A NOVEL AND SIMPLE RULE OF THUMB FOR MULTIPLICITY CONTROL IN EQUIVALENCE TESTING USING TWO ONE-SIDED TESTS

Equivalence testing is growing in use in scientific research outside of its traditional role in the drug approval process. Largely due to its ease of use and recommendation from the United States Food and Drug Administration guidance, the most common statistical method for testing (bio)equivalence is the two one-sided tests procedure (TOST). Like classical point-null hypothesis testing, TOST is subject to multiplicity concerns as more comparisons are made. In this manuscript, a condition that bounds the family-wise error rate (FWER) using TOST is given. This condition then leads to a simple solution for controlling the FWER. Specifically, we demonstrate that if all pairwise comparisons of k independent groups are being evaluated for equivalence, then simply scaling the nominal Type I error rate down by (k - 1) is sufficient to maintain the family-wise error rate at the desired value or less. The resulting rule is much less conservative than the equally simple Bonferroni correction. An example of equivalence testing in a non drug-development setting is given.

The duration of capture and restraint during anesthesia and euthanasia influences glucocorticoid levels in male golden hamsters

Deep litter has been shown to decrease stereotypic wire-gnawing in male golden hamsters, suggesting that increased litter depth may be associated with decreased chronic stress levels. To determine the relationship between litter depth and stress levels in hamsters, the authors measured serum levels of corticosterone, cortisol, and ACTH in male golden hamsters kept in cages with three different depths of litter. The duration of handling the hamsters significantly increased the concentrations of corticosterone, cortisol, and the ratio of cortisol/corticosterone. It took longer to catch hamsters housed in cages with deep litter and the ACTH levels were higher in these hamsters. The positive effect of the enrichment (deep litter) was diminished by methodological problems during handling/anesthesia.

Golden-winged Warbler habitat model validation for northern Wisconsin and central Minnesota

Between 1966 and 2003, the Golden-winged Warbler (Vermivora chrysoptera) experienced declines of 3.4% per year in large parts of the breeding range and has been identified by Partners in Flight as one of 28 land birds requiring expedient action to prevent its continued decline. It is currently being considered for listing under the Endangered Species Act. A major step in advancing our understanding of the status and habitat preferences of Golden-winged Warbler populations in the Upper Midwest was initiated by the publication of new predictive spatially explicit Golden-winged Warbler habitat models for the northern Midwest. Here, I use original data on observed Golden-winged Warbler abundances in Wisconsin and Minnesota to compare two population models: the hierarchical spatial count (HSC) model with the Habitat Suitability Index (HSI) model. I assessed how well the field data compared to the model predictions and found that within Wisconsin, the HSC model performed slightly better than the HSI model whereas both models performed relatively equally in Minnesota. For the HSC model, I found a 10% error of commission in Wisconsin and a 24.2% error of commission for Minnesota. Similarly, the HSI model has a 23% error of commission in Minnesota; in Wisconsin due to limited areas where the HSI model predicted absences, there was incomplete data and I was unable to determine the error of commission for the HSI model. These are sites where the model predicted presences and the Golden-winged Warbler did not occur. To compare predicted abundance from the two models, a 3x3 contingency table was used. I found that when overlapped, the models do not complement one another in identifying Golden-winged Warbler presences. To calculate discrepancy between the models, the error of commission shows that the HSI model has only a 6.8% chance of correctly classifying absences in the HSC model. The HSC model has only 3.3% chance of correctly classifying absences in the HSI model. These findings highlight the importance of grasses for nesting, shrubs used for cover and foraging, and trees for song perches and foraging as key habitat characteristics for breeding territory occupancy by singing males.

Habitat Associations of the Golden-Winged Warbler in Honduras

The global population of the Neotropical migrant Golden-winged Warbler (Vermivora chrysoptera) has declined steadily over the past fifty years. While factors influencing this decline have been well researched on the breeding grounds, little is known about the distribution and habitat requirements of this warbler on its stationary non-breeding range. Recent efforts to quantify the non-breeding habitat requirements of this warbler have focused on Colombia and Costa Rica, though the species ranges as far north as the Yucatan Peninsula, Mexico. To address the gap in knowledge from the northern portion of the non-breeding range, I conducted 80 serial point-count surveys targeting Goldenwinged Warblers at eight field sites in Honduras, Central America. I found that Goldenwinged Warblers occupy a greater variety of habitats than previously recognized, including pine-oak forest and semi-deciduous broadleaf forest. I also documented habitat associations that have not been observed in other parts of the non-breeding range with respect to elevation, rainfall, and spatial segregation by sex. These results demonstrate the need to consider the entire non-breeding range in conservation planning, as Goldenwinged Warbler habitat associations appear to vary regionally.

Geology and Ore Deposits of the Golden Era and Goldfinch Mines, Argenta Mining District, Montana.

This report includes the results of geological investigation of a small area in the northern part of the Argenta mining district. Approximately two square miles were mapped. The underground working of the three mines only were accessible: the Goldfinch. Golden Era, and Mayday mines.

Geology and Ore Deposits of the Golden Messenger MIne, Lewis and Clark County, Helena, Montana.

The Golden Messenger Mine which is approximately twenty-three miles northeast of Helena, Montana, near York, on Trout Creek, has long presented several problems of both theoretical and practical interest.

Geology of the Golden Sunlight Mine and Vicinity

The Golden Sunlight Mine is in the northern part of the Cardwell mining district on the eastern slope of a small range that rises by a series of benches to an elevation of 7,200 at a point five miles east of the town of Whitehall in Jefferson County.

A Report of the Geology of the Golden Sunlight Mining District

This paper is a report of a geological survey made of an area of approximately fifty square miles lying Northeast of Whitehall, Montana, in the region of the Golden Sun­light Mine. The survey was made by a field party consisting of twenty-three members of the senior class of the Montana School of Mines.