. We sought a better and less costly device for presenting attractant. The 3rd objective related to optimizing the sampling effort within manpower and road-network constraints. The current design (Roughton and Sweeny 1979) employs lines of 50 scent stations observed for 4 days. Because stations are only 0.5 km apart and coyotes occasionally visit consecutive stations, stations cannot be regarded as independent sampling units. Likewise, field observation and scrutiny of visitation patterns in our survey data suggested individual carnivores may visit the same (or nearby) stations on more than 1 night, so nights are also not independent sampling units. For analytical purposes, the interrelationship of scentstation visits spatially and among nights delimits the sampling unit as each line of 50 stations run for 4 days (a 50 x 4 line). Because observer checks, at most, 2 lines in a week, the maximum data yield is 2 sampling units/man-week. Increased sampling efficiency seemed desirable. The 4th objective was to determine the most powerful appropriate statistical test for scent-station data. The only statistical analyses routinely performed for our survey are statewide and West-wide comparisons of coyote visitation rates for succeeding years. Coyote trend analyses for areas within states are legitimate, but would not yield useful results because of inadequate sample sizes. Even at the statewide level, statistically significant changes in coyote visitation are rarely detected between years, even though the percent changes are sometimes striking. We believe this results from inadequate sample sizes under the current survey design and an inherent lack of power in the Z test applied to the USFWS survey data. The Z test (Roughton and Sweeny 1979) assumes that: the survey lines are independent, which they are; the data are normally distributed, which is uncertain; and the variance for a given line is homogeneous from year to year, which is likely only under stable population conditions. The rarity of stable conditions is the root of the problem, because the estimated variance for a given line is based on the data for all years in which that line was run, even though part of the year-toyear variability may result from true changes in population density, the parameter we are trying to estimate. We believe this test lacks satisfactory power to detect the year-to-year changes (which are of primary interest), requires dubious assumptions, and relies upon overly conservative estimates of variance. We thank C. E. Harris, J. T. Roughton, B. G. Wagner, Jr., and L. D. Walker for assistance in data collection; D. Alexander, C. Becenti, M. Kaschke, E. Olson, C. D. Sykes, M. Walker, J. Wilbrecht, and L. A. Windberg for cooperation and advice in selecting study areas; D. C. Bowden, J. I. Hodges, K. Marshall, and C. Romesburg for advice and assistance in statistical analysis and computer programming; and F. F. Knowlton and L. C. Stoddart for criticism of the manuscript.