[ABE-L] Seminário DEST/UFMG em 23/06/2023

[Marcos Prates]

Caros,

Na próxima sexta-feira (23 de Junho, às 13:30h) o ciclo de Seminários do
Departamento de Estatística da UFMG terá a apresentação do prof. Michael
Willig da UConn.

Michael Willig is a Board of Trustees Distinguished Professor of Ecology &
Evolutionary Biology, Director of the Center for Environmental Sciences &
Engineering, and Executive Director of the Institute of the Environment at
the University of Connecticut. He graduated summa cum laude, with a BS in
Biology from the University of Pittsburgh. Thereafter, he obtained a PhD in
Biological Sciences, with an emphasis in Ecology, at the same institution.
Prior to coming to UConn, he was the Director of NSF’s Division of
Environmental Biology and a Program Officer in the Ecology Program. In
addition, he served as the Chair of the Department of Biological Sciences
and Director of the Institute of Environmental Studies at Texas Tech
University. Throughout his career, Dr. Willig has focused on integrating
research and education with respect to long-term and broad-scale
environmental issues, sustainable management of biodiversity, and
disturbance ecology. He has published over 250 peer reviewed scientific
articles, and is the author or editor of eight books or monographs. He has
mentored scores of undergraduates, 25 MS students, 13 PhD students, and 12
post-doctoral fellows, as well as a number of visiting scholars from
Argentina, Belgium, Brazil, and Israel. He has received 10s of millions
dollars of grant support for his research from a variety of federal (i.e.,
NSF, NIH, USDA, EPA, DoD, and DoE) and state agencies. Of particular note,
he has enjoyed 30 years of continuous funding from NSF as part of the
Luquillo Mountains Long-Term Ecological Research project in Puerto Rico.
Based on three decades of research on populations, communities, and
metacommunities, he received funding from NSF’s OPUS program, to synthesize
theoretical and empirical understanding about the spatio-temporal responses
of biodiversity to climate-related disturbances (e.g., hurricanes and
droughts). Most recently, Dr. Willig was the recipient of the Merriam Award
from the American Society of Mammalogists in recognition of his enduring
and foundational contributions to the scientific study of mammals.

Título: Exploring Phenological Patterns in Ecology: Circular Statistics,
Methodological Concerns, and Bootstrap Approaches

Resumo: A major thrust of ecological research focuses on characterizing
spatial and temporal variation in biologically relevant characteristics,
and understanding its causes and consequences. Phenological studies
quantify the timing of biological events at any level in the biological
hierarchy from individuals to ecosystems. In particular, reproductive
phenologies (e.g., patterns regarding the number of pregnant females or
number of fruiting trees) are subject to intense selection pressures, as
the timing of birth, pollination, seed production, or recruitment of young
into populations is linked intimately to fitness and are constrained by
availability of resources or likelihood of multiple interspecific
interactions associated with predation, competition, and mutualism.
Consequently, considerable research has focused on the description of
reproductive phenologies and the development of quantitative approaches for
uncovering the nature of annual patterns. Generally, valuations of temporal
patterns can be undertaken based on two approaches: (1) those that explore
monotonic, linear, or curvilinear relationships (i.e., much of parametric
or non-parametric statistics); or (2) those that incorporate periodicity
when a temporal characteristic is measured on an interval scale, but the
designation of high or low values is arbitrary (i.e., circular statistics).
Unfortunately, approaches in circular statistics are not appropriate when
marginal totals (e.g., number of observations per time interval, a) arise
as a consequence of sampling effort or sampling success, which effectively
constrains the number of individuals in any reproductive category for any
value of a. Moreover, in some experimental designs involving annual
reproductive phenologies, a demographic response variable is actually
multinomial or at least binomial (e.g., pregnant versus not pregnant), and
failure to include this inherent categorical characteristic of the response
could lead to inaccurate conclusions. In such sampling designs, the number
of pregnant females associated with each value of a depends on two
characteristics: (1) the proportion of females in the population that is
pregnant at interval a, and (2) the number of individuals, pregnant or not
pregnant, that were captured in a particular month (interval a).
Consequently, heterogeneity in sample sizes, especially if some samples are
small for particular values of a, is problematic. In this talk, we present
results of an ongoing project designed to (1) demonstrate, via a number of
exemplar data sets, how application of classical circular statistics in
some designs can lead to erroneous and counterintuitive conclusions; (2)
develop a boot-strap approach to overcome limitations associated with
marginal totals; (3) apply this boot-strap approach to the exemplar data
sets to highlight its salient improvement; and (4) apply both circular
statistics (i.e., Rayleigh and Hermans-Rasson Tests) and the proposed
boot-strap approach to reproductive phenologies derived from well-studied
mammal species from the Amazon of Peru. Finally, we wish to promote
collaborations between statisticians and ecologists to address questions in
temporal biology.

O seminário será transmitido ao vivo pelo canal do Youtube "Seminários DEST
- UFMG <https://www.youtube.com/@seminariosdest-ufmg>".

https://www.youtube.com/@seminariosdest-ufmg

Att,
Marcos Prates
-------------- Próxima Parte ----------
Um anexo em HTML foi limpo...
URL: <http://lists.ime.usp.br/pipermail/abe/attachments/20230621/69371611/attachment.htm>