BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Bayesian modelling on the expected extinction time of species.
DTSTART;VALUE=DATE-TIME:20180709T021000Z
DTEND;VALUE=DATE-TIME:20180709T023000Z
DTSTAMP;VALUE=DATE-TIME:20241107T214704Z
UID:indico-contribution-342@conferences.maths.unsw.edu.au
DESCRIPTION:Speakers: Saritha Kodikara (Discipline of Mathematical Science
s\, School of Science\, RMIT University\, Melbourne\, Australia)\nIn this
study\, we propose a new Bayesian approach to calculate the expected extin
ction time of a species based on historical sighting record data. Unlike o
ther work\, our model allows comprehensively for uncertainties\, provides
the expected extinction time and the probability of extinction. It is ex
tremely difficult to determine whether a species is extinct based on histo
rical sighting records because knowing whether the last surviving individu
al of a species has finally died\, or is just unobserved\, remains proble
matical. Moreover\, an incorrect classification of a species as extinct c
an lead to failure in conserving a threatened species. On the other hand\,
it is also undesirable to classify a species as extant when it is actuall
y extinct as it can lead to misallocation of funds. Sightings with uncerta
in validity (uncertain sightings) play an important role in the inferences
made and need to be taken into account better than they have been. Recen
t studies have considered uncertain sightings while making inferences abou
t extinction\; however\, the difficulty of the problem requires making a n
umber of limiting assumptions that significantly reduce realism. We have a
ttempted to derive a more general model by incorporating sighting validity
into a new Bayesian model development. We employ the underlying idea of t
he beta-geometric/beta-binomial (BG/BB) model to build our Bayesian approa
ch for the analysis of extinction. Using the likelihood for the sighting d
ata\, along with the prior distributions of sighting probability and extin
ction probability\, we calculate the expected extinction time using a Mark
ov Chain Monte Carlo (MCMC) method which we simulate with JAGS. We apply t
his new approach to the sighting records of Caribbean monk seal (CMS)\, Do
do and Ivory-Billed Woodpecker species. Unlike other approaches that consi
der uncertainties in the sightings\, our model gives Bayesian confidence i
ntervals for the expected extinction time of a species.\n\nhttps://confere
nces.maths.unsw.edu.au/event/2/contributions/342/
LOCATION:University of Sydney New Law School/--028
URL:https://conferences.maths.unsw.edu.au/event/2/contributions/342/
END:VEVENT
END:VCALENDAR