BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:iCalendar-Ruby
BEGIN:VEVENT
CATEGORIES:Lecture or Presentation
DESCRIPTION:Topic: Truncated latent Gaussian copula model for zero-inflated
data\n\n \n\nDate:\n\nMonday\, January 13\, 2020\n\n \n\nSpeaker:\n\nDr. I
rina Gaynanova\, Assistant Professor\,\n\nTexas A & M University\n\n \n\nTe
a and refreshments with faculty and speaker:\n\n3:00pm to 3:45 pm in Wenige
r Room 245\n\n \n\nSeminar: \n\n4:00pm in Weniger Hall Room 149\n\n \n\nCos
t: \n\nThis seminar is open to the public\n\nAbstract:\n\nA great number of
multivariate statistical methods\, such as principal component analysis\,
discriminant analysis\, canonical correlation analysis and graphical lasso
to name a few\, require the estimate of covariance or correlation matrix of
variables as one of the inputs. It is typical to use Pearson sample correl
ation matrix\, which works well at capturing dependencies between normally
distributed variables. In this work we consider the problem of estimating d
ependencies between zero-inflated measurements\, which arise in miRNA data\
, microbiome data\, physical activity data\, etc. We propose truncated late
nt Gaussian copula to model the data with excess zeroes\, which allows us t
o derive a rank-based estimator of latent correlation matrix without the es
timation of marginal transformation functions. We prove the consistency of
corresponding estimator\, and demonstrate its use for the analysis of assoc
iations between gene expression and microRNA data of breast cancer patients
\, and for inferring the conditional independence graph in quantitate gut m
icrobiome data.
DTEND:20200114T005000Z
DTSTAMP:20201025T173657Z
DTSTART:20200114T000000Z
GEO:44.567877;-123.27751
LOCATION:Weniger Hall\, 245
SEQUENCE:0
SUMMARY:Statistics Research Seminar
UID:tag:localist.com\,2008:EventInstance_32381144326597
URL:https://events.oregonstate.edu/event/statistics_research_seminar_4746
END:VEVENT
END:VCALENDAR